Statistical method and display method for target object, and computer device, aircraft, control terminal and storage medium
By acquiring high-resolution images using an imaging device mounted on an aircraft and adjusting its attitude to capture multiple sub-region images, the high investment and statistical inaccuracies caused by the deployment of hardware equipment in existing technologies are solved, achieving efficient and accurate target object statistics.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SZ DJI TECH CO LTD
- Filing Date
- 2024-11-22
- Publication Date
- 2026-05-28
AI Technical Summary
In existing technologies, target object statistics require the pre-deployment of hardware equipment on site, resulting in a large investment of manpower and resources, and unreasonable equipment location can affect the accuracy of statistical results.
By using an imaging device mounted on the aircraft, a second image with a higher resolution than the initial image is acquired, the target object is identified and statistical information is determined, and multiple images of different sub-regions are taken from the same position by adjusting the aircraft's attitude, thus avoiding large-scale movement.
It reduces the need for hardware deployment, improves the flexibility and accuracy of statistics, saves material and human resources, and achieves efficient and accurate target object recognition and statistics through high-resolution images and posture adjustment.
Smart Images

Figure CN2024133979_28052026_PF_FP_ABST
Abstract
Description
Statistical methods, display methods, computer equipment, aircraft, control terminals, and storage media of the target object Technical Field
[0001] This application relates to the field of aircraft technology, and more specifically, to a statistical method, display method, computer equipment, aircraft, control terminal, and computer-readable storage medium for a target object. Background Technology
[0002] In related technologies, statistics involving target objects have practical application needs in various industries, providing effective reference value for decision support, resource allocation, and operational optimization.
[0003] Target object statistics typically require the pre-deployment of necessary hardware equipment in the relevant site. This involves multiple aspects, including equipment configuration, installation, debugging, maintenance, and daily management and data processing. Especially in large-scale scenarios, this often requires a significant investment of manpower and resources. Furthermore, if the equipment is not deployed appropriately in the site, such as being installed too low or at an inaccurate angle, the statistical results may be inaccurate. Summary of the Invention
[0004] In view of this, this application provides a statistical method for the target object, a display method, a computer device, an aircraft, a control terminal, and a computer-readable storage medium.
[0005] In a first aspect, embodiments of this application provide a statistical method for a target object, comprising: selecting a target region in a first image, wherein the target region contains a target object; controlling an imaging device mounted on an aircraft to take a picture toward the target region to obtain a second image; identifying the target object in the second image; and determining statistically relevant information of the target object in the second image based on the identified target object; wherein the resolution of the second image is greater than the resolution of the first image.
[0006] The beneficial effects are at least as follows: Selecting the target area from the first image, controlling the aircraft's imaging device to capture a second image of the target area, and identifying the target object in the second image facilitates the statistical analysis of relevant information about the target object. Specifically, the first image facilitates focusing on the target area to be analyzed; the second image has a higher resolution than the first image, which is beneficial for acquiring local detail information, thereby improving the accuracy of target object identification and statistical analysis.
[0007] Secondly, embodiments of this application provide a method for displaying a target object, comprising: displaying a first image on a user interface; displaying a selected target area on the first image, wherein the target area contains a target object; and displaying statistical information related to the target object on the user interface; wherein the statistical information related to the target object is determined based on a second image, the second image being acquired by an imaging device mounted on an aircraft taking pictures of the target area, and the resolution corresponding to the second image being greater than the resolution corresponding to the first image.
[0008] The beneficial effects are at least as follows: the first image makes it easier to focus on the target area that needs to be statistically analyzed; the resolution of the second image is greater than that of the first image, which is conducive to the acquisition of local detail information, so as to improve the accuracy of target object identification and statistics; and by displaying statistical information on the user interface, users can understand the statistical situation of the target object more quickly and intuitively.
[0009] Thirdly, embodiments of this application provide a method for statistical analysis of target objects, comprising: selecting a target region in a first image, wherein the target region contains a target object, and the target region includes multiple sub-regions; controlling an aircraft to fly to one or more preset positioning positions based on location-related information of the target region; and controlling an imaging device mounted on the aircraft to adjust its attitude to capture images of the multiple sub-regions respectively while the aircraft is at one or more preset positioning positions, thereby acquiring multiple second images; wherein the multiple second images include a second image A and a second image B, and the second image A and the second image B are captured when the aircraft is at the same preset positioning position. The acquisition includes two images: second image A, acquired by the imaging device in a first orientation toward the target region; and second image B, acquired by the imaging device in a second orientation toward the target region, wherein the first orientation differs from the second orientation, and the sub-region covered by second image A is at least partially different from the sub-region covered by second image B; identifying the target object in multiple second images; and determining statistically relevant information of the target object in multiple second images based on the identified target object; wherein the field of view of the second image is smaller than the field of view of the first image, and the resolution of the second image is greater than the resolution of the first image.
[0010] The beneficial effects are at least as follows: By selecting the target region in the first image and maintaining the aircraft at the same preset positioning position, multiple second images of different sub-regions within the target region can be captured by adjusting the attitude of the aircraft's imaging device. This allows for fixed-point imaging within multiple different sub-regions without requiring extensive aircraft movement, facilitating the determination of statistical information related to the target object within these sub-regions. This approach is time-saving, efficient, and power-saving. Furthermore, the field of view of the first image is larger than that of the second image, which is beneficial for acquiring overall global information and focusing on the target region requiring statistical analysis. The resolution of the second image is greater than that of the first image, which is beneficial for acquiring local detail information, thereby improving the accuracy of target object identification and statistical analysis.
[0011] Fourthly, embodiments of this application provide a method for displaying a target object, comprising: displaying a first image on a user interface; displaying a selected target area on the first image, the target area containing a target object, the target area including multiple sub-areas; displaying statistical information related to the target object on the user interface; wherein the statistical information related to the target object is determined based on a second image A and a second image B, the second image A being acquired by controlling an imaging device mounted on the aircraft to take pictures toward the target area in a first posture when the aircraft is located at a preset positioning position, the second image B being acquired by controlling an imaging device mounted on the aircraft to take pictures toward the target area in a second posture when the aircraft is located at the same preset positioning position, the first posture being different from the second posture, the sub-areas covered by the second image A and the sub-areas covered by the second image B being at least partially different; and the field of view angles corresponding to the second image A and the second image B are both smaller than the field of view angle corresponding to the first image, and the resolutions corresponding to the second image A and the second image B are both greater than the resolution corresponding to the first image.
[0012] The beneficial effects are at least as follows: The first image facilitates focusing on the target area to be statistically analyzed; the field of view of the first image is larger than that of the second image, which is beneficial for acquiring overall global information and thus facilitating focusing on the target area. The resolution of the second image is higher than that of the first image, which is beneficial for acquiring local detail information, thereby improving the accuracy of target object identification and statistical analysis. Displaying statistical information on the user interface helps users quickly and intuitively understand the statistical status of the target object. Furthermore, by selecting the target area in the first image and maintaining the aircraft at the same preset positioning position, multiple second images of different sub-regions within the target area can be captured by adjusting the attitude of the aircraft's imaging device. This allows for fixed-point shooting within multiple different sub-regions without requiring extensive aircraft movement, facilitating the determination of statistical information related to the target object in multiple sub-regions, saving time, increasing efficiency, and conserving power.
[0013] Fifthly, embodiments of this application provide a computer device, including: at least one processor; and at least one memory including computer program code; wherein at least one of the memory and the computer program code are configured together with the at least one processor to enable the computer device to perform at least the methods described in the first aspect, the second aspect, the third aspect, or the fourth aspect.
[0014] In a sixth aspect, embodiments of this application provide an aircraft, comprising: at least one processor; and at least one memory including computer program code; wherein at least one of the memory and the computer program code are configured together with the at least one processor to enable the computer device to perform at least the statistical methods described in the first or third aspect.
[0015] In a seventh aspect, embodiments of this application provide a control terminal, comprising: at least one processor; and at least one memory including computer program code; wherein at least one of the memory and the computer program code are configured together with the at least one processor to enable the computer device to execute at least the display method described in the second or fourth aspect.
[0016] Eighthly, embodiments of this application provide a system comprising the aircraft described in the sixth aspect and the control terminal described in the seventh aspect.
[0017] Ninthly, embodiments of this application provide a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the method described in any one of the first, second, third, or fourth aspects. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of this application;
[0020] Figure 2 is a schematic diagram of a process for obtaining statistical information about a target object according to an embodiment of this application;
[0021] Figure 3 is a flowchart illustrating a statistical method for a target object provided in an embodiment of this application;
[0022] Figure 4 is a schematic diagram of the first image, the target area and its multiple sub-regions provided in the embodiments of this application;
[0023] Figure 5 is a schematic diagram of the second image A and the second image B corresponding to different sub-regions provided in the embodiments of this application;
[0024] Figure 6 is a schematic diagram of a shooting sequence provided in an embodiment of this application;
[0025] Figure 7 is a schematic diagram of another shooting sequence provided in an embodiment of this application;
[0026] Figure 8 is a schematic diagram of a target area and the center of each sub-region provided in an embodiment of this application;
[0027] Figure 9 is a schematic diagram of the coverage area of a target region and its sub-regions corresponding to a second image provided in an embodiment of this application;
[0028] Figure 10 is a schematic diagram of the coverage area of a second image corresponding to another target region and its various sub-regions provided in an embodiment of this application;
[0029] Figure 11A is a schematic diagram showing statistical information related to a target object according to an embodiment of this application;
[0030] Figure 11B is a schematic diagram of displaying statistically relevant information of a target object using a heatmap according to an embodiment of this application;
[0031] Figure 11C is a schematic diagram of another heat map displaying statistically relevant information of a target object provided in an embodiment of this application;
[0032] Figure 12 is a schematic diagram illustrating another method for displaying statistically relevant information of a target object, provided in an embodiment of this application.
[0033] Figure 13 is a flowchart illustrating a method for displaying a target object according to an embodiment of this application;
[0034] Figure 14 is a flowchart illustrating another statistical method for a target object provided in an embodiment of this application;
[0035] Figure 15 is a flowchart illustrating another method for displaying a target object provided in an embodiment of this application;
[0036] Figure 16 is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation
[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0038] Based on the problems in related technologies, this application provides a statistical method, display method and related equipment for target objects. Image data can be collected by an imaging device mounted on an aircraft, and then statistical information related to the target object can be determined through the image data. This eliminates the need to deploy a large number of additional hardware devices on site, reduces the investment of material and human resources, and avoids the limitation of fixed installation positions of hardware devices due to the flexibility of aircraft, thereby improving the flexibility and accuracy of statistics.
[0039] The statistical method for the target object provided in this application embodiment can be executed by a computer device. For example, the computer device includes, but is not limited to, at least one of the following: an aircraft, and the aircraft's control terminal.
[0040] From a structural perspective, aircraft can include rotorcraft, fixed-wing aircraft, unmanned helicopters, or hybrid fixed-wing / rotorcraft. Rotorcraft can be single-rotor, dual-rotor, tri-rotor, quadcopter, hexacopter, octocopter, decacopter, or dodeccopter. From an application perspective, aircraft can include, but are not limited to, manned aircraft, logistics aircraft, aerial photography aircraft, agricultural plant protection aircraft, and industry rescue aircraft. From a control method perspective, aircraft can include unmanned aircraft and manned aircraft. The above are merely illustrative examples, and this application does not impose specific limitations on the type of aircraft.
[0041] A control terminal is a device used to control and operate an aircraft, typically with the ability to communicate with the aircraft. The types and configurations of control terminals vary depending on the aircraft's purpose and technical requirements. Control terminals include, but are not limited to, remote controllers, tablets, laptops, mobile phones, motion-sensing control devices, and wearable devices (such as head-mounted glasses, watches, wristbands, and headsets).
[0042] In the embodiments of this application, the statistical methods for the target object can be performed entirely on the aircraft side, entirely on the aircraft control terminal side, or partially on the aircraft side and partially on the aircraft control terminal side.
[0043] In the embodiments of this application, the method for displaying the target object can be executed entirely on the aircraft side, entirely on the aircraft control terminal side, or some steps can be executed on the aircraft side and some steps can be executed on the aircraft control terminal side.
[0044] In some embodiments, please refer to Figures 1 and 2, which illustrate a possible application scenario. The imaging device 20 mounted on the aircraft 10 takes a picture of a designated location to obtain a first image, which is then sent to a control terminal 30. The user interface of the control terminal 30 displays the first image. Based on a first input operation by the user on the first image, such as a box selection operation, a target area in the first image can be selected. The user interface of the control terminal 30 can display the selected target area in the first image and send the selected target area to the aircraft 10. The imaging device 20 mounted on the aircraft 10 then takes a picture of the target area to obtain at least one second image. The aircraft 10 then identifies a target object in the second image and, based on the identified target object, determines statistical information related to the target object in the second image. The second image, the statistical information related to the target object, etc., are then sent to the control terminal 30 so that the statistical information related to the target object can be displayed in the user interface of the control terminal 30.
[0045] In some embodiments, the target objects to be statistically analyzed in this application include stationary objects. Stationary objects generally refer to objects whose position or state remains substantially unchanged during observation. In some scenarios, statistically analyzing the number or state of stationary objects helps achieve specific monitoring or analysis objectives. For example, statistically analyzing the state of stationary infrastructure such as buildings, billboards, streetlights, and traffic lights in a city can be used for urban management, facility maintenance, and analysis of aging or damaged infrastructure. Similarly, in the natural environment, statistically analyzing stationary natural objects such as trees, mountains, or still water bodies can help ecological researchers monitor environmental changes, the impacts of climate change, or assess the health status of static ecological elements within nature reserves.
[0046] In some embodiments, the target objects to be statistically analyzed in this application include moving objects, which are objects whose position or state changes during the observation period. These dynamic changes are crucial for applications such as traffic monitoring and security analysis. For example, statistically analyzing moving objects on roads, such as vehicles, pedestrians, and bicycles, can enable traffic flow monitoring, traffic signal control optimization, and even the identification and warning of abnormal behaviors (such as driving against traffic or speeding). Furthermore, in public places or high-security areas (such as airports, train stations, and shopping malls), statistically analyzing moving crowds, objects, or potential threats (such as suspicious packages or moving drones) can improve security and ensure rapid response.
[0047] In some embodiments, the target objects to be statistically analyzed in this application include at least one of humans and animals. Humans and animals are two common target objects, respectively involving the monitoring, tracking, or statistical analysis of organisms (whether human or animal). For example, in places such as retail stores, public transportation, and tourist attractions, statistical analysis of pedestrian or crowd behavior can be used to analyze crowd flow trends and for security management, such as identifying congested areas and suspicious behavior. As another example, in wildlife reserves, zoos, or natural habitats, statistical analysis and monitoring of wildlife activity patterns, population sizes, and health status helps researchers in species conservation, habitat protection, and ecosystem management.
[0048] In some embodiments, the target objects to be statistically analyzed in this application include mobile vehicles. A mobile vehicle refers to a means of transportation with mobility. Exemplary examples include vehicles or vessels, but are not limited to these. For instance, statistically analyzing the movement information of mobile vehicles (such as cars, trucks, etc.) on roads can enable real-time traffic monitoring, traffic signal optimization, and traffic accident detection and early warning. Furthermore, in marine monitoring, the activity of mobile vehicles (such as ships, offshore platforms, etc.) can be statistically analyzed to prevent illegal fishing activities, ensure waterway safety, and even conduct maritime rescue missions.
[0049] In some embodiments, please refer to Figure 3, which illustrates a statistical method for a target object. The method includes:
[0050] In S301, a target region containing the target object is selected in the first image.
[0051] For example, the first image may be an image taken by a sensor on board the aircraft, such as an RGB image or a point cloud image.
[0052] For example, the first image could also be a map, such as a topographic map, a raster map, etc.
[0053] Referring to Figure 2, in the first image captured by the aircraft, the user or computer device can select a target area to be statistically analyzed based on existing information. The target area can be selected manually by the user or automatically by the computer device. Selecting a target area helps focus on the statistical area, reduces interference from irrelevant areas, and improves statistical efficiency.
[0054] For example, the first image is displayed on the user interface provided by the control terminal, and the target area is selected by the control terminal in response to the user's first input operation in the first image. The first input operation includes a box selection operation by the user on the user interface. Box selection is an intuitive and simple method; users can accurately select the area of interest by dragging, which is suitable for most users. However, it is not limited to this; the first input operation can also be a click selection operation, a multi-touch operation, etc.
[0055] Alternatively, the first image may be automatically selected by a computer device (such as a control terminal or aircraft), for example, by selecting a specified area, such as the central area or other areas in the first image as the target area, or by selecting the area in the first image where the target object is identified as the target area. This embodiment does not impose any limitations on this.
[0056] In S302, the imaging device on the control aircraft is directed to take pictures of the target area to obtain a second image.
[0057] For example, the aircraft can adjust its attitude in the air to accurately point its onboard imaging device at the target area. The imaging device then captures at least one second image of the target area, the second image having a higher resolution than the first image. The higher resolution of the second image is achieved through methods such as zooming or adjusting the focal length of the imaging device, making the target object clearer in the second image and capturing more details of the target object for subsequent identification and analysis.
[0058] In S303, the target object in the second image is identified.
[0059] For example, computer devices can use image recognition technologies such as machine learning or deep learning algorithms to analyze a second image, identify and locate the target object. Automating the recognition process reduces human intervention and can improve recognition efficiency.
[0060] In S304, based on the identified target object, statistical information related to the target object in the second image is determined; wherein the resolution of the second image is greater than the resolution of the first image.
[0061] For example, based on the recognition results of the target object in the second image, statistical information related to the target object in the second image can be obtained.
[0062] In this embodiment, a target area is selected from the first image, and the imaging device of the aircraft is controlled to shoot towards the target area to obtain a second image. The target object in the second image is then identified to facilitate the statistical analysis of relevant information about the target object. The first image facilitates focusing on the target area to be analyzed; the resolution of the second image is higher than that of the first image, ensuring that the target object is clearly presented, which is beneficial for obtaining local detail information and thus improving the accuracy of target object identification and statistical analysis.
[0063] In this embodiment, the resolution of the second image is greater than the resolution of the first image.
[0064] In one possible implementation, the aircraft carries a first imaging device and a second imaging device. The first imaging device acquires a first image, and the second imaging device acquires a second image, the resolution of which is greater than that of the first image. For example, the first imaging device is suitable for capturing images with a large field of view, providing a relatively global overview and facilitating rapid focusing on the target area to be analyzed after understanding the overall picture. For example, the second imaging device is used to acquire higher-resolution images, suitable for capturing local details and facilitating accurate identification of the target object to be analyzed in the second image.
[0065] For example, the first imaging device includes a wide-angle camera, and the second imaging device includes a telephoto camera. Further, the second imaging device includes a zoom camera, which can adjust the focal length as needed to change the field of view and resolution of the image, enabling image capture at different focal lengths. This camera offers great flexibility, allowing for dynamic adjustment of the viewing angle and focal length without changing the imaging equipment, making it ideal for use in complex and dynamic environments.
[0066] In one possible configuration, the first imaging device and the second imaging device are set up independently. The first imaging device and the second imaging device are installed on the aircraft as independent devices, and may each be equipped with an independent gimbal or mounting bracket, or integrated into the same gimbal.
[0067] In one possible configuration, the first imaging device and the second imaging device are integrated within the same imaging housing, for example, corresponding to different lens modules within the same imaging device. This configuration can reduce the structural complexity of the imaging device, reduce weight and volume, and improve compactness, integration, and lightweighting.
[0068] In one possible configuration, the first imaging device and the second imaging device are integrated on the same gimbal. The synchronous movement of the two imaging devices can be controlled by adjusting the gimbal, thereby reducing the driving complexity of the imaging devices, reducing weight and volume, and improving compactness, integration, and lightweighting.
[0069] In another possible implementation, the aircraft is equipped with an optical zoom camera as its imaging device. This camera captures a first image and a second image, with the second image having a higher resolution than the first image. The optical zoom camera can achieve different optical zooms on a single device without changing lenses or other equipment, improving the aircraft's efficiency and flexibility. It's important to note that optical zoom works by changing the position of optical elements (such as lenses) within the camera lens, adjusting the focal length to control the width of the field of view. The zoom process maintains the optical quality and sharpness of the image. When using optical zoom, users can select different focal lengths and field of view angles to alter the level of detail in the image.
[0070] The first image was taken with an optical zoom camera at a lower focal length. In this case, the optical zoom camera has a wide field of view, capturing a larger area. Typically, such images are suitable for obtaining an overview of the overall environment or scene. For example, when an aircraft is cruising or monitoring, using a lower focal length allows for a quick acquisition of the overall situation of the surrounding environment.
[0071] The second image is taken by an optical zoom camera at a higher focal length. In this case, the optical zoom camera has a narrower field of view, focusing on distant objects and capturing more detail, thus providing higher image resolution. For example, an aircraft might zoom in from a distant target to photograph distant buildings, specific objects, or other detailed parts for more precise analysis.
[0072] In some embodiments, considering that if both the first and second images are captured vertically downwards by the imaging device, the identifiable features of the target object may be limited. For example, if the target object is a person, only local features such as the head and shoulders may be displayed. Such an angle makes it difficult to fully reflect the detailed information of the target object, which will affect the recognition effect. Therefore, in order to further improve the recognition effect of the target object, the imaging device can perform tilted shooting when capturing the first and second images.
[0073] In other words, when capturing the first and second images, the optical axis of the imaging device is not parallel to the yaw axis of the imaging device. By adjusting the angle between the optical axis of the imaging device and the yaw axis, tilt shooting can be achieved, thereby effectively capturing more details and facial features of the target object and improving recognition accuracy.
[0074] Furthermore, the angle between the optical axis of the imaging device and the yaw axis of the imaging device is an acute angle to achieve a tilting effect. By tilting the camera, the imaging device can capture more details and features of the target object, thereby significantly improving the accuracy of target object recognition.
[0075] In some embodiments, the imaging device has at least two different zoom levels. In one possible scenario, the aircraft carries at least two zoom cameras with different zoom levels. In another possible scenario, one imaging device carried by the aircraft is an optical zoom camera with at least two different zoom levels.
[0076] In the process of controlling the imaging device on the aircraft to shoot towards the target area to obtain a second image, the computer device first selects a target zoom level from at least two different zoom levels mentioned above; then, it controls the imaging device on the aircraft to shoot towards the target area at the target zoom level to obtain a second image. By selecting an appropriate target zoom level, details within the target area can be captured more clearly; for example, in scenarios requiring the identification of small or distant targets, a higher zoom level can magnify the target in the image, improving the target's clarity and recognition accuracy. Furthermore, by selecting an appropriate target zoom level, the number of unnecessary second image shots can be reduced; for example, when shooting a large target area, reducing the zoom level to cover a larger area can reduce the complexity of multiple shots and stitching, improving overall efficiency.
[0077] In one possible implementation, a target zoom level can be selected from at least two different zoom levels based on user input. The user input can be performed and received by a control terminal. Manual selection allows users to optimize shooting results based on personal experience and needs, meeting personalized application scenarios.
[0078] In another possible implementation, the target zoom level can be automatically selected from at least two different zoom levels based on preset rules. For example, the target zoom level can be automatically selected from at least two different zoom levels based on the distance between the aircraft and the target object. In this embodiment, automatic selection can reduce the complexity of manual intervention by the user, improve efficiency, and reduce intervention.
[0079] Specifically, the computer device can automatically select the target zoom magnification from at least two different zoom magnifications based on the distance between the aircraft and the target object and the depth of field range corresponding to the acquisition of the first image. The depth of field range for acquiring the first image varies depending on the type of target object; different types of target objects correspond to different volume ranges. For example, the zoom magnification required by the imaging device to acquire the second image may be greater than or equal to the distance magnification; where the distance magnification is the distance multiple between the distance between the aircraft and the target object and the reference distance indicated by the aforementioned depth of field range.
[0080] For the same target object, the farther the distance between the aircraft and the target object, the larger the field of view of the imaging device will be, and the smaller the proportion of the target object in the field of view will be. In order to maintain the detail display of the target object, it is necessary to increase the focal length (i.e. increase the zoom magnification) so that the target object occupies more space in the picture.
[0081] For the same distance between the aircraft and the target object, the larger the target object, the larger the area it occupies in the field of view of the imaging device. In this case, a wider field of view (i.e., a lower zoom magnification) is required to capture the full view of the target object.
[0082] By following these rules, the zoom level can be dynamically selected to adapt to different target objects and distances, ensuring better shooting results.
[0083] In some embodiments, if the field of view corresponding to the second image is equal to the field of view corresponding to the first image, the imaging device only needs to capture one second image to cover the target area.
[0084] In other embodiments, the field of view corresponding to the second image is smaller than that corresponding to the first image. That is, the field of view corresponding to the first image is larger, which is beneficial for acquiring overall global information and facilitating focusing on the target area to be statistically analyzed. Furthermore, to fully cover the target area, the imaging device needs to capture multiple second images. The resolution of the second images is greater than that of the first images, which is beneficial for acquiring local detail information, thereby improving the accuracy of target object identification and statistical analysis. It is understood that "multiple second images" here refers to two or more second images, and each second image corresponds to a sub-region of the target area. That is, referring to Figure 4, the target area can be divided into multiple sub-regions, i.e., two or more sub-regions.
[0085] When the imaging device is shooting towards the target area, it can be controlled to shoot towards different sub-regions of the target area to obtain multiple second images. In this embodiment, multiple second images are obtained by finely capturing different sub-regions of the target area, which can achieve higher imaging resolution and more accurate target recognition. Each second image covers a smaller area, so higher resolution can be used for shooting, thereby improving the ability to capture details and resulting in higher image quality.
[0086] Furthermore, when the imaging device is pointing towards the target area, the attitude of the imaging device on the aircraft can be adjusted to capture multiple second images of different sub-regions of the target area. By adjusting the attitude of the imaging device, it can more flexibly adapt to different positions and angles of the target area, thereby capturing richer image information.
[0087] For example, after selecting a target area, the aircraft can be controlled to fly to one or more preset positioning positions based on the location-related information of the target area. Then, while the aircraft is in one or more preset positioning positions, the imaging device on the aircraft is controlled to adjust its attitude to take pictures of multiple sub-areas to obtain multiple second images. The field of view of the second image is smaller than the field of view of the first image.
[0088] Among them, the location-related information of the target area includes, but is not limited to, at least one of the following: (1) the location of the target area in the first image, which may be the location of the center coordinates of the target area in the first image, or the three-dimensional coordinates of the center position of the target area in three-dimensional space; (2) the relative position of the target area and the aircraft, which may be the distance, direction or angle of the target area relative to the current position of the aircraft.
[0089] When the aircraft is positioned at one or more preset locations, the imaging device on board the aircraft is controlled to adjust its attitude to capture multiple images of multiple sub-regions. There are two possible implementation methods:
[0090] In the first possible implementation (single-point shooting at the same preset positioning location), a preset positioning location can be determined based on the location-related information of the target area. While the aircraft is controlled to remain at this preset positioning location, the imaging device on board the aircraft adjusts its attitude to capture images of different sub-regions within the target area, thereby acquiring multiple second images. In this way, the aircraft can acquire multiple second images covering different sub-regions of the target area from the same positioning location. Each second image may correspond to one or more parts of the target area, thus providing more detailed information about the target object. The aircraft does not need to fly over a large area; it only needs to adjust the attitude of the imaging device to acquire second images of multiple different sub-regions, greatly reducing flight distance and energy consumption, and improving shooting efficiency.
[0091] Please refer to Figure 5. Multiple second images include second image A and second image B. Second images A and B are acquired while the aircraft is maintaining the same preset positioning position. Second image A is acquired by the imaging device shooting towards the target area in a first posture, and second image B is acquired by the imaging device shooting towards the target area in a second posture. The first posture differs from the second posture, and the sub-regions covered by second image A and second image B are at least partially different. In this embodiment, the target area is selected from the first image. The aircraft remains at the preset positioning position, and by adjusting the posture of the aircraft's imaging device, second images corresponding to at least two different sub-regions within the target area can be captured. This allows for fixed-point shooting within multiple different sub-regions without requiring extensive aircraft movement, facilitating the subsequent determination of statistical information related to the target object within these sub-regions. This method is time-saving, efficient, and conserves power.
[0092] For example, the preset positioning position can be the position where the imaging device captures the first image. That is, during the capture of the first and second images by the imaging device, the positioning position of the aircraft remains fixed. The aircraft does not need to move over a large area, but rather captures images of local areas by adjusting the attitude of the imaging device. The aircraft can complete multiple shooting tasks at a defined preset positioning position, which can reduce possible errors or instabilities during flight and also reduce the loss of kinetic energy of the aircraft.
[0093] Alternatively, the preset positioning position may differ from the aircraft position corresponding to the first image captured by the imaging device. The better shooting position is determined based on the positional information of the target area. This embodiment does not impose any restrictions on this.
[0094] For example, keeping the aircraft at the same preset positioning position includes controlling the aircraft to hover at the same preset positioning position, that is, the aircraft stays in a relatively fixed spatial position, and its latitude, longitude and altitude remain basically stable.
[0095] For example, keeping an aircraft at the same predetermined position means that the aircraft's center of mass remains essentially unchanged. The center of mass is the aircraft's center of gravity, typically a reference point for stable flight. This description indicates that the aircraft's overall position remains stable, and the position of its center of mass relative to the ground does not change significantly. It is understood that keeping the aircraft's center of mass essentially unchanged does not mean the aircraft is completely stationary, but rather that it remains relatively stable within a small range.
[0096] For example, the aircraft maintaining the same preset positioning position means that the aircraft's positioning position remains essentially unchanged. The aircraft's positioning position is determined by the aircraft's positioning module. The positioning module includes one or more of the following: GPS positioning module, GLONASS positioning module, Galileo positioning module, BeiDou positioning module, real-time dynamic RTK positioning module from a base station, and network RTK positioning module.
[0097] In the second possible implementation (multi-point shooting at multiple preset positioning locations), multiple preset positioning locations are determined based on location-related information of the target area, i.e., two or more preset positioning locations. These multiple preset positioning locations are the shooting points that the aircraft needs to fly to, and at least some of the preset positioning locations can cover different sub-regions of the target area. The imaging device can adjust its attitude at at least some of the preset positioning locations to shoot towards at least two different sub-regions, thereby acquiring two or more second images. This embodiment, by shooting at multiple preset positioning locations, can ensure that each second image is at a better shooting angle, avoiding image quality degradation caused by the limited viewpoint of a single location.
[0098] The first possible implementation method (single-point shooting at the same preset location) is suitable for small or concentrated target areas. The aircraft only needs to slightly adjust its attitude to cover multiple sub-regions. This method saves flight time and energy and is suitable for rapid and efficient target area analysis. The second possible implementation method (multi-point shooting at multiple preset locations) is suitable for scenarios with large or widely distributed target areas. By flying the aircraft to multiple preset locations and adjusting the attitude of the imaging device at each location to take pictures, the target area can be more comprehensively covered, reducing image overlap or blind spots.
[0099] For example, during the acquisition of multiple second images, the aforementioned imaging device on the control aircraft adjusts its attitude, including at least one of the following situations:
[0100] (1) Adjust the attitude of the imaging device around its pitch angle. The pitch angle controls the vertical direction of the imaging device, that is, the imaging device rotates around its lateral axis (roll axis) to adjust the vertical field of view of the imaging device. This adjustment is mainly to change the vertical angle of the imaging device's orientation to ensure that the imaging device can cover the area above or below the target area. When the target area has a large range in the vertical direction, it is necessary to adjust the pitch angle to ensure that the image covers different heights of the target area.
[0101] (2) Adjust the attitude of the imaging device around its yaw angle. The yaw angle controls the horizontal direction of the imaging device, that is, the imaging device rotates around its vertical axis, changing the horizontal field of view of the imaging device. This adjustment is mainly used to change the horizontal angle of the imaging device so that the imaging device can cover different horizontal directions of the target area. When the target area is relatively wide in the horizontal direction, it is necessary to adjust the yaw angle to ensure that the imaging device can cover the entire target area, especially when shooting a large area of ground.
[0102] (3) Control the imaging device to adjust its attitude around the roll angle. The roll angle controls the rotation of the imaging device around its front and rear axes, and this adjustment affects the horizontal stability of the imaging device. The roll angle of the imaging device can be adjusted to maintain the shooting stability of the imaging device and avoid image distortion or shooting angle deviation from the target area.
[0103] By flexibly controlling at least one of the pitch angle, yaw angle, and roll angle of the imaging device, the imaging device can accurately align with different sub-regions in the target area, ensuring that multiple second images can fully cover each sub-region of the target area.
[0104] For example, the aforementioned control of the imaging device mounted on the aircraft adjusts its attitude through at least one of the following methods:
[0105] (1) Controlling the aircraft carrying the imaging device to adjust its attitude, thereby causing the imaging device to adjust its attitude; this method refers to indirectly changing the shooting angle of the imaging device by adjusting the attitude of the aircraft itself (i.e., the pitch angle, yaw angle, and roll angle of the aircraft). When the aircraft adjusts its attitude, the onboard imaging device follows the change in the attitude of the aircraft and changes its shooting direction accordingly.
[0106] (2) Control the gimbal carrying the imaging device to adjust its attitude, thereby driving the imaging device to adjust its attitude; the gimbal is a mechanical device used to support and adjust the attitude of the imaging device. By controlling the movement of the gimbal, the pitch angle, yaw angle and roll angle of the imaging device can be precisely adjusted, and the shooting direction of the imaging device can be changed.
[0107] (3) Control the imaging device itself to adjust its attitude. This method directly controls the attitude adjustment of the imaging device itself, without relying on the adjustment of the aircraft or gimbal. For example, the imaging device has an independent attitude control system that can adjust the pitch angle, yaw angle or roll angle independently.
[0108] Understandably, depending on the mission requirements, an appropriate adjustment method (such as any one of the three adjustment methods mentioned above, or any combination thereof) can be selected to precisely adjust the shooting angle of the imaging device while ensuring the stability of the aircraft. This helps to improve the accuracy of mission execution and image quality.
[0109] In one example, an aircraft carries an imaging device via a gimbal. Assuming the gimbal has physical limitations in the yaw direction, preventing it from independently adjusting the required large yaw angle under certain conditions, a solution is to control the aircraft's overall yaw angle. This change in the aircraft's attitude influences the yaw angles of both the gimbal and the imaging device, achieving the target angle. The gimbal's pitch angle adjustment, however, is unrestricted and has a large range of motion. Therefore, the vertical shooting angle of the imaging device can be precisely changed directly by controlling the gimbal's pitch angle, without requiring the aircraft's attitude to be involved. For instance, the required attitude adjustment for the imaging device can be divided into yaw angle adjustment for the aircraft and pitch angle adjustment for the gimbal. Even with gimbal yaw limitations, the aircraft and gimbal collaborate to achieve complete and efficient attitude adjustment of the imaging device.
[0110] In some embodiments, if the orientation of the same reference object (such as a building, landmark, etc.) relative to the same reference plane (such as the horizon, vertical line of gravity, etc.) is inconsistent in the first and second images, it may lead to visual differences, making subsequent comparison analysis and identification difficult and resulting in a poor user experience. Therefore, to avoid inconsistent visual display effects of the same specific reference object in the first and second images, when the imaging device is shooting towards the target area, the preset parameters of the imaging device can be adjusted to ensure that the orientation of the same reference object relative to the reference plane is approximately consistent. For example, the preset parameters of the imaging device include the roll angle of the imaging device. By adjusting the roll angle, the changes in image orientation caused by the physical decoupling of the aircraft attitude change and the gimbal attitude change can be compensated, ensuring that the orientation of the same reference object relative to the same reference plane remains consistent in both images, facilitating user comparison and identification.
[0111] Please refer to Figures 9 and 10. Figure 9 corresponds to the target area division method before adjusting the preset parameters of the imaging device, and Figure 10 corresponds to the target area division method after adjusting the preset parameters of the imaging device. In Figure 10, the orientation of the same reference object in the second image and the first image relative to the same reference plane is basically the same.
[0112] In some embodiments, when capturing multiple second images, excessive overlap between adjacent images (such as overlapping portions of a ground-covered area) can affect shooting efficiency. Therefore, when the imaging device is shooting towards the target area, preset parameters of the imaging device can be adjusted to ensure that the overlap between adjacent images in the multiple second images is less than a preset overlap rate. For example, the preset parameters of the imaging device include the roll angle, which directly affects the boundary orientation of the shooting field of view. Precise adjustment of the roll angle can change the boundary position, that is, change the overlapping area of adjacent second images, thereby precisely controlling the overlap rate.
[0113] Please refer to Figures 9 and 10. Figure 9 corresponds to the target region division method before adjusting the preset parameters of the imaging device, and Figure 10 corresponds to the target region division method after adjusting the preset parameters of the imaging device. The image overlap rate between adjacent pairs of second images in Figure 10 is less than the image overlap rate between adjacent pairs of second images in Figure 9.
[0114] In some embodiments, after selecting a target area, the imaging device can be controlled to adjust its posture to capture images of multiple sub-regions based on a preset shooting sequence, thereby acquiring multiple second images. The shooting sequence specifies the shooting order of the multiple second images. This embodiment controls the imaging device to shoot in different postures based on a preset shooting sequence, achieving efficient and accurate target area coverage shooting.
[0115] Specifically, referring to Figure 4 or Figure 5, the computer device can divide the target area into an M*N array, such as a 3*4 array in Figure 4 or Figure 5. The array includes M*N sub-regions; for example, the target area in Figure 4 or Figure 5 includes 12 sub-regions. M and N are both positive integers. Each sub-region corresponds to at least one second image. That is, based on the multiple sub-regions, the number of second images that can be captured can be determined. Then, based on a preset shooting sequence, the imaging device can be controlled to adjust its posture to capture images of the sub-regions of the array, thereby acquiring multiple second images. This embodiment, by dividing the target area into an M*N array and controlling it using a shooting sequence, can not only efficiently cover the target area but also adapt to different task requirements through flexible division and sequence adjustment, achieving high-quality imaging and efficient resource utilization.
[0116] In this embodiment, M and N can be equal or unequal, and the specific settings can be made according to the actual application scenario. This embodiment does not impose any restrictions on this. M and N are both positive integers greater than 0.
[0117] The imaging devices for different sub-regions have different orientations. By controlling the orientation of the imaging devices, images can be taken from multiple sub-regions.
[0118] For example, in the same row direction of an M-row * N-column array, at least one of the following conditions must be met:
[0119] (1) The yaw angle of the imaging device corresponding to each sub-region increases or decreases sequentially.
[0120] For example, during the imaging process targeting sub-regions within the same row, the imaging device progressively adjusts its yaw angle, aligning it sequentially with the center point of each sub-region from left to right or right to left. The direction of the yaw angle change (increasing or decreasing) depends on factors such as the initial orientation of the imaging device and the order in which the target regions are divided. By changing the yaw angle, it ensures that all sub-regions within the same row are covered sequentially without omission.
[0121] (2) The pitch angles of the imaging devices corresponding to each sub-region are roughly the same.
[0122] During the process of shooting sub-regions in the same row, since the sub-regions in the same row are located within a similar vertical height range, the pitch angle (angle facing the vertical direction) of the imaging device remains basically unchanged.
[0123] (3) The yaw angle of the imaging device corresponding to each sub-region is adjusted by the movement of the aircraft around the yaw axis of the aircraft.
[0124] When shooting sub-regions within the same row, if the gimbal has a yaw limit, the yaw angle adjustment of the imaging device is not completed by the gimbal alone, but is achieved through the yaw motion of the aircraft itself. That is, the aircraft rotates around its own vertical axis (yaw axis), which drives the imaging device to align with each sub-region, thus avoiding the problem that the gimbal cannot cover all sub-regions within the same row when the yaw angle is limited.
[0125] (4) The roll angle of the imaging device corresponding to each sub-region first decreases and then increases or first increases and then decreases.
[0126] During the imaging process targeting sub-regions within the same row, the sub-region located at the center of the row has the smallest roll angle, while the roll angles of the imaging devices corresponding to the sub-regions on either side of the center gradually increase. Alternatively, the sub-region located at the center of the row has the largest roll angle, while the roll angles of the imaging devices corresponding to the sub-regions on either side of the center gradually decrease. The change in roll angle typically exhibits symmetrical characteristics, meaning that the roll angles of the left and right sub-regions within the same row change proportionally with the positional offset distance. As described above, adjusting the roll angle of the imaging device can make the orientation of a specific reference object in the second image corresponding to a sub-region approximately the same as the orientation of the same specific reference object in the first image relative to the same specific reference plane, or can make the overlap rate between two second images corresponding to adjacent sub-regions less than a preset overlap rate.
[0127] For example, in the row direction of the array, the roll angle of the imaging device corresponds to a smaller roll angle for sub-regions closer to the center of the row, and a larger roll angle for sub-regions farther from the center of the row. Sub-regions located at the center are often aligned with the reference line of sight of the imaging device, and the imaging device does not need to make large roll adjustments, so the roll angle is minimal. As sub-regions deviate from the center (e.g., move left or right), the imaging device needs to gradually increase the roll angle to align these sub-regions, thereby making the coverage of the sub-regions in the field of view of the imaging device more uniform, reducing visual shift or distortion, and ensuring that the same reference object in the second image maintains a consistent orientation.
[0128] (5) The roll angle of the imaging device corresponding to each sub-region is adjusted by the movement of the gimbal carrying the imaging device around the roll axis of the gimbal.
[0129] During the process of shooting a sub-region in the same row, while the aircraft remains hovering, the roll angle is adjusted by controlling the gimbal carrying the imaging device to rotate around the roll axis, thereby achieving the purpose of covering the sub-region.
[0130] In other words, when shooting sub-regions within the same row, the adjustments to the yaw and roll angles are designed to accurately cover the sub-regions within the same row and maintain image consistency.
[0131] For example, in the same column direction of an M row * N column array, at least one of the following conditions must be met:
[0132] (1) The pitch angle of the imaging device corresponding to each sub-region increases or decreases sequentially.
[0133] During the process of capturing images of sub-regions within the same column, as the imaging device captures images of these sub-regions from top to bottom (or bottom to top) of the target area, the pitch angle of the imaging device changes sequentially. For example, when capturing images from bottom to top, the pitch angle of the imaging device gradually increases. When capturing images from top to bottom, the pitch angle of the imaging device gradually decreases.
[0134] (2) The yaw angles of the imaging devices corresponding to each sub-region are roughly the same.
[0135] During the process of shooting the same column of sub-regions, the sub-regions of the same column are almost on the same straight line in the horizontal direction, with no significant lateral changes. The imaging device can cover all sub-regions without changing the yaw angle.
[0136] (3) The pitch angle of the imaging device corresponding to each sub-region is adjusted by the movement of the gimbal carrying the imaging device around the pitch angle of the gimbal.
[0137] During the process of shooting sub-regions in the same column, the imaging device flexibly adjusts the pitch angle through the gimbal to align with the sub-regions in the vertical direction. This requires the aircraft itself to adjust its attitude, reducing the complexity of flight movement.
[0138] (4) The roll angle of the imaging device corresponding to each sub-region increases or decreases sequentially.
[0139] During the process of capturing images of sub-regions within the same column, in order to ensure the consistency of the orientation of the content in the first and second images, or to ensure that the image overlap rate between adjacent second images is less than a preset overlap rate, the imaging device needs to adjust the roll angle to align the sub-regions. Sub-regions within the same column exhibit an increasing or decreasing trend in roll angle. For example, tilting the top sub-region of the same column corresponds to the minimum roll angle, while the bottom sub-region corresponds to the maximum roll angle. This ensures the consistency of the reference object orientation in each second image.
[0140] (5) The roll angle of the imaging device corresponding to each sub-region is adjusted by the movement of the gimbal carrying the imaging device around the roll axis of the gimbal.
[0141] During the process of shooting sub-regions in the same column, the imaging device controls the roll angle through the roll axis of the gimbal to quickly align the sub-regions in the vertical direction.
[0142] In other words, when shooting a sub-region of the same column, the adjustment of the pitch and roll angles is aimed at accurately covering the sub-region of the same column and maintaining image consistency.
[0143] For example, the preset shooting sequence includes traversing the array in a roughly "Z"-shaped shooting sequence. By following the "Z"-shaped trajectory to cover the entire array, it ensures that every part of the target area has a corresponding image. The path rule is simple and efficient, and can avoid repetition or omission that may be caused by random movement.
[0144] In one possible scenario, as shown in Figure 6, the horizontal lines of the "Z" shape correspond to the row direction of the array, and the vertical lines of the "Z" shape correspond to the column direction. That is, the imaging device takes at least one second image row by row along the horizontal direction of the target area. After each row is completed, it switches to the next row to take the next image. After completing the first row from left to right, it moves directly to the starting point of the next row (from right to left) to continue shooting, and so on. This row-by-row horizontal imaging reduces the frequency of vertical movement of the aircraft; most of the time, only yaw angle adjustments are needed. For target areas that are wide horizontally but narrow vertically, this method can quickly achieve coverage.
[0145] In another possible scenario, please refer to Figure 7. The horizontal lines of the "Z" shape correspond to the column direction of the array, and the vertical lines of the "Z" shape correspond to the row direction of the array. That is, the imaging device takes at least one second image column by column along the vertical direction of the target area, and switches to the next column after each column is completed. That is, after completing the first column from top to bottom, it moves directly to the starting point of the next column (from bottom to top) to continue shooting, and so on. Vertical column-by-column shooting focuses more on adjusting the pitch angle and reduces the frequent adjustment of the yaw angle; for target areas that are high in the vertical direction but narrow in the horizontal direction, this method can quickly cover them.
[0146] For example, if the actual size of the target area exceeds the coverage of a single second image (that is, the coverage of the field of view of the imaging device corresponding to the second image), the target area needs to be divided into multiple sub-regions, each of which is covered by at least one second image. In other words, the number of multiple second images is determined based on the size of the target area and the field of view of the imaging device corresponding to the second image.
[0147] The number of second images depends on the ratio between the size of the target region and the field of view. The number of second images can be dynamically determined based on the relationship between the size of the target region and the field of view of the imaging device corresponding to the second image, thus avoiding insufficient coverage or redundancy.
[0148] For the same target area, the larger the field of view of the imaging device corresponding to the second image, the fewer the number of sub-regions are divided. Similarly, the fewer the number of second images that need to be captured, and vice versa.
[0149] When the field of view of the imaging device corresponding to the second image is fixed, the larger the target area, the more sub-regions are divided. Similarly, the more second images need to be captured, and vice versa.
[0150] An example is provided where each sub-region corresponds to one second image:
[0151] The imaging device attitude corresponding to each second image is determined based on the position of the center of the sub-region corresponding to the second image in the first image. Specifically, the imaging device attitude corresponding to each second image can be determined based on the position of the center of the sub-region corresponding to the second image in the first image, the field of view of the imaging device when acquiring the first image, and the imaging device attitude when acquiring the first image. The imaging device attitude corresponding to each second image includes the yaw angle, pitch angle, and roll angle of the imaging device. For example, please refer to Figure 8, which shows a schematic diagram of the target area and the center of each sub-region.
[0152] For each second image, the yaw angle of the imaging device is determined based on the position of the center of the sub-region corresponding to the second image in the first image, the field of view of the imaging device when acquiring the first image, and the yaw angle of the imaging device when acquiring the first image. Specifically, the position of the center of the sub-region corresponding to the second image in the first image reflects the relative position of that sub-region within the horizontal field of view; the field of view of the first image is used to map the pixel positions of the first image to actual spatial angles; the yaw angle of the first image serves as an initial reference angle, and the calculated yaw angle of the second image is an adjustment based on this initial reference angle.
[0153] The pitch angle of the imaging device corresponding to each second image can be determined based on the position of the center of the sub-region corresponding to the second image in the first image, the field of view of the imaging device when acquiring the first image, and the pitch angle of the imaging device when acquiring the first image. Specifically, the position of the center of the sub-region corresponding to the second image in the first image reflects the relative position of that sub-region within the vertical field of view; the field of view of the first image is used to map the pixel positions of the first image to actual spatial angles; the pitch angle of the first image serves as an initial reference angle, and the calculated pitch angle of the second image is an adjustment based on this initial reference angle.
[0154] Please refer to Figure 9. Figure 9 shows the division of the target area into sub-regions with a constant roll angle. The coverage area of the second image corresponding to each sub-region captured by the imaging device follows the rule of larger objects appearing closer to the object and smaller objects appearing farther away. In Figure 9, the wider side is the side closer to the aircraft, and the narrower side is the side farther away from the aircraft. Figure 9 shows the case where the roll angle of the imaging device for each sub-region remains constant. It can be seen that in the same row, the sub-region farther from the center column has a greater degree of misalignment between its image orientation and the first image; in the same column, the sub-region in the row closer to the aircraft has a greater degree of misalignment between its image orientation and the first image.
[0155] Please refer to Figure 10, which shows the division of each sub-region in the target area under the condition of roll angle change, and the coverage of the second image corresponding to each sub-region captured by the imaging device. It can be seen that the orientation of the image of each sub-region is roughly aligned with the corresponding area of the first image.
[0156] This embodiment dynamically calculates the yaw angle, pitch angle, and roll angle corresponding to each second image based on the center position of the sub-region in the first image, combined with the field of view of the first image and the attitude of the imaging device corresponding to the first image. This can achieve precise coverage of each sub-region of the target area, avoid missed shots, reduce the rate of repeated shooting, and ensure the viewing experience between the first image and the second image.
[0157] In some embodiments, the multiple second images include second image A and second image B, which are adjacent images and have an overlapping area. The overlap rate of the overlapping area is less than or equal to a preset overlap rate. The preset overlap rate can be set according to the specific application scenario.
[0158] For example, the preset overlap rate is greater than or equal to 0 and less than or equal to 10%. This is a relatively small overlap rate threshold setting, which can reduce the computational burden or storage usage of the second image and alleviate the problem of duplicate recognition or duplicate statistics.
[0159] For example, the preset overlap rate is 5%. This low overlap rate can effectively avoid excessive image overlap, which leads to redundant data or unnecessary calculations, thereby optimizing image storage and processing.
[0160] For example, after obtaining the second image A and the second image B, the target objects in the second image A and the target objects in the second image B can be identified, and then based on the identified target objects, statistical information related to the target objects in the second image A and the second image B can be determined.
[0161] Specifically, the computer device can identify target objects in a second image A containing an image overlap area and in a second image B containing an image overlap area, and identify target objects in the image overlap area. Then, based on the target objects identified in the second image A containing the image overlap area, the target objects identified in the second image B containing the image overlap area, and the target objects identified in the image overlap area, it determines statistically relevant information about the target objects in the second image A and the second image B. This embodiment, by considering the target objects in the image overlap area, helps to ensure the statistical accuracy of the target objects.
[0162] For example, if the statistical information related to the target objects includes the number of target objects, then the number of target objects identified in the second image A (which includes the image overlap area) can be added to the number of target objects identified in the second image B (which also includes the image overlap area), and then the number of target objects identified in the image overlap area can be subtracted to obtain the number of target objects in the second image A and the second image B. This embodiment avoids the problem of double counting by considering and adjusting the target objects in the image overlap area, thus ensuring the accuracy of the target object count.
[0163] In other embodiments, the multiple second images include a second image A and a second image B, which are adjacent images. There is no image overlap between the second images A and B, that is, the overlap rate between two adjacent second images is 0. This helps to simplify the subsequent process of determining the statistical information related to the target object and improves the statistical efficiency.
[0164] In some embodiments, the statistical information related to the target object includes at least one of the following: the count of the target object, the spatial distribution of the target object, and the trend of the target object's change.
[0165] For example, the target object count characterizes the number of target objects identified in the second image, reflecting the total number of target objects and helping to understand the distribution or density of target objects in the target area.
[0166] For example, the spatial distribution of a target object represents its location in space, and statistical analysis of the spatial distribution of a target object can be used to characterize the aggregation or dispersion pattern of the target object within the target area.
[0167] For example, the changing trend of a target object represents the change in the quantity, location, or status of the target object over time, and can be used for trend prediction and dynamic monitoring.
[0168] Specifically, in some embodiments, statistical information related to the target objects includes the number of target objects. In large-scale monitoring scenarios, the statistical analysis of the number of target objects is crucial for resource assessment, event analysis, and other purposes.
[0169] Specifically, in some embodiments, statistically relevant information about the target objects includes the density of the target objects. The density of target objects refers to the number of target objects per unit area. By calculating the density of target objects, the degree of concentration of target objects within the target area can be understood. High density usually indicates that the target area is rich in resources or that some kind of activity is concentrated.
[0170] Taking the density of target objects as an example, the statistical information related to target objects in the second image is determined, including: identifying the number of target objects in the second image, determining the area of the second image, and determining the density of target objects in the second image based on the number of target objects and the area of the second image. Specifically, the density data of target objects can be obtained by using the ratio of the number of target objects to the area of the second image, providing a basis for further analysis of the distribution of targets.
[0171] Specifically, regarding the area of the second image, relevant information about reference points in the second image can be obtained. Then, based on the relevant information about the reference points and the field of view of the imaging device corresponding to the acquisition of the second image, the area of the second image is determined. This embodiment calculates the area based on the field of view, which can more accurately quantify the area covered by the image, especially in complex three-dimensional environments, helping to eliminate errors caused by changes in viewing angle.
[0172] Specifically, based on the relevant information of the reference point and the field of view of the imaging device corresponding to the acquisition of the second image, the positional information of multiple vertices in the second image can be determined. These vertices are essentially on the same moving surface as the reference point. Then, based on the positional information of these vertices, the area of the second image can be determined. This implementation, by obtaining the positional information of multiple vertices in the second image, can more accurately define the boundaries of the image region, thereby accurately calculating the area of the second image. For example, the positional information of four points intersecting the ground surface within the field of view (FOV) of the imaging device can be calculated, and the surface area of the second image can be calculated based on the positional information of these four points.
[0173] The relevant information for the reference point includes at least one of the following: the reference point's location information and the relative distance between the reference point and the aircraft. For example, the reference point corresponds to the center of the second image, but is not limited to this. Selecting a reference point (such as the center of the second image) ensures the accuracy and consistency of area calculation. The reference point provides a relatively fixed reference position, avoiding errors caused by the movement of the aircraft and imaging device.
[0174] For example, the relevant information about the reference point is obtained based on the aircraft's distance sensors. Distance sensors include, but are not limited to, lidar. A pre-defined positional calibration relationship exists between the distance sensors and the imaging device. Accurate distance measurements from the distance sensors (e.g., lidar) provide precise relative position data for the aircraft and the imaging device, helping to determine the size and boundaries of the target area and ensuring the geometric accuracy of the image.
[0175] In some embodiments, after identifying the target object in the second image, statistical information related to the target object is also displayed on the user interface so that users can intuitively understand the statistical information.
[0176] For example, displaying statistical information in a preset style on the user interface includes at least one of the following scenarios:
[0177] (1) Display statistical information in numerical form on the user interface;
[0178] Statistical information is displayed directly in numerical form, such as the number, density, and distribution ratio of target objects. Numerical data presentation is clear, concise, and easy for users to understand quickly, making it suitable for scenarios involving quantitative analysis, such as monitoring and statistics. For example, the upper left corner of Figure 11A displays the number of people and vehicles in the target area.
[0179] (2) Display statistical information related to different sub-regions of the target area in the form of a heatmap on the user interface;
[0180] Different sub-regions of the target area are represented by different colors or brightness levels based on the level of statistical information. For example, areas with high target object density are represented in red, and areas with low density are represented in blue. Users can intuitively perceive the distribution of statistical information, facilitating regional comparison, and can quickly identify areas requiring special attention through the heatmap. For example, please refer to Figure 11B, which shows a schematic diagram of different sub-regions of the target area displayed in heatmap form. Please also refer to Figure 11C, which shows a schematic diagram of statistically relevant information of target objects in the target area displayed in heatmap form.
[0181] (3) Highlight at least a portion of each target object on the user interface;
[0182] Adding highlight markers to the outline or exterior of the target object, such as thick borders, dynamic flashing, or color highlighting, allows the style of the highlight markers to contrast with the background, making it easier for users to notice the target object. Highlighting effects can attract user attention, prevent overlooking key targets, and facilitate user clicking and selection of the target object, enabling subsequent refined operations.
[0183] (4) Mark the target objects in the form of icons within the preset range of each target object on the user interface, such as the human-shaped icon in Figure 13. Different types of target objects can correspond to different icon styles, such as using a shape-shifting icon.
[0184] Use fixed-style icons (such as dots, arrows, or phantom icons) to mark the center or vicinity of the target object; the icon size, color, or shape can be dynamically adjusted according to the target object's attributes or category. This method allows for precise location marking of the target object, facilitating target association analysis for users.
[0185] For example, in a scenario where target objects are labeled with icons within a preset range on the user interface, different types of target objects correspond to different icon styles. By displaying differentiated icon styles for different types of target objects, the user interface can efficiently present the distribution of multiple types of target objects. Different icon styles allow users to quickly identify the type of target object, improving observation efficiency.
[0186] The types of target objects can be predefined (e.g., people, vehicles, animals, buildings, etc.), and then unique icon styles can be assigned to each type of target object, including color, shape, size, or animation effects. For example, people are represented by green stick figure icons; vehicles by blue car-shaped icons; animals by yellow triangle icons; and buildings by gray rectangle icons. In a real-time scene, the control terminal can automatically identify the type of target object and overlay the corresponding type of icon within the preset area of the target object in the user interface. As shown in Figure 12, "stick figure icons" are displayed around people in the image.
[0187] In areas with a high density of target objects, the icon position can be automatically adjusted or the icon size reduced to minimize overlap. Alternatively, the brightness, color, or animation effects of the icons can be dynamically adjusted based on the importance or priority of the target objects; for example, important targets (such as vehicles that are prioritized for tracking) can be represented by flashing icons or special colors.
[0188] In some embodiments, when multiple categories of target objects are statistically analyzed, the statistical information of each category of target object can be displayed separately on the user interface, as shown in Figure 12, where the total number of people and vehicles in the image is displayed in the upper right corner. Displaying statistical information separately by category avoids confusion caused by mixing them together, making the information presentation clearer and more intuitive; the information of each category of target object is statistically analyzed and displayed separately, which helps users to conduct in-depth analysis of the characteristics and trends of different target types.
[0189] In some embodiments, after displaying statistical information about the target objects on the user interface, the displayed statistical information can be updated in response to user editing operations. Users can dynamically adjust the displayed content of the statistical information according to actual needs, such as adding, deleting, or reclassifying target objects, thereby ensuring that the statistical data remains consistent with the latest requirements. Alternatively, when the automatically identified target object category or quantity is incorrect, users can manually correct it through editing operations to ensure data accuracy. For example, in Figure 12, a small number of people in the upper left corner are not identified, and no human-shaped icons are displayed around them. Users can manually edit to add or delete incorrectly identified target objects.
[0190] In some embodiments, in response to statistical information not meeting preset conditions, a computer device (such as a control terminal or aircraft) can also generate a prompt message. This prompt message includes at least one of warning information and evacuation guidance information. This embodiment automatically compares statistical information with preset conditions and generates prompts, eliminating the need for manual user monitoring and significantly shortening the time required to detect anomalies.
[0191] For example, in response to statistically relevant information exceeding a preset threshold, the computer device generates a warning message. For instance, if the statistical information shows that the density of target objects in a certain area is too high, exceeding a preset density threshold, a warning message is generated to remind the user that there may be a safety hazard in that area. If the number or distribution of target objects is abnormal (such as crowds gathering), evacuation guidance information can be automatically triggered to guide the target objects to a safe area. Through timely warning messages, users can avoid potential risks in high-density areas, such as stampedes or other accidents.
[0192] The preset conditions can also be other conditions, such as indicating an anomaly if the number of target objects in the target area does not decrease within a certain time period. Alternatively, an alert can be generated if the number of target objects increases or decreases rapidly.
[0193] The prompts can be delivered through at least one of the following methods: visual cues, voice cues, and tactile cues.
[0194] For visual cues, abnormal areas can be highlighted in the user interface, or flashing warning signs can be displayed. For voice cues, the audio device on the control terminal can provide real-time reminders to the user, suitable for scenarios where the user cannot focus on observing the interface. For haptic cues, subtle cues can be sent to the user through vibration or other means, particularly suitable for noisy environments.
[0195] In some embodiments, a second image may be displayed on the user interface in response to a second user input operation. For example, a user may perform a specific operation (such as clicking, dragging, selecting, double-clicking, etc.) on the first image on the user interface as a second input operation, triggering the display of the second image.
[0196] For example, in response to a second input operation by the user on the first image, a second image is switched / overlaid on the user interface. The second image has a higher resolution and can provide detailed, high-definition information about the target area. For instance, the correspondence between the target areas of the second image and the first image can be calculated, and the corresponding second image can be retrieved and switched based on this correspondence, or the second image can be overlaid on the first image. Since the second image has a higher resolution than the first image, switching or overlaying it can provide clearer and more detailed information about the target area, allowing the user to observe more local details.
[0197] For example, in response to a second input operation by the user on a preset area of the first image, a second image corresponding to the preset area is displayed on the user interface. The preset area positioning function allows users to quickly perform detailed viewing of areas of interest, avoiding repeated operations on the entire image. A high-resolution second image of the preset area can be extracted and displayed based on the user-interacted preset area, thereby facilitating the user to obtain more detailed information about the preset area through the second image.
[0198] It should be noted that the statistical methods corresponding to the above embodiments can be executed entirely on the aircraft side, entirely on the aircraft's control terminal side, or partially on the aircraft side and partially on the aircraft's control terminal side. This application does not impose any limitations on this. In some embodiments where the control methods corresponding to the above embodiments involve partially executed on the aircraft side and partially on the aircraft's control terminal side, the following steps are executed independently on the aircraft's control terminal side:
[0199] Please refer to Figure 13. This application embodiment also provides a display method, which includes:
[0200] In S1301, the first image is displayed on the user interface.
[0201] For example, the user interface can be displayed on the control terminal's built-in display or on an external display that is communicatively connected to the control terminal.
[0202] In S1302, the selected target area is displayed on the first image, wherein the target area contains the target object.
[0203] In S1303, statistical information related to the target object is displayed on the user interface; wherein, the statistical information related to the target object is determined based on a second image, which is acquired by the imaging device on the aircraft taking pictures of the target area, and the resolution of the second image is greater than the resolution of the first image.
[0204] For detailed implementation of this embodiment, please refer to the foregoing embodiments, which will not be repeated here.
[0205] In an exemplary application scenario, taking public safety as an example, the goal is to solve the problem of crowd monitoring during major holidays and large event squares. Aerial photography using drones is used to obtain overall crowd flow information: quantity, aggregation, and distribution. Based on the aerial photography results, crowd flow analysis is performed to determine areas requiring crowd guidance. Guidance resources are then rationally allocated based on the analysis results, and guides are assigned to key areas. Guides can communicate in real-time with drone operators via walkie-talkies or mobile phones, adjusting guidance direction and methods according to the crowd flow. The allocation of guidance resources is flexibly adjusted based on key event times and crowd flow conditions to ensure safety and prevent stampedes.
[0206] Beyond pedestrian flow information, there's a need for vehicle statistics on highways and key urban roads; similarly, there's a need for target recognition in the counting of vessels on busy waterways. It can also be generalized to other fields, such as animal or plant species quantity counting and density calculation problems. The aircraft can support the identification of people, vehicles, vessels, and other types of target objects, and count the number of target objects in each image.
[0207] For example, the aircraft is equipped with a wide-angle camera, a first zoom camera, a second zoom camera, and a lidar, with the first zoom camera and the second zoom camera having different zoom ratios.
[0208] When the aircraft flies to the desired position, it controls the wide-angle camera to take pictures of the designated location to obtain a wide-angle image (i.e., the first image mentioned above). The wide-angle image is then sent to the user interface for display. The user can select the target area to be counted in the wide-angle image by using a box selection operation. The user interface then sends the selected target area to the aircraft.
[0209] By using the ranging function of the lidar, the relative distance between the target object and the aircraft in the target area can be known. Based on the distance between the aircraft and the target object, the target zoom camera can be automatically selected from two zoom cameras. For the specific selection method, please refer to the relevant description of the "target zoom magnification" selection process above, which will not be repeated here.
[0210] Based on information such as the field of view of the wide-angle camera, the field of view of the target zoom camera, and the attitude of the wide-angle camera when capturing wide-angle images, the number of zoom images to be captured and the attitude of the target zoom camera when capturing each zoom image can be determined. The specific determination process is described above and will not be repeated here. The target zoom camera can then capture multiple zoom images according to a preset shooting sequence.
[0211] Multiple zoom images can be obtained by the aircraft taking pictures at the same location. Alternatively, multiple zoom images can be obtained by the aircraft taking pictures at different locations. The aircraft can take at least two zoom images at at least some of the locations by adjusting the attitude of the target zoom camera. The aircraft can generate aerial flight paths based on the different locations to execute aerial photography.
[0212] After acquiring multiple zoom images, the aircraft identifies target objects in each image to determine the number of target objects in each image. Then, by utilizing the overlap rate between adjacent zoom images, duplicate counts of target objects are eliminated, generating the total number of target objects for the target region. Alternatively, if there is no overlap between adjacent zoom images, the number of target objects in each image can be summed.
[0213] For the area of each zoom image, for example, the active surface of the target object in the zoom image, such as the ground surface, can be estimated based on the point cloud collected by the lidar. Then, based on the ground surface and the field of view of the target zoom camera, the latitude and longitude of the four points (i.e. the four vertices of the zoom image) that intersect within the field of view of the ground surface and the target zoom camera can be calculated. Finally, the area of the second image can be calculated based on the estimated latitude and longitude.
[0214] Finally, given the number of target objects in each zoomed image and the area of each zoomed image, the density of target objects in each zoomed image and the total density of target objects in the target region can also be calculated.
[0215] There are at least one of the following solutions to improve the accuracy of lidar:
[0216] (1) If a preset type of object exists in the target area, output a prompt message indicating that the lidar is affected; wherein, the preset type is used to describe the type of object that affects the detection results of the lidar. For example, the prompt message can be given visually, audibly, or tactilely. The preset type includes at least one of the following: specular reflective object, low reflectivity object, transparent object, and multi-surface object.
[0217] (2) For each three-dimensional point acquired by the lidar, the deviation angle can be obtained based on the difference between the incident angle of the three-dimensional point and the reference incident angle; based on the deviation angle and the reflectivity correction model corresponding to the reference incident angle, the reflectivity of the three-dimensional point is corrected, thereby improving the accuracy of the lidar.
[0218] (3) By adjusting the zoom and focus of the zoom camera, the approximate distance to the object being measured can be obtained. The zoom camera's focusing system adjusts the lens position according to the position of the object being photographed, making the image of the object clear. If the zoom camera is focused on a specific object, the distance between the lens and the sensor can be used to estimate the distance to that object. The lidar can use this prior distance to filter out noise that may exist in other distance ranges from the point cloud collected by the lidar.
[0219] (4) If the current environment of the unmanned aerial vehicle is a preset environment, the preset environment includes at least one of the following: rain and fog environment, sandstorm environment and snowy environment, the intensity of the noise points filtered by the lidar is increased, thereby improving the accuracy of the lidar.
[0220] In some embodiments, referring to Figure 14, this application embodiment also provides a statistical method for a target object, the method comprising:
[0221] In S1401, a target region is selected in the first image, wherein the target region contains a target object and the target region includes multiple sub-regions.
[0222] In S1402, based on location-related information of the target area, the aircraft is controlled to fly to one or more preset positioning locations.
[0223] In S1403, while the aircraft is maintained at one or more preset positioning positions, the imaging device on the aircraft is controlled to adjust its attitude to take pictures of multiple sub-regions respectively, thereby acquiring multiple second images; wherein, the multiple second images include second image A and second image B, second image A and second image B are acquired while the aircraft is maintained at the same preset positioning position, second image A is acquired by the imaging device taking pictures of the target area with a first attitude, and second image B is acquired by the imaging device taking pictures of the target area with a second attitude, the first attitude is different from the second attitude, and the sub-regions covered by second image A are at least partially different from the sub-regions covered by second image B.
[0224] In S1404, target objects in multiple second images are identified.
[0225] In S1405, based on the identified target object, statistical information related to the target object in multiple second images is determined; wherein the field of view of the second image is smaller than the field of view of the first image, and the resolution of the second image is greater than the resolution of the first image.
[0226] In this embodiment, a target region is selected in the first image. The aircraft remains at the same preset positioning position. By adjusting the attitude of the aircraft's imaging device, multiple second images of different sub-regions within the target region can be captured. This allows for fixed-point imaging within multiple different sub-regions without requiring extensive aircraft movement, facilitating the determination of statistical information related to the target object within these sub-regions. This approach is time-saving, efficient, and power-saving. Furthermore, the field of view of the first image is larger than that of the second image, which is beneficial for acquiring overall global information and focusing on the target region requiring statistical analysis. The resolution of the second image is greater than that of the first image, which is beneficial for acquiring local detail information, thereby improving the accuracy of target object identification and statistical analysis.
[0227] For the specific implementation of the statistical method for the target object, please refer to the description in the relevant section above. The principle of some steps in this embodiment is the same as or similar to the principle of the relevant steps in the previous embodiment. Without obvious contradiction, the description in the previous embodiment is also applicable to this embodiment, and will not be repeated here.
[0228] It should be noted that the statistical methods corresponding to the above embodiments can be executed entirely on the aircraft side, entirely on the aircraft's control terminal side, or partially on the aircraft side and partially on the aircraft's control terminal side. This application does not impose any restrictions on this.
[0229] In some embodiments where the control method steps are executed on the aircraft side and some steps are executed on the aircraft's control terminal side, in some embodiments, the control terminal side executes the following steps separately:
[0230] In some embodiments, referring to Figure 15, this application embodiment also provides a method for displaying a target object, the method comprising:
[0231] In S1501, the first image is displayed on the user interface.
[0232] In S1502, the selected target region is displayed on the first image. The target region contains the target object and includes multiple sub-regions.
[0233] In S1503, statistical information related to the target object is displayed on the user interface. The statistical information is determined based on the second image A and the second image B. The second image A is obtained by the aircraft being positioned at a preset location and the imaging device on the aircraft being controlled to take pictures of the target area in a first attitude. The second image B is obtained by the aircraft being positioned at the same preset location and the imaging device on the aircraft being controlled to take pictures of the target area in a second attitude. The first attitude is different from the second attitude. The sub-regions covered by the second image A and the second image B are at least partially different. Furthermore, the field of view angles corresponding to the second image A and the second image B are both smaller than the field of view angle corresponding to the first image, and the resolutions corresponding to the second image A and the second image B are both greater than the resolution corresponding to the first image.
[0234] In this embodiment, the displayed first image facilitates focusing on the target area to be statistically analyzed. The field of view of the first image is larger than that of the second image, which is beneficial for acquiring overall global information and thus facilitating focusing on the target area. The resolution of the second image is greater than that of the first image, which is beneficial for acquiring local detail information, thereby improving the accuracy of target object identification and statistics. By displaying statistical information on the user interface, users can quickly and intuitively understand the statistical situation of the target object. Furthermore, by selecting the target area in the first image and keeping the aircraft at the same preset positioning position, multiple second images of different sub-regions within the target area can be captured by adjusting the attitude of the aircraft's imaging device. This allows for fixed-point shooting within multiple different sub-regions without large-scale aircraft movement, facilitating the determination of statistical information related to the target object in multiple different sub-regions, saving time, increasing efficiency, and conserving power consumption.
[0235] For details on the specific implementation of the method for displaying the target object, please refer to the descriptions in the relevant sections above. The principles of some steps in this embodiment are the same as or similar to those of the relevant steps in the aforementioned embodiments. Without obvious deviation, the descriptions in the aforementioned embodiments also apply to this embodiment, and will not be repeated here.
[0236] The various technical features in the above embodiments can be combined arbitrarily, as long as there is no conflict or contradiction between the combinations of features. Therefore, the arbitrary combination of the various technical features in the above embodiments is also within the scope of this specification.
[0237] In some embodiments, referring to FIG16, this application embodiment also provides a computer device, including: at least one processor 1601; and at least one memory 1602 including computer program code; wherein, at least one of the memory 1602 and the computer program code are configured together with the at least one processor 1601 such that the computer device is at least capable of performing the method described in any of the above embodiments.
[0238] The processor 1601 executes the computer program code included in the memory 1602. The processor 1601 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0239] The memory 1602 stores computer program code for any of the above methods. The memory 1602 may include at least one type of storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. Furthermore, the computer device can cooperate with network storage devices that perform storage functions via a network connection. The memory 1602 can be an internal storage unit of the computer device, such as the hard disk or RAM of the computer device. The memory 1602 can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Further, the memory 1602 may include both internal and external storage units of the computer device. The memory 1602 can also be used to temporarily store data that has been output or will be output.
[0240] The computer device can be an aircraft or a control terminal. The computer device includes at least a processor 1601 and a memory 1602. Those skilled in the art will understand that Figure 16 is merely an example of a computer device and does not constitute a limitation on the computer device. It may include more or fewer components than shown, or combine certain components, or different components. For example, when the computer device is an aircraft, the computer may also include an imaging device, a distance sensor, at least one positioning module, etc.
[0241] The specific implementation process of the functions and roles of each unit in the above-mentioned equipment can be found in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.
[0242] In some embodiments, this application also provides an aircraft, including: at least one processor; and at least one memory including computer program code; wherein at least one of the memory and the computer program code are configured together with the at least one processor to enable the computer device to perform at least any of the statistical methods described above.
[0243] In some embodiments, this application also provides a control terminal, including: at least one processor; and at least one memory including computer program code; wherein at least one of the memory and the computer program code are configured together with the at least one processor to enable the computer device to execute at least any of the display methods described above.
[0244] In some embodiments, referring to FIG1, this application also provides a system including an aircraft and a control terminal.
[0245] In some embodiments, this application also provides a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, which can be executed by a processor of a device to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a computer device, enables the computer device to perform the above-described method.
[0246] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0247] The methods and apparatus provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A statistical method for a target object, characterized in that, include: Select a target region in the first image, wherein the target region contains the target object; The imaging device mounted on the aircraft is controlled to shoot towards the target area to obtain a second image; Identify the target object in the second image; as well as Based on the identified target object, determine the statistical information related to the target object in the second image; The resolution of the second image is greater than the resolution of the first image.
2. A method for displaying a target object, characterized in that, include: Display the first image on the user interface; Display a selected target region on the first image, wherein the target region contains a target object; and The user interface displays statistical information related to the target object. The statistical information is determined based on a second image, which is acquired by an imaging device mounted on the aircraft and taken towards the target area. The resolution of the second image is greater than that of the first image.
3. The method according to claim 1 or 2, characterized in that, The statistical information includes the count of the target objects, the spatial distribution of the target objects, and / or the changing trend of the target objects.
4. The method according to claim 1 or 2, characterized in that, The statistical information includes the number of the target objects.
5. The method according to claim 1 or 2, characterized in that, The statistical information includes the density of the target object.
6. The method according to any one of claims 1, 3 to 5, characterized in that, Determining the statistical information related to the target object in the second image includes: Identify the number of target objects in the second image; Determine the area of the second image; and The density of the target objects in the second image is determined based on the number of target objects and the area of the second image.
7. The method according to claim 6, characterized in that, Determining the area of the second image includes: Obtain relevant information about the reference points in the second image; Based on the relevant information of the reference point and the field of view of the imaging device corresponding to the acquisition of the second image, the area of the second image is determined.
8. The method according to claim 7, characterized in that, Determining the area of the second image based on the relevant information of the reference point and the field of view of the imaging device corresponding to the acquisition of the second image includes: Based on the relevant information of the reference point and the field of view of the imaging device corresponding to the acquisition of the second image, the position information of multiple vertices in the second image is determined, wherein the multiple vertices are substantially on the same moving surface as the reference point; and The area of the second image is determined based on the position information corresponding to multiple vertices in the second image.
9. The method according to claim 7, characterized in that, The relevant information of the reference point includes the location information of the reference point and / or the relative distance information between the reference point and the aircraft.
10. The method according to claim 7, characterized in that, The relevant information about the reference point is obtained based on the distance sensor of the aircraft.
11. The method according to claim 10, characterized in that, The distance sensor includes a lidar.
12. The method according to claim 10, characterized in that, The distance sensor and the imaging device have a preset position calibration relationship.
13. The method according to claim 7, characterized in that, The reference point corresponds to the center of the second image.
14. The method according to claim 1 or 2, characterized in that, The target area includes multiple sub-regions; The method further includes: Based on the location-related information of the target area, the aircraft is controlled to fly to one or more preset positioning locations; The imaging device carried by the aircraft takes pictures of the target area, including: While the aircraft is positioned at one or more of the preset locations, the imaging device on the aircraft is controlled to adjust its attitude to take pictures of the multiple sub-regions respectively, thereby acquiring multiple second images; the field of view of the second image is smaller than the field of view of the first image. The multiple second images include second image A and second image B, which are acquired when the aircraft is in the same preset positioning position. Second image A is acquired by the imaging device in a first posture toward the target area, and second image B is acquired by the imaging device in a second posture toward the target area. The first posture is different from the second posture, and the sub-region covered by second image A is at least partially different from the sub-region covered by second image B.
15. The method according to claim 1 or 2, characterized in that, The target area includes multiple sub-regions; The imaging device carried by the aircraft takes pictures of the target area, including: When the imaging device is taking pictures toward the target area, the imaging device on the aircraft is controlled to adjust its attitude and take pictures toward different sub-regions of the target area to obtain multiple second images; wherein the field of view of the second image is smaller than the field of view of the first image.
16. The method according to claim 14 or 15, characterized in that, The control of the imaging device mounted on the aircraft to adjust its attitude includes at least one of the following situations: Control the imaging device to adjust its attitude around the pitch angle of the imaging device; Control the imaging device to adjust its attitude around the yaw angle of the imaging device; The imaging device is controlled to adjust its attitude around the roll angle of the imaging device.
17. The method according to claim 14 or 15, characterized in that, The attitude adjustment of the imaging device carried by the aircraft is achieved through at least one of the following methods: The aircraft equipped with the imaging device is controlled to adjust its attitude, thereby causing the imaging device to adjust its attitude. Control the gimbal carrying the imaging device to adjust its attitude, thereby causing the imaging device to adjust its attitude; Control the imaging device itself to adjust its posture.
18. The method according to claim 1 or 2, characterized in that, The imaging device carried by the aircraft takes pictures of the target area, including: When the imaging device takes a picture toward the target area, the preset parameters of the imaging device are adjusted so that the orientation of a specific reference object in the second image relative to a specific reference plane is approximately the same as the orientation of the same specific reference object in the first image relative to the same specific reference plane.
19. The method according to claim 14, characterized in that, The control of the imaging device mounted on the aircraft to adjust its attitude to take pictures of multiple sub-regions respectively, thereby acquiring multiple second images, includes: When the imaging device takes pictures toward the target area, the preset parameters of the imaging device are adjusted so that the overlap rate between adjacent pairs of images in multiple second images is less than the preset overlap rate.
20. The method according to claim 18 or 19, characterized in that, The preset parameters include the roll angle of the imaging device.
21. The method according to claim 14, characterized in that, The control of the imaging device mounted on the aircraft to adjust its attitude to take pictures of multiple sub-regions respectively, thereby acquiring multiple second images, includes: Based on a preset shooting sequence, the imaging device is controlled to adjust its posture to shoot towards multiple sub-regions respectively, thereby acquiring multiple second images.
22. The method according to claim 21, characterized in that, The method of controlling the imaging device to adjust its posture to capture multiple second images by shooting at multiple sub-regions based on a preset shooting sequence includes: The target region is divided into an array of M rows and N columns, wherein the array includes M*N sub-regions, where M and N are both positive integers, and each sub-region corresponds to at least one of the second images; and Based on the preset shooting sequence, the imaging device is controlled to adjust its posture to shoot towards the sub-regions of the arrays respectively, thereby acquiring multiple second images.
23. The method according to claim 22, characterized in that, M and N are equal, or M and N are not equal.
24. The method according to claim 22, characterized in that, The orientation of the imaging device varies depending on the sub-region.
25. The method according to claim 22, characterized in that, In the same row direction of the array, at least one of the following conditions must be met: The yaw angle of the imaging device corresponding to each of the sub-regions increases or decreases sequentially. The pitch angles of the imaging device corresponding to each of the sub-regions are approximately the same; The yaw angle of the imaging device corresponding to each of the sub-regions is adjusted by the movement of the aircraft around the yaw axis of the aircraft; The roll angle of the imaging device corresponding to each of the sub-regions first decreases and then increases or first increases and then decreases; The roll angle of the imaging device corresponding to each of the sub-regions is adjusted by the movement of the gimbal carrying the imaging device around the roll axis of the gimbal.
26. The method according to claim 22, characterized in that, In the same column direction of the array, at least one of the following conditions is met: The pitch angle of the imaging device corresponding to each of the sub-regions increases or decreases sequentially. The yaw angles of the imaging devices corresponding to each of the sub-regions are approximately the same; The pitch angle of the imaging device corresponding to each of the sub-regions is adjusted by the movement of the gimbal carrying the imaging device around the pitch angle of the gimbal; The roll angle of the imaging device corresponding to each of the sub-regions increases or decreases sequentially. The roll angle of the imaging device corresponding to each of the sub-regions is adjusted by the movement of the gimbal carrying the imaging device around the roll axis of the gimbal.
27. The method according to claim 22, characterized in that, The preset shooting sequence includes traversing the array in a roughly "Z" shaped shooting sequence.
28. The method according to claim 27, characterized in that, The horizontal lines of the "Z" shape correspond to the row direction of the array, and the vertical lines of the "Z" shape correspond to the column direction of the array.
29. The method according to claim 27, characterized in that, The horizontal lines of the "Z" shape correspond to the column direction of the array, and the vertical lines of the "Z" shape correspond to the row direction of the array.
30. The method according to claim 22, characterized in that, In the row direction of the array, the roll angle of the imaging device corresponding to the sub-region closer to the center of the row is smaller, and the roll angle of the imaging device corresponding to the sub-region further away from the center of the row is larger.
31. The method according to claim 1 or 2, characterized in that, The imaging device carried by the aircraft takes pictures of the target area, including: The imaging device is controlled to shoot at different sub-regions of the target area to obtain multiple second images.
32. The method according to claim 31, characterized in that, The number of the second images is determined based on the size of the target region and the field of view of the imaging device corresponding to the second image.
33. The method according to claim 31, characterized in that, The multiple second images include second image A and second image B, and there is an image overlap area between second image A and second image B.
34. The method according to claim 33, characterized in that, The overlap rate of the overlapping area of the image is less than or equal to the preset overlap rate.
35. The method according to claim 34, characterized in that, The preset overlap rate is greater than or equal to 0 and less than or equal to 10%.
36. The method according to claim 34, characterized in that, The preset overlap rate is 5%.
37. The method according to claim 33, characterized in that, The step of determining statistical information related to the target object in the second image based on the identified target object includes: Based on the identified target object, statistical information related to the target object in the second image A and the second image B is determined.
38. The method according to claim 37, characterized in that, The step of determining statistically relevant information of the target object in the second image A and the second image B based on the identified target object includes: Identify the target object in the second image A containing the image overlap area and the target object in the second image B containing the image overlap area; Identify the target object in the overlapping region of the image; and Based on the target object identified in the second image A containing the image overlap area, the target object identified in the second image B containing the image overlap area, and the target object identified in the image overlap area, statistical related information of the target object in the second image A and the second image B is determined.
39. The method according to claim 38, characterized in that, The step of determining statistically relevant information about the target objects in the second image A and the second image B, based on the target objects identified in the second image A containing the image overlap region, the target objects identified in the second image B containing the image overlap region, and the target objects identified in the image overlap region, includes: The number of target objects identified in the second image A, which includes the image overlap area, is added to the number of target objects identified in the second image B, which also includes the image overlap area, and then the number of target objects identified in the image overlap area is subtracted to obtain the number of target objects in the second image A and the second image B.
40. The method according to claim 1 or 2, characterized in that, The imaging device includes a first imaging device and a second imaging device, wherein the first image is acquired by the first imaging device and the second image is acquired by the second imaging device.
41. The method according to claim 40, characterized in that, The first imaging device includes a wide-angle camera, and / or the second imaging device includes a telephoto camera.
42. The method according to claim 41, characterized in that, The second imaging device includes a zoom camera.
43. The method according to claim 40, characterized in that, The first imaging device and the second imaging device are set up independently; The first imaging device and the second imaging device are integrated within the same imaging housing; And / or, the first imaging device and the second imaging device are integrated on the same gimbal.
44. The method according to claim 1 or 2, characterized in that, The imaging device includes an optical zoom camera, and both the first image and the second image are acquired by the optical zoom camera.
45. The method according to claim 1 or 2, characterized in that, The imaging device has at least two different zoom levels.
46. The method according to claim 45, characterized in that, The imaging device mounted on the control aircraft takes pictures of the target area to obtain a second image, including: Select the target zoom magnification from the at least two different zoom magnifications; The imaging device mounted on the control aircraft is used to take pictures of the target area at the target zoom level to obtain the second image.
47. The method according to claim 46, characterized in that, The step of selecting the target zoom magnification from the at least two different zoom magnifications includes: Based on user input, the target zoom factor is selected from at least two different zoom factors.
48. The method according to claim 46, characterized in that, The imaging device has at least two different zoom magnifications. Selecting a target zoom magnification from the at least two different zoom magnifications includes: Based on preset rules, the target zoom factor is automatically selected from at least two different zoom factors.
49. The method according to claim 48, characterized in that, The automatic selection of the target zoom magnification from at least two different zoom magnifications based on preset rules includes: Based on the distance between the aircraft and the target object, the target zoom factor is automatically selected from at least two different zoom factors.
50. The method according to claim 49, characterized in that, The automatic selection of the target zoom magnification from at least two different zoom magnifications based on the distance between the aircraft and the target object includes: Based on the distance between the aircraft and the target object and the depth of field range corresponding to the acquisition of the first image, the target zoom factor is automatically selected from the at least two different zoom factors.
51. The method according to claim 1 or 2, characterized in that, The optical axis of the imaging device is not parallel to the yaw axis of the imaging device.
52. The method according to claim 51, characterized in that, The angle between the optical axis of the imaging device and the yaw axis of the imaging device is an acute angle.
53. The method according to claim 2, characterized in that, The display of statistical information related to the target object on the user interface includes: The statistical information is displayed on the user interface in a preset style.
54. The method according to claim 53, characterized in that, The display of the statistical information in a preset style on the user interface includes at least one of the following situations: The statistical information is displayed in numerical form on the user interface; The user interface displays the statistical information corresponding to different sub-regions of the target area in the form of a heatmap. At least a portion of each of the target objects is highlighted on the user interface; The target objects are marked with icons within a preset range on the user interface.
55. The method according to claim 54, characterized in that, When the target objects are marked with icons within a preset range on the user interface, different types of target objects correspond to different icon styles.
56. The method according to claim 2, characterized in that, The display of statistical information related to the target object on the user interface includes: The user interface displays statistical information related to the target objects in various categories.
57. The method according to claim 2, characterized in that, After displaying the statistical information of the target object on the user interface, the method further includes: In response to the user's editing action, the displayed statistical information is updated.
58. The method according to claim 1 or 2, characterized in that, The method further includes: generating a prompt message in response to the statistical information not meeting preset conditions.
59. The method according to claim 58, characterized in that, The prompt message is generated in response to the statistical information exceeding a preset threshold.
60. The method according to claim 59, characterized in that, The prompts include warning messages and / or evacuation guidance messages.
61. The method according to claim 1 or 2, characterized in that, The target area is selected in the first image in response to a first input operation by the user.
62. The method according to claim 61, characterized in that, The first input operation includes a user selection operation on the user interface.
63. The method according to claim 1 or 2, characterized in that, The method further includes: In response to a second input action by the user, the second image is displayed on the user interface.
64. The method according to claim 63, characterized in that, The step of displaying the second image on the user interface in response to a second input operation by the user includes: In response to the user's second input operation on the first image, the second image is toggled / overlaid on the user interface; or, In response to a second input operation by a user on a preset area of the first image, the second image corresponding to the preset area is displayed on the user interface.
65. The method according to claim 1 or 2, characterized in that, The target object includes static objects.
66. The method according to claim 1 or 2, characterized in that, The target object includes moving objects.
67. The method according to claim 1 or 2, characterized in that, The target objects include people or animals.
68. The method according to claim 1 or 2, characterized in that, The target object includes a mobile vehicle.
69. The method according to claim 68, characterized in that, The mobile vehicle includes vehicles or vessels.
70. The method according to claim 1 or 2, characterized in that, The second image includes a second image A and a second image B, which are acquired when the aircraft is in the same preset positioning position.
71. The method according to claim 70, characterized in that, The aircraft maintaining the same preset positioning position includes controlling the aircraft to hover at the same preset positioning position.
72. The method according to claim 70, characterized in that, The fact that the aircraft remains at the same preset positioning position indicates that the center of mass of the aircraft remains essentially unchanged.
73. The method according to claim 70, characterized in that, The aircraft remaining at the same preset positioning position means that the aircraft's positioning position remains basically unchanged.
74. The method according to claim 73, characterized in that, The location of the aircraft is determined by the aircraft's positioning module.
75. The method according to claim 74, characterized in that, The positioning module includes one or more of the following: GPS positioning module, GLONASS positioning module, Galileo positioning module, BeiDou positioning module, real-time dynamic RTK positioning module of base station, and network RTK positioning module.
76. A statistical method for a target object, characterized in that, include: Select a target region in the first image, wherein the target region contains a target object and the target region includes multiple sub-regions; Based on the location-related information of the target area, the aircraft is controlled to fly to one or more preset positioning locations; When the aircraft is held at one or more of the preset positioning positions, the imaging device on the aircraft is controlled to adjust its attitude to take pictures of the multiple sub-regions respectively, thereby acquiring multiple second images; wherein, the multiple second images include second image A and second image B, second image A and second image B are acquired when the aircraft is held at the same preset positioning position, second image A is acquired by the imaging device taking pictures of the target area with a first attitude, and second image B is acquired by the imaging device taking pictures of the target area with a second attitude, the first attitude is different from the second attitude, and the sub-regions covered by second image A are at least partially different from the sub-regions covered by second image B; Identify the target object in multiple second images; and Based on the identified target object, statistical information related to the target object in multiple second images is determined; Wherein, the field of view of the second image is smaller than that of the first image, and the resolution of the second image is greater than that of the first image.
77. A method for displaying a target object, characterized in that, include: Display the first image on the user interface; A selected target region is displayed on the first image, the target region containing a target object, and the target region includes multiple sub-regions; The user interface displays statistical information related to the target object. The statistical information is determined based on a second image A and a second image B. The second image A is obtained by the aircraft being positioned at a preset location and the imaging device on the aircraft being controlled to take a picture of the target area in a first posture. The second image B is obtained by the aircraft being positioned at the same preset location and the imaging device on the aircraft being controlled to take a picture of the target area in a second posture. The first posture is different from the second posture, and the sub-regions covered by the second image A and the sub-regions covered by the second image B are at least partially different. Furthermore, the field of view angles corresponding to the second image A and the second image B are both smaller than the field of view angle corresponding to the first image, and the resolutions corresponding to the second image A and the second image B are both greater than the resolutions corresponding to the first image.
78. A computer device, characterized in that, include: At least one processor; as well as At least one memory containing computer program code; In this embodiment, at least one of the memory and the computer program code are configured together with the at least one of the processors such that the computer device is at least capable of performing the method according to any one of claims 1 to 77.
79. An aircraft, characterized in that, include: At least one processor; as well as At least one memory containing computer program code; In this embodiment, at least one of the memory and the computer program code are configured together with the at least one of the processors to enable the computer device to perform at least the statistical method of claim 1 or 76.
80. A control terminal, characterized in that, include: At least one processor; as well as At least one memory containing computer program code; In this embodiment, at least one of the memory and the computer program code are configured together with the at least one of the processors to enable the computer device to perform at least the display method of claim 2 or 77.
81. A system, characterized in that, It includes the aircraft as described in claim 79 and the control terminal as described in claim 80.
82. A computer-readable storage medium storing computer instructions thereon, characterized in that, When executed by a processor, the computer instructions implement the method described in any one of claims 1 to 77.