Target tracking marking method and system, electronic equipment and storage medium
By combining the position information of the high-altitude camera device and the perspective information of the image acquisition device, calculating the relative latitude and longitude of the target and marking its parameter information, the problem that the high-altitude camera device cannot obtain the target details information is solved, and precise command and broadcast are achieved.
Patent Information
- Application Number
- CN202411879829.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-04-11
AI Technical Summary
In large-scale events or fire rescue scenarios, high-altitude camera equipment cannot obtain detailed information about the target, resulting in the command hall being unable to achieve accurate command or broadcast.
The image is acquired and the target is identified through the image acquisition device, combined with the equipment's latitude, longitude, height and northeastern pose information, calculate the relative latitude, longitude of the target, and compare it with the actual latitude, longitude, and longitude of the target. If it matches, mark the parameter information of the target in the image.
It achieves that while tracking the target, the target is marked in detail, improving the accuracy of command and the quality of broadcasting.
Smart Images
Figure CN119810149A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer vision tracking, and more particularly to a target tracking and marking method. Background Art
[0002] In scenarios such as large-scale events and fire rescue, commanders need to have a global grasp of the scene. In order to grasp the overall situation, commanders generally use high-altitude camera equipment such as high-altitude drones, helicopters carrying cameras, hot air balloons and other equipment to record the scene in real time, so as to grasp the situation on the scene in real time. With the continuous development of drone vision algorithms, drones can track targets such as personnel, vehicles and other equipment in real time, select, track, and draw trajectories of targets, and project them onto the large screen in the command hall in real time. However, the high-altitude camera equipment is located at a high position and cannot obtain detailed information about the target, such as the name of the person and the number of the vehicle. The command hall can only understand the general layout information from the global video, and cannot achieve accurate command or broadcast. If in the above scenario, the large screen can mark the detailed content of the target while displaying the global image, it will be of great value for achieving accurate broadcast and accurate command. Summary of the invention
[0003] In a first aspect, in order to solve the problem mentioned in the background technology, the present invention provides a target tracking and marking method.
[0004] The above-mentioned technical purpose of the present invention is achieved through the following technical solutions: the target tracking and marking method comprises the following steps: acquiring a first image through an image acquisition device, identifying and tracking the target; acquiring the longitude and latitude, altitude and north-east posture information of the image acquisition device, and calculating the longitude and latitude of the center point of the first image through the longitude and latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculating the relative longitude and latitude of the center point of the target according to the pixel position of the center point of the target and the longitude and latitude of the center position of the first image and the north-east posture; acquiring target information, the target information including the actual longitude and latitude and parameter information of the target; judging whether the target indicated by the relative longitude and latitude is the same target as the target indicated by the actual longitude and latitude; if so, marking the target in the first image with the target parameter information.
[0005] Furthermore, the target information is acquired through a terminal device, which includes a positioning device, a storage device and a communication device; the positioning device is used to obtain the actual longitude and latitude of the target, and the storage device stores the target parameter information; the communication device is used to send the actual longitude and latitude of the target and the target parameter information.
[0006] Furthermore, the target information is acquired through an image acquisition device; the target carries a coding carrier; there is a code on the coding carrier; the specific method is as follows: acquire a second image through the image acquisition device, identify the coding carrier, and parse the code to obtain target parameter information; acquire the longitude and latitude, altitude and north-east posture information of the image acquisition device, and calculate the longitude and latitude of the center point of the second image through the longitude and latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the coding carrier according to the pixel position of the center point of the coding carrier and the longitude and latitude of the center position of the second image and the north-east posture.
[0007] Furthermore, the code is arranged horizontally; includes an identification segment and an information segment; the identification segment is arranged in front of the information segment to indicate the reading order; the identification segment is a black triangle block; the information segment is used to store the encoded information; the information segment includes a plurality of square pixel blocks arranged in sequence; the square pixel blocks are arranged horizontally in sequence; the square pixel blocks are black or white; the black and white square pixel blocks are decoded to represent 0 and 1, respectively.
[0008] Furthermore, there are 8 square pixel blocks in total, representing an 8-bit binary number; the target parameter acquisition method is as follows: construct a correspondence table between coding information and target parameters; the target parameters include one or more of target type, model, name, position, and age; obtain the code through an image acquisition device, and obtain the coding information after parsing the code; obtain the target parameter information through the correspondence table.
[0009] Furthermore, the image acquisition device is a drone or a helicopter; the image acquisition device is a drone image payload or a camera.
[0010] In a second aspect, the present invention provides a target tracking and marking system, comprising the following modules: a global image acquisition module, configured to acquire a first image, identify and track a target in the first image; a target relative longitude and latitude calculation module, configured to acquire the longitude and latitude, altitude and north-east posture information of the global image acquisition module, and calculate the longitude and latitude of the center point of the first image through the longitude and latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the target according to the pixel position of the center point of the target and the longitude and latitude of the center position of the first image, and the north-east posture; a target information mapping module; configured to acquire target information, the target information including the actual longitude and latitude and parameter information of the target; determine whether the target indicated by the relative longitude and latitude is the same target as the target indicated by the actual longitude and latitude; if so, mark the target in the first image with the target parameter information.
[0011] Furthermore, it also includes: a target information acquisition module; configured to acquire a second image, identify a coding carrier, and parse the code to obtain target parameter information; the coding carrier is carried by a target; the coding information is obtained after the code is identified; the coding information has a corresponding relationship with the target parameter information; the target parameter information is obtained after the code is parsed; a target actual longitude and latitude calculation module is configured to acquire the longitude and latitude, altitude and north-east posture information of the target information acquisition module, calculate the longitude and latitude of the center point of the second image through the longitude and latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the coding carrier according to the pixel position of the center point of the coding carrier and the longitude and latitude of the center position of the second image and the north-east posture.
[0012] In a third aspect, the present invention provides an electronic device, characterized in that it includes at least one processor, at least one memory and a data bus; wherein: the processor and the memory communicate with each other through the data bus; the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute any one of the methods described in the first aspect.
[0013] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any one of the first aspects.
[0014] In summary, the present invention has at least the following beneficial effects:
[0015] By combining the latitude and longitude, altitude, north-east posture and viewing angle information of the image acquisition device, the solution can accurately calculate the longitude and latitude of the center point of the first image, and further deduce the relative longitude and latitude of the target center point; then compare it with the actual longitude and latitude of the target to obtain the parameter information of the tracked target. It can mark the target while tracking it. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 Schematic diagram of target tracking and marking method
[0017] Figure 2 The corresponding schematic diagram of Example 1
[0018] Figure 3 It is a coding diagram
[0019] Figures 4-5 Schematic diagram of target tracking and marking system in Example 2
[0020] Figures 6-7 This is a schematic diagram of the effect of embodiment 2.
[0021] Figure 8 Schematic diagram of electronic equipment in Example 3 DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0023] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the various embodiments described below and the various features in the embodiments can be combined with each other. In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. In addition, the naming or numbering of the steps appearing in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.
[0024] Embodiment 1:
[0025] like Figure 1 As shown, the technical solution provided in this embodiment is applied to scenes such as events and fire rescue. For the sake of convenience, this embodiment uses the fire rescue scene as an example. During the fire rescue process, the command hall often uses equipment such as drones to grasp the overall situation of the rescue scene. For example, the distribution of personnel and vehicles on the scene, the distance between personnel and the rescue point, and other information.
[0026] A target tracking and marking method applied to a fire rescue scene comprises the following steps:
[0027] S1 acquires a first image through an image acquisition device to identify and track a target. The first image is an image that can reflect the overall situation, such as using a drone to acquire images at high altitude.
[0028] S2 obtains the latitude and longitude, altitude and north-east posture information of the image acquisition device, and calculates the longitude and latitude of the center point of the first image through the latitude and longitude, altitude, north-east posture and viewing angle information of the image acquisition device.
[0029] S3 calculates the relative longitude and latitude of the target center point according to the pixel position of the target center point and the longitude and latitude of the center position of the first image and the north-east posture; obtains target information, wherein the target information includes the actual longitude and latitude and parameter information of the target;
[0030] S4 determines whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude; if so, the target is marked in the first image with target parameter information.
[0031] In this embodiment, the image acquisition device includes a carrying platform, a gimbal and a camera. The carrying platform can be a quad-axis or multi-axis rotor drone, a helicopter, a hot air balloon or other aircraft that can fly stably. The image acquisition device is equipped with an artificial intelligence image recognition model, which can realize the functions of selecting, tracking and marking the target.
[0032] Optionally, the recognition and tracking of the target described in step S1 uses the algorithm provided by OPENCV. This includes
[0033] Shi-Tomasi Corner Detection Algorithm: It is used to detect feature points in the first frame of the video, which will be used for tracking in subsequent frames. This is achieved through the cv2.goodFeaturesToTrack function, which detects corners based on given parameters such as maximum number of corners, quality level, minimum distance, and block size.
[0034] Lucas-Kanade optical flow algorithm: used to calculate the motion of feature points between two frames. This is implemented by the cv2.calcOpticalFlowPyrLK function, which calculates the change in the position of feature points between the old frame (old_gray) and the new frame (frame_gray). The optical flow algorithm assumes that feature points move "smoothly" in consecutive frames, and tries to find the new position of each feature point in the next frame.
[0035] The two algorithms are combined to track moving objects in the video. The cv2.add function is also used to overlay the drawn trajectory onto the current frame so that the tracking effect can be displayed while the video is playing.
[0036] The carrying platform provided in this embodiment includes GPS, Beidou positioning or other positioning devices, which can obtain the latitude and longitude position information of the carrying platform; it also includes an altimeter or a laser rangefinder for measuring the height of the carrying platform from the ground or the distance between the carrying platform and the measurement point.
[0037] In step S2, the viewing angle information includes the pitch angle, horizontal angle, focal length and resolution of the gimbal. Taking a drone equipped with a gimbal and a camera as an example, obtaining the longitude and latitude of the center point of the first graphic includes the following steps:
[0038] Keep the drone level and make the drone nose always face due north, and establish a north-east coordinate system with the drone; the azimuth of the center point of the first image relative to the ground projection point of the drone can be calculated through the horizontal angle of the gimbal rotation; after obtaining the height and the pitch angle of the gimbal, the distance between the center point of the first image and the ground projection point of the drone, as well as the distance between the drone and the corresponding position of the center point of the first image can be calculated through trigonometric functions.
[0039] After obtaining the longitude and latitude of the drone through GPS or Beidou positioning, the longitude and latitude of the center point of the first image can be calculated through the direction and distance between the center point of the first image and the ground projection point of the drone.
[0040] In step S3, after the target is identified in the first image, the pixel coordinates of the target point are obtained; then the direction, pixel distance and orientation parameters between the center point of the target and the center point of the first image can be calculated. The relative distance between the corresponding position of the center point of the first image and the center point of the target can be obtained through the focal length of the image acquisition device, the distance between the drone and the center point of the first image, and the pixel distance between the center point of the target and the center point of the first image.
[0041] The relative distance calculation formula between the corresponding position of the center point of the first image and the center point of the target is as follows:
[0042] L d =L p* L h / L f；
[0043] Among them, L d is the relative distance between the target and the corresponding position of the center point of the first image, L p is the pixel distance between the center point of the target in the first image and the center point of the first image; L h is the distance between the UAV and the corresponding position of the center point of the first image; L f is the focal length of the camera.
[0044] The relative longitude and latitude of the target center point are calculated by the relative distance and orientation parameters and the longitude and latitude of the corresponding position of the center point of the first image. The target may be a person, a vehicle, or equipment.
[0045] The image acquisition device does not directly measure the actual latitude and longitude of the target, and cannot obtain detailed information of the target. Therefore, in step S4, it is necessary to obtain relatively accurate actual latitude and longitude of the target and target parameter information.
[0046] Optionally, the method for determining whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude is as follows: the actual longitude and latitude are compared with the relative longitude and latitude. If the distance is lower than a threshold, it is considered that the two indicate the same target, a corresponding relationship between the target in the first image and the actual target is established, and the target is marked in the first image with the target parameter information. The image acquisition device sends the processed image to the large screen of the on-site command center for real-time display. The threshold selection is conventionally selected by those skilled in the art.
[0047] Optionally, when there are multiple targets in the first image, the method for determining whether the target indicated by the relative longitude and latitude and the target indicated by the actual longitude and latitude are the same target is to obtain the relative longitude and latitude and the actual longitude and latitude of the multiple targets; compare the actual longitude and latitude with the relative longitude and latitude one by one, and the group with the smallest difference between the relative longitude and latitude and the actual longitude and latitude is considered to indicate the same target. Thereafter, a corresponding relationship between the target in the first image and the actual target is established, and the target is marked in the first image with the target parameter information.
[0048] In a possible solution, the target information is obtained through a terminal device, which includes a positioning device, a storage device and a communication device; the positioning device is used to obtain the actual longitude and latitude of the target, and the storage device stores the target parameter information; the communication device is used to send the actual longitude and latitude of the target and the target parameter information. The terminal device is a special device such as a mobile phone or walkie-talkie carried by firefighters; or a navigator, communicator and other devices carried by vehicles. The terminal device is used to be installed on the vehicle or carried by the firefighter. The terminal device can send location information and target parameter information in real time. The target parameter information includes information such as the name of the person, age, gender, length of service, type of work, license plate number, and vehicle type.
[0049] In one possible solution, the image acquisition device is capable of simultaneously identifying and tracking multiple targets. The above solution is used to calculate the relative longitude and latitude of each target respectively. After obtaining the actual longitude and latitude of the target, the set of actual longitude and latitude closest to the relative longitude and latitude is determined to be the same target, and the target is marked using the parameter information of the target.
[0050] In a possible solution, the target information is acquired by an image acquisition device; the target carries a coding carrier; the coding carrier has a code; the specific steps are as follows:
[0051] S30 constructs a correspondence table between the coding information and the target parameter information; Figure 2 As shown, the target parameter information includes one or more of target type, model, name, position, and age.
[0052] S31 acquires the second image through the image acquisition device, identifies the coding carrier, parses the coding to obtain coding information, and obtains the target parameter information by looking up the corresponding table.
[0053] S32 obtains the latitude and longitude, altitude and north-east posture information of the image acquisition device, and calculates the longitude and latitude of the center point of the second image through the latitude and longitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculates the relative longitude and latitude of the center point of the encoding carrier according to the pixel position of the center point of the encoding carrier and the longitude and latitude of the center position of the second image and the north-east posture.
[0054] The coding carrier can be a helmet, the top of a vehicle, clothes worn by firefighters, etc.
[0055] The image acquisition device can be a drone or a fixed camera installed on site. The imaging device can recognize specific codes, such as QR codes, bar codes, etc. The image acquisition device includes a positioning device, a communication device, and a height measurement device. The method by which the image acquisition device obtains the relative longitude and latitude of the encoding carrier through the second image is as described above and will not be repeated here.
[0056] like Figure 3 As shown, in a possible solution, the code is arranged horizontally; it includes an identification segment and an information segment; the identification segment is set before the information segment to indicate the reading order; the identification segment is a black triangle block. The information segment is used to store the coded information; the information segment includes a plurality of sequentially arranged square pixel blocks; the square pixel blocks are sequentially arranged horizontally; the square pixel blocks are black or white; the black and white square pixel blocks are decoded to represent 0 and 1 respectively.
[0057] There are a total of 8 square pixel blocks, representing an 8-bit binary number; 256 target parameter information can be obtained. If the number of targets is large, a larger capacity can be obtained by increasing the number of binary bits. Using 8 pixel blocks, on the one hand, this encoding method can meet most usage scenarios. On the other hand, the code composed of 8 pixel blocks can be displayed as clearly as possible in a limited space. Compared with a QR code or a barcode, the code provided by this embodiment is more conducive to the recognition of the code by a drone or a fixed camera at a certain distance.
[0058] In a possible equivalent solution, the square pixel blocks may be colored blocks, and blocks of different colors may be used to represent more dimensional information, such as black and white blocks representing people, and red and yellow blocks representing vehicles.
[0059] In a possible equivalent solution, the square pixel blocks may be colored blocks, and different colored blocks may represent different numbers, such as white for 0, black for 1, yellow for 2, blue for 4, and red for 5. Similarly, different colors may be used to represent 0 to 9.
[0060] Example 2
[0061] like Figure 4 As shown, this embodiment provides a target tracking and marking system, including the following modules:
[0062] The global image acquisition module is configured to acquire a first image, and identify and track a target in the first image.
[0063] The target relative longitude and latitude calculation module is configured to obtain the longitude and latitude, altitude and north-east posture information of the global image acquisition module, calculate the longitude and latitude of the center point of the first image through the longitude and latitude, altitude, north-east posture and viewing angle information of the image acquisition device; and calculate the relative longitude and latitude of the center point of the target based on the pixel position of the center point of the target and the longitude and latitude of the center position of the first image and the north-east posture.
[0064] The target actual longitude and latitude calculation module is configured to obtain target information, which includes the actual longitude and latitude of the target and parameter information; determine whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude; if so, mark the target in the first image with the target parameter information.
[0065] The target parameter information storage module is configured to construct or store a correspondence table between the encoding information and the target parameter information.
[0066] The target information acquisition module is configured to acquire the second image, identify the coding carrier, and parse the code to obtain target parameter information; the coding carrier is carried by the target; after identifying the code, the coding information is obtained; after parsing the code, the target parameter information is obtained through a corresponding table.
[0067] The target information mapping module is configured to obtain target information, which includes the actual longitude and latitude of the target and target parameter information; determine the proximity between the relative longitude and latitude and the actual longitude and latitude, and if the proximity is lower than a threshold, determine that the target identified in the first image is the same as the actual target, and finally mark the target using the target parameter information.
[0068] like Figure 5As shown, in a possible solution, the global image acquisition module, the target relative longitude and latitude module and the target information mapping module are deployed on a high-altitude UAV; the target actual longitude and latitude calculation module and the target information acquisition module are deployed on a low-altitude UAV. The high-altitude UAV refers to a UAV used to collect global images at high altitudes in this system, and the low-altitude UAV refers to a UAV used to obtain target coding information at low altitudes. The low-altitude UAV obtains the actual longitude and latitude of the target and the target parameter information through the method provided in Example 1 and transmits them to the high-altitude UAV; the high-altitude UAV tracks and marks the target using the method provided in Example 1, and then transmits the processed image information to the command center for display on the large screen.
[0069] In a possible solution, the parameter information storage module may be configured in a low-altitude UAV. The low-altitude UAV directly parses and obtains the target parameter information and transmits it to the high-altitude UAV.
[0070] In a possible solution, the parameter information storage module is configured in the server. In this solution, the low-altitude drone collects the code and transmits it to the server. The server obtains the target parameter information by looking up the corresponding table and transmits it to the low-altitude drone, which then transmits it to the high-altitude drone; and displays the target parameter information in the video image of the high-altitude drone.
[0071] In a possible solution, the parameter information storage module is configured on a high-altitude drone, and the low-altitude drone transmits the collected coded information to the high-altitude drone, which parses the code to obtain the target parameter information.
[0072] The beneficial effects of this embodiment are as follows:
[0073] like Figures 6-7 As shown in the figure, high-altitude drones take pictures of the overall situation and use intelligent algorithms to track the real-time location of people and vehicles. Low-altitude drones can be controlled to take pictures of the positions of each person and vehicle, decode the information obtained, and then transmit it to high-altitude drones, which will be displayed in the video images of high-altitude drones. High-altitude drones will mark the information of people and vehicles in the high-altitude global images. Rescuers can see the name and location of each person from the global image, which is convenient for rescue commanders to dispatch personnel.
[0074] After the low-altitude drone acquires the parameters of a target, the high-altitude drone stably tracks and marks it and can fly to other targets. One low-altitude drone can cover a large area.
[0075] Example 3
[0076] like Figure 8As shown, an embodiment of the present application provides an electronic device, which includes at least one processor, at least one memory and a data bus; wherein: the processor and the memory communicate with each other through the data bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute a target tracking and marking method. For example, the following is implemented:
[0077] Acquire the first image, identify and track the target in the first image. Acquire the longitude, latitude, altitude and north-east posture information of the global image acquisition module, calculate the longitude and latitude of the center point of the first image through the longitude, latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the target according to the pixel position of the center point of the target and the longitude and latitude of the center position of the first image, and the north-east posture. Acquire the longitude, latitude, altitude and north-east posture information of the target information acquisition module, calculate the longitude and latitude of the center point of the second image through the longitude, latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the encoding carrier according to the pixel position of the center point of the encoding carrier and the longitude and latitude of the center position of the second image, and the north-east posture. Construct or store a correspondence table between the encoding information and the target parameter information. Acquire the second image, identify the encoding carrier, parse the encoding to obtain the target parameter information; the encoding carrier is carried by the target; obtain the encoding information after identifying the encoding; obtain the target parameter information through the correspondence table after parsing the encoding. Obtain target information, the target information including actual longitude and latitude of the target and parameter information; determine whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude; if so, mark the target in the first image with the target parameter information.
[0078] Among them, the memory can be, but is not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
[0079] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0080] Example 4
[0081] The present application provides a computer-readable storage medium having a computer program stored thereon, which implements a target tracking and marking method when executed by a processor. For example, it implements:
[0082] Acquire the first image, identify and track the target in the first image. Acquire the longitude, latitude, altitude and north-east posture information of the global image acquisition module, calculate the longitude and latitude of the center point of the first image through the longitude, latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the target according to the pixel position of the center point of the target and the longitude and latitude of the center position of the first image, and the north-east posture. Acquire the longitude, latitude, altitude and north-east posture information of the target information acquisition module, calculate the longitude and latitude of the center point of the second image through the longitude, latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the encoding carrier according to the pixel position of the center point of the encoding carrier and the longitude and latitude of the center position of the second image, and the north-east posture. Construct or store a correspondence table between the encoding information and the target parameter information. Acquire the second image, identify the encoding carrier, parse the encoding to obtain the target parameter information; the encoding carrier is carried by the target; obtain the encoding information after identifying the encoding; obtain the target parameter information through the correspondence table after parsing the encoding. Obtain target information, the target information including actual longitude and latitude of the target and parameter information; determine whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude; if so, mark the target in the first image with the target parameter information.
[0083] If the above functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.
[0084] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.
Claims
1. A target tracking and marking method, characterized in that: The target tracking and marking method comprises the following steps: Acquire a first image through an image acquisition device, and identify and track a target; Obtaining the latitude and longitude, altitude, and north-east posture information of the image acquisition device, and calculating the longitude and latitude of the center point of the first image through the latitude and longitude, altitude, north-east posture, and viewing angle information of the image acquisition device; Calculate the relative longitude and latitude of the center point of the target according to the pixel position of the center point of the target, the longitude and latitude of the center position of the first image, and the north-east posture; Acquire target information, wherein the target information includes actual latitude and longitude and parameter information of the target; Determine whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude; if so, mark the target in the first image with target parameter information.
2. A target tracking and marking method according to claim 1, characterized in that: The target information is obtained through a terminal device, which includes a positioning device, a storage device and a communication device; the positioning device is used to obtain the actual latitude and longitude of the target, and the storage device stores the target parameter information; The communication device is used to send the actual latitude and longitude of the target and target parameter information.
3. A target tracking and marking method according to claim 1, characterized in that: The target information is obtained by an image acquisition device; the target carries a coding carrier; the coding carrier has a code; the specific method is as follows: Acquire a second image through an image acquisition device, identify the coding carrier, and parse the coding to obtain target parameter information; Obtain the latitude and longitude, altitude and north-east posture information of the image acquisition device, and calculate the longitude and latitude of the center point of the second image through the latitude and longitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the encoding carrier according to the pixel position of the center point of the encoding carrier and the longitude and latitude of the center position of the second image and the north-east posture.
4. A target tracking and marking method according to claim 3, characterized in that: The codes are arranged horizontally; It includes an identification segment and an information segment; the identification segment is arranged before the information segment and is used to indicate the reading order; the identification segment is a black triangle block; The information segment is used to store coded information; the information segment includes a plurality of square pixel blocks arranged in sequence; the square pixel blocks are arranged in sequence horizontally; the square pixel blocks are black or white; the black and white square pixel blocks are decoded to represent 0 and 1 respectively.
5. A target tracking and marking method according to claim 4, characterized in that: There are 8 square pixel blocks in total, representing an 8-bit binary number; the target parameter acquisition method is as follows: Constructing a correspondence table between the coding information and the target parameters; the target parameters include one or more of the target type, model, name, position, and age; Obtain the code through the image acquisition device, and obtain the code information after parsing the code; The target parameter information is obtained through the correspondence table.
6. A target tracking and marking method according to claim 5, characterized in that: The image acquisition device is a drone or a helicopter; the image acquisition device is a drone image payload or a camera.
7. A target tracking and marking system, characterized in that: Includes the following modules: A global image acquisition module is configured to acquire a first image, identify and track a target in the first image; The target relative longitude and latitude calculation module is configured to obtain the longitude and latitude, altitude and north-east attitude information of the global image acquisition module, calculate the longitude and latitude of the center point of the first image through the longitude and latitude, altitude, north-east attitude and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the target according to the pixel position of the center point of the target and the longitude and latitude of the center position of the first image and the north-east attitude; The target information mapping module is configured to obtain target information, which includes the actual longitude and latitude of the target and parameter information; determine whether the target indicated by the relative longitude and latitude is the same as the target indicated by the actual longitude and latitude; if so, mark the target in the first image with the target parameter information.
8. The target tracking and marking system according to claim 7, characterized in that: include: The target information acquisition module is configured to acquire the second image, identify the coding carrier, and parse the coding to obtain the target parameter information; The coding carrier is targeted; After the code is identified, the code information is obtained; the code information corresponds to the target parameter information; after the code is parsed, the target parameter information is obtained; The actual longitude and latitude calculation module of the target is configured to obtain the longitude and latitude, altitude and north-east posture information of the target information acquisition module, calculate the longitude and latitude of the center point of the second image through the longitude and latitude, altitude, north-east posture and viewing angle information of the image acquisition device; calculate the relative longitude and latitude of the center point of the encoding carrier according to the pixel position of the center point of the encoding carrier and the longitude and latitude of the center position of the second image and the north-east posture.
9. An electronic device, characterized in that: It includes at least one processor, at least one memory and a data bus; wherein: the processor and the memory communicate with each other through the data bus; the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the method according to any one of claims 1-6.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.