Object recognition method and device, computer equipment and medium

Abstract

The invention relates to the technical field of target recognition, and discloses an object recognition method and device, computer equipment and a medium, and the method comprises the steps: obtaining a target image and flight parameters of an unmanned plane, recognizing a first object in the target image and pixel coordinates of the first object, and determining the geographic position of the first object based on the flight parameters and the pixel coordinates of the unmanned plane, and determining a target object in the target area according to the geographic position of the first object. According to the method, the first object in the target image is identified, and then the target object in the target range is acquired according to the geographic position of the first object, so that omission of the to-be-identified object in the target range is reduced, and the identification accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of target recognition technology, and in particular to an object recognition method, device, computer equipment and medium. Background Art

[0002] Drones (unmanned aerial vehicles) have a wide range of application scenarios in many fields due to their high efficiency, flexibility and versatility. Inspection drones are drone systems that carry various sensors (such as high-definition cameras, infrared thermal imaging, laser radar, etc.) and combine technologies such as the Internet of Things, cloud computing and artificial intelligence to complete large-scale, high-efficiency inspection tasks. Due to the large range of drone photography, current technology can usually only identify all objects within the shooting range, making it difficult to identify them in a targeted manner. Summary of the invention

[0003] In view of this, the present invention provides an object recognition method, apparatus, computer device and medium to solve the problem that it is difficult to specifically recognize objects.

[0004] In a first aspect, the present invention provides an object recognition method, the method comprising:

[0005] Obtain target images and UAV flight parameters;

[0006] Identifying a first object in a target image and pixel coordinates of the first object, and determining a geographic location of the first object based on flight parameters of the drone and the pixel coordinates;

[0007] A target object within a target area is determined based on the geographic location of the first object.

[0008] In a second aspect, the present invention provides an object recognition device, the device comprising:

[0009] Parameter acquisition module, used to obtain target images and flight parameters of the UAV;

[0010] a location determination module, configured to identify a first object in a target image and pixel coordinates of the first object, and determine a geographic location of the first object based on flight parameters of the drone and the pixel coordinates;

[0011] The target object determination module is used to determine the target object in the target area based on the geographical location of the first object.

[0012] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the method of the first aspect or any corresponding embodiment thereof.

[0014] The object recognition method provided by the present invention includes acquiring a target image and flight parameters of a drone, identifying a first object in the target image and the pixel coordinates of the first object, and determining the geographic location of the first object based on the flight parameters and pixel coordinates of the drone, and then determining the target object in the target area according to the geographic location of the first object. The present invention reduces the omission of objects to be recognized within the target range and improves the recognition accuracy by recognizing the first object in the target image and then acquiring the target object within the target range according to the geographic location of the first object. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a flow chart of an object recognition method according to an embodiment of the present invention;

[0017] Figure 2 is a structural block diagram of an object recognition device according to an embodiment of the present invention;

[0018] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] The full name of UAV is unmanned aircraft, which is an unmanned aircraft controlled by radio remote control equipment and self-contained program control devices, or an aircraft operated completely or intermittently autonomously by an on-board computer. Inspection UAV is a UAV system that is equipped with various sensors (such as high-definition cameras, infrared thermal imaging, lidar, etc.), combined with technologies such as the Internet of Things, cloud computing and artificial intelligence, to complete large-scale and high-efficiency inspection tasks. Electronic fence technology is usually aimed at the fence of UAV flight. The electronic fence is a virtual flight boundary set for the UAV using a positioning system. Since the range of UAV shooting is relatively large, current technology can usually only identify all objects within the shooting range, and it is difficult to specifically identify objects within the electronic fence. Based on this, the present invention provides an object recognition method.

[0021] According to an embodiment of the present invention, an embodiment of an object recognition method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0022] In this embodiment, an object recognition method is provided, which can be used in terminals such as computers and tablet computers. Figure 1 is a flow chart of an object recognition method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0023] Step S101, obtaining a target image and flight parameters of the UAV.

[0024] The target image is captured by the drone when it is performing a flight mission. The drone is equipped with a collection device, such as a camera, which can be used to take photos or videos. When the drone collects the video, the target image can be captured from the video as needed.

[0025] The flight parameters of the drone correspond to the target image, that is, in this embodiment, the flight parameters of the drone refer to the flight parameters of the drone when shooting the target image. The flight parameters may specifically include the latitude and longitude, flight altitude, attitude angle, etc. of the drone, where the attitude angle may include roll angle, pitch angle and yaw angle, and the attitude angle describes the angle of the acquisition device on the drone relative to the world coordinate system.

[0026] Step S102, identifying a first object and pixel coordinates of the first object in the target image, and determining a geographic location of the first object based on flight parameters of the drone and the pixel coordinates.

[0027] The first object is a pre-set object to be identified, the pixel coordinates represent the coordinates of the first object in the target image, the pixel coordinates are in pixels, and the geographic location of the first object represents the longitude and latitude of the first object. Identify all first objects in the target image, and further determine the pixel coordinates of all first objects in the image, the pixel coordinates are in pixels.

[0028] In order to determine the geographic location of the first object, the pixel coordinates can be first converted into image coordinates in the target image, where the image coordinates represent the coordinates in the target image in the image coordinate system, and the image coordinates are in physical length (e.g., millimeters). The image coordinates are then converted into the camera coordinate system, which is a three-dimensional rectangular coordinate system established with the optical center of the camera as the origin. When converting the image coordinates to the camera coordinate system, the flight height in the flight parameters can be used, and the flight height is used as the z coordinate of the camera coordinate system coordinates. The x coordinate and y coordinates in the camera coordinate system are calculated based on the flight height. The camera coordinate system coordinates are then converted into the world coordinate system. The world coordinate system coordinates are used to describe the position of the object in the real world. Specifically, a rotation matrix can be constructed according to the flight parameters of the drone, and the camera coordinate system coordinates are converted into the world coordinate system through the rotation matrix. This process actually converts the first object in the target image captured by the camera from the coordinate system centered on the camera to the world coordinate system centered on the real world. After obtaining the world coordinate system coordinates, the world coordinate system coordinates are converted into longitude and latitude to determine the geographic location of the first object.

[0029] Step S103: determining a target object in a target area based on the geographic location of the first object.

[0030] The target area is a pre-set area. The target area is a range defined based on the actual ground conditions. The target area can be used as an electronic fence. Since the drone takes pictures at a certain flight altitude, the collected target image may not be completely equivalent to the target area. The target image may contain part or all of the target area.

[0031] The first object in the target area is determined by the geographical location of the first object, and the first object in the target area is defined as the target object. This embodiment is used to identify the first object (ie, the target object) in the target area.

[0032] In this embodiment, real-time recognition can be performed according to the recognition requirements, and an early warning can be issued immediately if a problem is found after the target object in the target area is recognized. For example, if the drone collects a target image over the railroad track, the area inside the railroad track is set as the target area, the first object is a person, and the target image contains not only the railroad track but also the area outside the railroad track, and the target object to be recognized is the person inside the railroad track in the target image. For safety reasons, an early warning can be issued immediately if a person is found inside the railroad track.

[0033] The object recognition method provided in this embodiment includes acquiring a target image and flight parameters of a drone, identifying a first object in the target image and the pixel coordinates of the first object, and determining the geographic location of the first object based on the flight parameters and pixel coordinates of the drone, and then determining the target object in the target area according to the geographic location of the first object. The present invention reduces the omission of objects to be recognized within the target range and improves the recognition accuracy by recognizing the first object in the target image and then acquiring the target object within the target range according to the geographic location of the first object.

[0034] In this embodiment, a method for object recognition is provided, which comprises the following steps:

[0035] Step S201, obtain the target image and the flight parameters of the UAV. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0036] Step S202: Identify a first object and pixel coordinates of the first object in the target image, and determine a geographic location of the first object based on the flight parameters of the drone and the pixel coordinates.

[0037] Specifically, the above step S202 includes:

[0038] Step S2021, obtaining identification requirements.

[0039] The recognition requirement at least includes a first object and a target area.

[0040] The recognition requirement includes the object that needs to be recognized by the object recognition method provided in the embodiment of the present invention, that is, the first object and the target area. In this embodiment, the first object can be a person, an animal, or any other entity that needs to be recognized. For the user, the first object to be recognized can be input according to the actual object recognition requirement, and the target area can be set. When setting the target area, it can be achieved by inputting the boundary coordinates or the longitude and latitude of the boundary.

[0041] In addition, the recognition requirements may also include some system parameters, such as setting the image processing method, and may also capture the video collected by the drone as required. The recognition requirements include but are not limited to the first object and the target area.

[0042] Step S2022: Identify the first object in the target image based on the identification requirement, and determine the pixel coordinates of the first object.

[0043] After the recognition requirement is determined, all first objects in the target image are recognized, and pixel coordinates of all first objects are collected according to the recognized first objects.

[0044] Step S203: determining the geographic location of the first object based on the flight parameters and pixel coordinates of the drone.

[0045] Specifically, the above step S203 includes:

[0046] Step S2031, converting pixel coordinates into image coordinates based on the central pixel coordinates of the target image.

[0047] The center pixel coordinates of the target image represent the pixel coordinates of the center point of the target image. This step is used to convert the pixel coordinates of the first object into image coordinates. The pixel coordinate system where the pixel coordinates are located has the upper left corner of the image as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis. The image coordinate system where the image coordinates are located is a coordinate system with the center of the target image as the origin.

[0048] Further, step S2031 includes the following steps:

[0049] (1) A first coordinate difference and a second coordinate difference are determined based on the pixel coordinates and the center pixel coordinates.

[0050] The center pixel coordinates refer to the coordinates of the center point of the target image in the pixel coordinate system. Let the pixel coordinates be (u, v) and the center pixel coordinates be (x0, y0).

[0051] The differences between the x-coordinate and the y-coordinate of the pixel coordinate and the center pixel point coordinate are calculated respectively, the first coordinate difference is used to represent the x-coordinate difference, and the second coordinate difference is used to represent the y-coordinate difference.

[0052] (2) Determine a first coordinate in the image coordinates based on the first coordinate difference and the physical length in the first direction, and determine a second coordinate in the image coordinates based on the second coordinate difference and the physical length in the second direction.

[0053] The physical length in the first direction represents the physical length corresponding to each pixel in the x-axis direction in the pixel coordinate system, and the physical length in the second direction represents the physical length corresponding to each pixel in the y-axis direction in the pixel coordinate system. The first coordinate in the image coordinate represents the coordinate in the x-axis direction in the image coordinate system, and the second coordinate represents the coordinate in the y-axis direction in the image coordinate system. The image coordinates are determined according to the following formula:

[0054] x=(u-x0)×dx

[0055] y=(v-y0)×dy

[0056] Among them, image coordinates (x, y), pixel coordinates (u, v), center pixel coordinates (x0, y0), dx represents the physical length in the first direction, and dy represents the physical length in the second direction.

[0057] Step S2032, determining the height of the drone relative to the ground based on the flight parameters of the drone, and converting the image coordinates to the camera coordinate system based on the camera parameters and the height to determine the camera coordinate system coordinates.

[0058] The camera is arranged on the UAV, and the camera parameters at least include the focal length of the camera.

[0059] Assume that the acquisition device on the drone is a camera, and the flight parameters of the drone include the height of the drone relative to the ground when acquiring the target image. The camera parameters include the focal length of the camera, which is a basic optical parameter of the camera lens and determines the magnification of the imaging. In this embodiment, it represents the focal length used by the camera when acquiring the target image.

[0060] In this step, the image coordinates are converted to the camera coordinate system. The camera coordinate system is a three-dimensional rectangular coordinate system established with the optical center of the camera as the origin. The height can be used as the z coordinate of the camera coordinate system, and the x and y coordinates of the camera coordinate system can be calculated based on the height.

[0061] Further, step S2032 includes the following steps:

[0062] (1) Calculate the first product of the first coordinate in the image coordinates and the height, and the second product of the second coordinate in the image coordinates and the height, respectively.

[0063] (2) Determine the coordinates of the camera coordinate system based on the ratio of the first product to the camera focal length and the ratio of the second product to the camera focal length.

[0064] The camera coordinate system coordinates are determined according to the following formula:

[0065]

[0066] The image coordinates are (x, y), x represents the first coordinate in the image coordinates, y represents the second coordinate in the image coordinates, and Z c represents the height, f represents the focal length of the camera, and the coordinates of the camera coordinate system are (X c ,Y c ,Z c ).

[0067] Step S2033, constructing an attitude angle rotation matrix according to the flight parameters of the UAV, and converting the camera coordinate system coordinates into the world coordinate system coordinates according to the rotation matrix.

[0068] The flight parameters of the drone also include attitude angles, which include roll angle, pitch angle, and yaw angle. In this step, the camera coordinate system coordinates are converted to the world coordinate system to obtain the world coordinate system coordinates. The world coordinate system coordinates can be used to describe the position of an object in the real world. Specifically, a rotation matrix can be constructed according to the flight parameters of the drone, and the camera coordinate system coordinates can be converted to the world coordinate system through the rotation matrix.

[0069] Further, step S2033 includes the following steps:

[0070] (1) Calculate the third product of the camera coordinate system coordinates and the rotation matrix.

[0071] (2) Determine the world coordinate system coordinate based on the sum of the third product and the first coordinate of the drone.

[0072] Among them, the first coordinate of the drone is used to represent the coordinate of the drone in the world coordinate system.

[0073] The rotation matrix R is constructed according to the attitude angle of the drone. First, the rotation moment of each attitude angle is constructed as follows:

[0074]

[0075] Among them, R ω represents the roll angle matrix, R θ represents the pitch angle matrix, R k Represents the yaw angle matrix.

[0076] In order to obtain the total rotation matrix R, these rotation matrices need to be multiplied in a specific order. The rotation matrix R is obtained as follows:

[0077] R=R ω ·R θ ·R κ

[0078] The world coordinate system coordinates are determined according to the following formula:

[0079]

[0080] The world coordinate system is (X, Y, Z), the first coordinate of the drone is (X0, Y0, Z0), and the camera coordinate system is (X c ,Y c ,Z c ), the unit of the world coordinate system is meter.

[0081] Step S2034, converting the world coordinate system coordinates into geographic coordinates according to the flight parameters of the UAV.

[0082] The flight parameters at least include the attitude angle, initial longitude and initial latitude of the UAV.

[0083] The initial longitude and initial latitude of the drone are the longitude and latitude of the location where the drone is located when taking the target image, and can be obtained through a positioning system carried by the drone.

[0084] Further, step S2034 includes the following steps:

[0085] (1) The latitude change is determined based on the ratio of the first coordinate of the world coordinate system to the radius of the earth, and the latitude is determined based on the sum of the latitude change and the initial latitude.

[0086] (2) Determine the longitude change based on the ratio of the second coordinate of the world coordinate system to the radius of the earth, and determine the longitude according to the sum of the longitude change and the initial longitude.

[0087] The coordinates of the world coordinate system are (X, Y, Z), the first coordinate of the world coordinate system is X, the second coordinate of the world coordinate system is Y, the radius of the earth refers to the average radius of the earth (about 6371000 meters), and the longitude and latitude are determined according to the following formulas:

[0088]

[0089] Among them, R E represents the radius of the earth, Y represents the second coordinate of the world coordinate system, and X represents the first coordinate of the world coordinate system. represents the change in latitude, represents the initial latitude, Δλ represents the change in longitude, λ0 represents the initial longitude, represents latitude and λ represents longitude.

[0090] The object recognition method provided by the present invention obtains a target image and the flight parameters of a drone, identifies a first object in the target image and the pixel coordinates of the first object, determines the geographical location of the first object based on the flight parameters and the pixel coordinates of the drone, and determines the target object in the target area based on the geographical location of the first object. The present invention determines all target objects in the target area by comparing the geographical location of the first object with the target area, reduces the possibility of misidentification, improves the accuracy of identification, and can perform real-time identification according to identification requirements. If a problem is found after identification, an early warning can be issued immediately.

[0091] In this embodiment, an object recognition device is also provided, which is used to implement the above-mentioned embodiments and implementation methods, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0092] This embodiment provides an object recognition device, such as Figure 2 As shown, including:

[0093] The parameter acquisition module 301 is used to acquire the target image and the flight parameters of the UAV;

[0094] a location determination module 302, configured to identify a first object in a target image and pixel coordinates of the first object, and determine a geographic location of the first object based on flight parameters of the drone and the pixel coordinates;

[0095] The target object determination module 303 is configured to determine a target object within a target area based on the geographic location of the first object.

[0096] In some optional implementations, the location determination module 302 includes:

[0097] A requirement identification unit, configured to obtain an identification requirement, wherein the identification requirement at least includes the first object and the target area;

[0098] A pixel coordinate determination unit is used to identify the first object in the target image based on the recognition requirement and determine the pixel coordinates of the first object.

[0099] In some optional implementations, the location determination module 302 includes:

[0100] A pixel coordinate conversion unit, used for converting the pixel coordinates into image coordinates based on the central pixel coordinates of the target image;

[0101] an image coordinate conversion unit, configured to determine the height of the drone relative to the ground based on the flight parameters of the drone, and to convert the image coordinates into a camera coordinate system based on camera parameters and the height to determine the camera coordinate system coordinates, wherein the camera is provided on the drone, and the camera parameters include at least the focal length of the camera;

[0102] A camera coordinate conversion unit, used to construct an attitude angle rotation matrix according to the flight parameters of the UAV, and convert the camera coordinate system coordinates into world coordinate system coordinates according to the rotation matrix;

[0103] A world coordinate system coordinate conversion unit is used to convert the world coordinate system coordinates into geographic coordinates according to the flight parameters of the UAV, wherein the flight parameters at least include the attitude angle, initial longitude and initial latitude of the UAV.

[0104] In some optional implementations, the pixel coordinate conversion unit includes:

[0105] A first coordinate difference determining subunit, configured to determine a first coordinate difference and a second coordinate difference based on the pixel coordinates and the center pixel coordinates;

[0106] The image coordinate determination subunit is used to determine the first coordinate in the image coordinate based on the first coordinate difference and the physical length in the first direction, and to determine the second coordinate in the image coordinate based on the second coordinate difference and the physical length in the second direction.

[0107] In some optional embodiments, the image coordinate conversion unit includes:

[0108] a product calculation subunit, used to respectively calculate a first product of the first coordinate in the image coordinates and the height, and a second product of the second coordinate in the image coordinates and the height;

[0109] The camera coordinate system coordinate determination subunit is used to determine the camera coordinate system coordinates based on the ratio of the first product to the camera focal length and the ratio of the second product to the camera focal length respectively.

[0110] In some optional implementations, the camera coordinate conversion unit includes:

[0111] A third product calculation subunit, used for calculating a third product of the camera coordinate system coordinates and the rotation matrix;

[0112] The world coordinate system coordinate determination subunit is used to determine the world coordinate system coordinate based on the sum of the third product and the first coordinate of the drone, and the first coordinate of the drone is used to characterize the coordinate of the drone in the world coordinate system.

[0113] In some optional implementations, the geographic coordinates include longitude and latitude, and the world coordinate system coordinate conversion unit includes:

[0114] a latitude determination subunit, configured to determine a latitude change based on a ratio of the second coordinate of the world coordinate system to the radius of the earth, and determine the latitude according to the sum of the latitude change and the initial latitude;

[0115] The longitude determination subunit is used to determine the longitude change based on the ratio of the first coordinate of the world coordinate system to the radius of the earth, and determine the longitude according to the sum of the longitude change and the initial longitude.

[0116] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0117] The object recognition device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0118] The embodiment of the present invention also provides a computer device having the above Figure 2 The device shown.

[0119] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0120] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0121] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0122] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0123] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0124] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0125] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0126] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the present invention.

Claims

1. A method for object recognition, characterized in that: The method comprises: Obtain target images and UAV flight parameters; Identifying a first object in a target image and pixel coordinates of the first object, and determining a geographic location of the first object based on flight parameters of the drone and the pixel coordinates; A target object within a target area is determined based on the geographic location of the first object.

2. The method according to claim 1, characterized in that The identifying a first object in a target image and pixel coordinates of the first object include: Acquire identification requirements, where the identification requirements at least include the first object and the target area; The first object in the target image is identified based on the identification requirement, and pixel coordinates of the first object are determined.

3. The method according to claim 2, characterized in that The determining the geographic location of the first object based on the flight parameters of the drone and the pixel coordinates includes: Converting the pixel coordinates into image coordinates based on the center pixel coordinates of the target image; Determine the height of the drone relative to the ground based on the flight parameters of the drone, and convert the image coordinates into a camera coordinate system based on camera parameters and the height to determine the camera coordinate system coordinates, wherein the camera is provided on the drone, and the camera parameters include at least the focal length of the camera; Constructing an attitude angle rotation matrix according to the flight parameters of the UAV, and converting the camera coordinate system coordinates into world coordinate system coordinates according to the rotation matrix; The world coordinate system coordinates are converted into geographic coordinates according to the flight parameters of the UAV, wherein the flight parameters at least include the attitude angle, initial longitude and initial latitude of the UAV.

4. The method according to claim 3, characterized in that The converting the pixel coordinates into image coordinates based on the central pixel coordinates of the target image comprises: determining a first coordinate difference and a second coordinate difference based on the pixel coordinates and the center pixel coordinates; A first coordinate in the image coordinates is determined based on the first coordinate difference and a physical length in a first direction, and a second coordinate in the image coordinates is determined based on the second coordinate difference and a physical length in a second direction.

5. The method according to claim 4, characterized in that The step of converting the image coordinates into a camera coordinate system based on the camera parameters and the height, and determining the coordinates of the camera coordinate system, comprises: respectively calculating a first product of a first coordinate in the image coordinates and the height, and a second product of a second coordinate in the image coordinates and the height; The camera coordinate system coordinates are determined based on a ratio of the first product to the camera focal length and a ratio of the second product to the camera focal length, respectively.

6. The method according to claim 3, characterized in that: The step of converting the camera coordinate system coordinates into world coordinate system coordinates according to the rotation matrix comprises: Calculating a third product of the camera coordinate system coordinates and the rotation matrix; The coordinates of the world coordinate system are determined based on the sum of the third product and the first coordinates of the drone, and the first coordinates of the drone are used to represent the coordinates of the drone in the world coordinate system.

7. The method according to any one of claims 3, characterized in that The geographic coordinates include longitude and latitude, and the converting the world coordinate system coordinates into geographic coordinates according to the flight parameters of the drone includes: Determine a latitude change based on a ratio of a second coordinate of the world coordinate system coordinate to a radius of the earth, and determine a latitude according to a sum of the latitude change and the initial latitude; The longitude change is determined based on the ratio of the first coordinate of the world coordinate system to the radius of the earth, and the longitude is determined according to the sum of the longitude change and the initial longitude.

8. An object recognition device, characterized in that: The device comprises: Parameter acquisition module, used to obtain target images and flight parameters of the UAV; a location determination module, configured to identify a first object in a target image and pixel coordinates of the first object, and determine a geographic location of the first object based on flight parameters of the drone and the pixel coordinates; The target object determination module is used to determine the target object in the target area based on the geographical location of the first object.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the object recognition method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the object recognition method according to any one of claims 1 to 7.

Images