Three-dimensional target detection method, electronic device, and storage medium

Abstract

The application provides a three-dimensional object detection method, an electronic device and a storage medium. The method comprises: acquiring a detection image and a depth image corresponding to the detection image; inputting the detection image into a trained object detection model to determine an object category of an object in the detection image and a two-dimensional edge frame of the object; determining an object model and a three-dimensional edge frame from a three-dimensional object model library according to the object category; calculating point cloud data and a distance from a depth camera to the object model according to the depth image and the two-dimensional edge frame; determining a rotation angle of the object model according to the object model and the point cloud data; and determining a position of the object model in a three-dimensional space according to the distance from the depth camera to the object model, the rotation angle and the three-dimensional edge frame. The application can quickly determine the position of the object in the three-dimensional space.

Description

TECHNICAL FIELD

[0001] The present application relates to computer vision and deep learning technology, in particular to a three-dimensional object detection method, an electronic device and a storage medium. BACKGROUND

[0002] In the field of automatic driving, an automatic driving system detects objects in front of or near a vehicle using different types of sensors to make corresponding decisions. Therefore, the automatic driving system needs to quickly and accurately detect the category and position of the object to ensure driving safety. Most current three-dimensional object detection algorithms need a large number of labeled samples to detect the category of the object, and it is difficult to label the rotation angle of the object and requires the use of regression operation, which takes a long time to predict. In addition, most current three-dimensional object detection algorithms also need to accurately detect the distance between the vehicle and the object in front, and most current methods use light detection and ranging (LiDAR) or radar to obtain depth information, but the cost of using LiDAR or radar is high and the field of view is relatively small. SUMMARY

[0003] In view of the above, it is necessary to provide a three-dimensional object detection method, an electronic device and a storage medium, which can solve the problem of difficult rotation angle labeling and the problem of high detection cost.

[0004] The embodiment of the present application provides a three-dimensional object detection method, which comprises: acquiring a detection image and a depth image corresponding to the detection image, wherein the depth image is acquired by a depth camera; inputting the detection image into a trained object detection model, determining an object category of an object in the detection image and a two-dimensional edge frame of the object by using the object detection model; determining an object model corresponding to the object and a three-dimensional edge frame corresponding to the object model from a three-dimensional object model library according to the object category; calculating point cloud data of the object framed by the two-dimensional edge frame and a distance from the depth camera to the object model according to the depth image and the two-dimensional edge frame; determining a rotation angle of the object model according to the object model and the point cloud data; and determining a position of the object model in a three-dimensional space according to the distance from the depth camera to the object model, the rotation angle and the three-dimensional edge frame.

[0005] In an optional implementation, the calculation of the point cloud data of the object framed by the two-dimensional edge frame and the distance from the depth camera to the object model according to the depth image and the two-dimensional edge frame comprises: acquiring a depth value and coordinates of the object framed by the two-dimensional edge frame according to the depth image, determining the distance from the depth camera to the object model according to the depth value; and obtaining the point cloud data according to the coordinates and an internal and external parameter matrix transformation formula of the depth camera.

[0006] In an optional implementation, the determining the rotation angle of the object model according to the object model and the point cloud data comprises: obtaining first point cloud data of the object contour according to the point cloud data; converting the object model into second point cloud data; performing point cloud matching on the first point cloud data and the second point cloud data to obtain the rotation angle of the object model.

[0007] In an optional implementation, the method further comprises: obtaining a training image; constructing a target detection model based on a You Only Look Once (YOLO) network; inputting the training image into the target detection model for training, performing convolution and mean pooling alternately on the training image by the target detection model to obtain feature value data of the training image; processing the feature value data by a full connection layer of the target detection model to obtain a two-dimensional edge line frame of an object in the training image and an object category, and adjusting parameters of the target detection model to minimize a loss function to obtain the trained target detection model.

[0008] In an optional implementation, the processing the feature value data by the full connection layer of the target detection model to obtain the two-dimensional edge line frame of the object in the training image and the object category comprises: processing the feature value data by the full connection layer of the target detection model to obtain a plurality of candidate two-dimensional edge line frames of the object in the training image, and performing non-maximum suppression operation on the plurality of candidate two-dimensional edge line frames to obtain the two-dimensional edge line frame of the object in the training image and the object category.

[0009] In an optional implementation, the method further comprises: establishing the three-dimensional object model library, wherein the three-dimensional object model library comprises a plurality of object models corresponding to different object categories and a three-dimensional edge line frame corresponding to each object model, and the three-dimensional edge line frame comprises length, width and height corresponding to each object category.

[0010] In an optional implementation, the determining the position of the object model in the three-dimensional space according to the distance from the depth camera to the object model, the rotation angle and the three-dimensional edge line frame comprises: determining a direction of the object model in the three-dimensional space according to the rotation angle; and determining the position of the object model in the three-dimensional space according to the direction of the object model in the three-dimensional space, the distance from the depth camera to the object model and the three-dimensional edge line frame of the object model.

[0011] In an optional implementation, the method further comprises: outputting the object category and the position of the object in the three-dimensional space by taking the position of the object model in the three-dimensional space as the position of the object in the three-dimensional space.

[0012] The electronic device provided by the embodiments of the present application comprises a processor and a memory, and the processor is used to execute the computer program stored in the memory to realize the three-dimensional target detection method.

[0013] The computer readable storage medium provided by the embodiments of the present application stores at least one instruction, and the at least one instruction is executed by the processor to realize the three-dimensional target detection method.

[0014] By using the technical solutions provided by the embodiments of the present application, complex operations are not required, and the rotation angle of the object does not need to be labeled, thereby reducing the labor cost and quickly obtaining the three-dimensional position of the object. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 The flow chart of the three-dimensional target detection method provided by the embodiments of the present application is shown.

[0016] Figure 2 The flow chart of the non-maximum suppression method provided by the embodiments of the present application is shown.

[0017] Figure 3 The schematic diagram of determining the three-dimensional edge line frame provided by the embodiments of the present application is shown.

[0018] Figure 4 The structural schematic diagram of the electronic device provided by the embodiments of the present application is shown. DETAILED DESCRIPTION

[0019] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in combination with the drawings and specific embodiments. It should be noted that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0020] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application. The described embodiments are only a part of the embodiments of the present application, and are not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the present application.

[0021] The terms "first", "second", etc. are used only for the purpose of description and do not connote or imply relative importance or refer to the number of the features. Thus, features with "first", "second" can include one or more of the features explicitly or implicitly. In the description of some embodiments of the present application, the words "exemplary" and "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described as "exemplary" or "for example" in some embodiments of the present application is not necessarily to be construed as preferred or advantageous over other embodiments or designs.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0023] Referring to Figure 1 as shown, Figure 1 A flow chart of a three-dimensional target detection method provided by some embodiments of the present application. The method is applied in an electronic device (for example, the electronic device 4 as shown) and the electronic device can be any electronic product that can interact with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive Internet Protocol Television (IPTV), a smart wearable device, etc. Figure 4

[0024] The electronic device is a device that can automatically perform numerical calculation and / or information processing according to pre-set or stored instructions. The hardware of the electronic device includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, etc.

[0025] The network in which the electronic device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a Virtual Private Network (VPN), etc.

[0026] The method specifically includes the following steps. ​

[0027] 101, acquire a detection image and a depth image corresponding to the detection image.

[0028] In at least one embodiment of the present application, a camera mounted inside or outside the vehicle is used to take a picture, and the image of the front of the vehicle taken by the camera is used as the detection image.

[0029] In at least one embodiment of the present application, acquiring a depth image corresponding to the detection image includes using a depth camera to acquire a depth image, and using a depth camera mounted on the vehicle to take an image of the front of the vehicle as a depth image. It should be noted that when the image of the front of the vehicle is taken by the camera mounted inside or outside the vehicle as the detection image, the depth camera simultaneously takes the image of the front of the vehicle as the depth image, and the depth image corresponds to the detection image. For example, different types of cameras are used to take pictures of the same object in front of the vehicle to obtain the detection image and the depth image.

[0030] In an embodiment of the present application, the application scenario of the three-dimensional target detection method includes the field of vehicle automatic driving. In the process of vehicle driving, the three-dimensional target detection method is applied to realize three-dimensional detection of objects in front of the vehicle.

[0031] 102, input the detection image into the trained target detection model, and use the target detection model to determine the object class of the object in the detection image and the two-dimensional edge frame of the object.

[0032] In at least one embodiment of the present application, the trained target detection model includes a target detection model based on a You Only Look Once (YOLO) network, and the YOLO network includes a YOLOv3 network or a YOLOv5 network.

[0033] In at least one embodiment of the present application, the method for training the target detection model to obtain the trained target detection model includes:

[0034] acquire a training image;

[0035] input the training image into the target detection model for training, and obtain feature value data of the training image by alternately processing the target detection model through convolution and mean pooling;

[0036] The full connection layer of the target detection model is used to process the feature value data, to obtain a two-dimensional edge line frame of an object in the training image and an object category, and by adjusting parameters of the target detection model to minimize a loss function, the trained target detection model is obtained. In this embodiment, the parameters of the target detection model include, but are not limited to, a learning rate of the target detection model and an iteration number. In this embodiment, the loss function of the target detection model includes a mean square error loss function.

[0037] In at least one embodiment of the present application, the obtaining of the training image further includes performing a data enhancement operation on the training image to obtain more different training samples, and the data enhancement operation includes, but is not limited to, flipping an image, rotating an image, scaling an image, and cropping an image. Through the data enhancement operation, sample data can be effectively expanded, and the target detection model can be trained and optimized using more training images (for example, vehicle front image) in different scenes, so that the target detection model is more robust.

[0038] In at least one embodiment of the present application, the processing of the feature value data by the full connection layer of the target detection model to obtain a two-dimensional edge line frame of an object in the training image and an object category includes:

[0039] The full connection layer of the target detection model is used to process the feature value data, to obtain a two-dimensional edge line frame of an object in the training image and an object category, and by adjusting parameters of the target detection model to minimize a loss function, the trained target detection model is obtained. In this embodiment, the parameters of the target detection model include, but are not limited to, a learning rate of the target detection model and an iteration number. In this embodiment, the loss function of the target detection model includes a mean square error loss function.

[0040] In this embodiment, the performing of the non-maximum suppression operation (Non-Maximum Suppression, NMS) refers to Figure 2 The flowchart specifically includes:

[0041] 21. The multiple candidate two-dimensional edge line frames are sorted according to the scores of the candidate two-dimensional edge line frames, and the candidate two-dimensional edge line frame with the highest score is selected. The “candidate two-dimensional edge line frame” is a candidate two-dimensional edge line frame of an object in the training image.

[0042] 22. traversing other candidate two-dimensional edge frames, calculating Intersection Over Union (IOU) between the selected candidate two-dimensional edge frame and other candidate two-dimensional edge frames, and deleting the candidate two-dimensional edge frame corresponding to the IOU greater than a preset threshold. In this embodiment, the IOU is the degree of overlap between the selected candidate two-dimensional edge frame (i.e., the highest score) and other candidate two-dimensional edge frames.

[0043] 23. determining whether there are other candidate two-dimensional edge frames in addition to the selected candidate two-dimensional edge frame. If there are other candidate two-dimensional edge frames, the flow returns to 21. If there are no other candidate two-dimensional edge frames, 24 is executed to output the selected candidate two-dimensional edge frame as the two-dimensional edge frame of the object in the training image.

[0044] In at least one embodiment of the present application, the training of the target detection model can be completed by the above method, and the trained target detection model is obtained. Further, the detection image is input into the trained target detection model, and the object category and the two-dimensional edge frame in the detection image are output.

[0045] 103. determining, according to the object category, an object model corresponding to the object and a three-dimensional edge frame corresponding to the object model from a three-dimensional object model library.

[0046] In at least one embodiment of the present application, the three-dimensional target detection method further comprises: pre-establishing a three-dimensional object model library, wherein the three-dimensional object model library comprises a plurality of object models corresponding to different object categories and a three-dimensional edge frame corresponding to each object model, and each three-dimensional edge frame comprises length, width, and height corresponding to the object category.

[0047] In this embodiment, the object model is determined according to the object category and the three-dimensional edge frame of the object model is determined according to the object model. For example, as shown in FIG. 6, the object model corresponding to the object category "car" is determined according to the object category "car", and the three-dimensional edge frame of the object model is determined according to the object model. Figure 3 Figure 3 ​The determination of the three-dimensional edge frame schematic diagram is provided in the embodiment. When the object category is a small car, the object model of the small car is searched based on the three-dimensional object model library, and the three-dimensional edge frame of the small car is searched according to the object model of the small car. When the object category is a small truck, the object model of the small truck is searched based on the three-dimensional object model library, and the three-dimensional edge frame of the small truck is searched according to the object model of the small truck. When the object category is an electric vehicle, the object model of the electric vehicle is searched based on the three-dimensional object model library, and the three-dimensional edge frame of the electric vehicle is searched according to the object model of the electric vehicle. When the object category is a bus, the object model of the bus is searched based on the three-dimensional object model library, and the three-dimensional edge frame of the bus is searched according to the object model of the bus. In the embodiment, the object model includes, but is not limited to, a three-dimensional model.

[0048] 104, according to the depth image and the two-dimensional edge frame, the point cloud data of the object framed by the two-dimensional edge frame and the distance from the depth camera to the object model are calculated.

[0049] In at least one embodiment of the present application, the method for determining the distance from the depth camera to the object model includes:

[0050] According to the depth image, the depth value of the object framed by the two-dimensional edge frame is obtained.

[0051] According to the depth value, the distance from the depth camera to the object model of the object is determined. In the embodiment, the depth value is obtained by the depth camera, and the depth value is displayed by the depth camera when the depth image is captured by the depth camera. The depth value is the distance from the depth camera to the object, which is taken as the distance from the depth camera to the object model of the object in the embodiment.

[0052] In at least one embodiment of the present application, the method for obtaining the point cloud data includes:

[0053] According to the depth image, the coordinate set of the object framed by the two-dimensional edge frame is obtained.

[0054] According to the coordinate set and the internal and external parameter matrix transformation formula of the depth camera, the point cloud data is obtained. In the embodiment, the coordinate set of the object framed by the two-dimensional edge frame is the pixel coordinate set of the object, and the point cloud data is the world coordinate corresponding to the coordinate in the coordinate set of the object framed by the two-dimensional edge frame. The point cloud data is the data for representing the contour of the object. The coordinate in the coordinate set of the object framed by the two-dimensional edge frame is converted into the corresponding world coordinate through the internal and external parameter matrix transformation formula, and the internal and external parameter matrix transformation formula is:

[0055]

[0056] wherein (x, y, z) is the world coordinate, f is the focal length, D is the depth value, and (x1, y1) is the pixel coordinate of any pixel in the coordinate set of the object framed by the two-dimensional edge box. All coordinates in the coordinate set are converted into world coordinates one by one using the above formula to obtain the point cloud data.

[0057] 105, determining the rotation angle of the object model of the object according to the object model of the object and the point cloud data.

[0058] According to the point cloud data, the first point cloud data of the object contour is obtained.

[0059] The object model of the object is converted into second point cloud data.

[0060] The first point cloud data and the second point cloud data are matched to obtain the rotation angle of the object model of the object.

[0061] In at least one embodiment of the present application, converting the object model of the object into second point cloud data includes reading the object model of the object and generating point cloud data of the object model of the object as second point cloud data using a plurality of functions in a point cloud library (PCL).

[0062] In at least one embodiment of the present application, matching the first point cloud data and the second point cloud data to obtain the rotation angle of the object model of the object includes:

[0063] Fitting the points of the object contour in the first point cloud data into a first plane and calculating the curvature of the first plane, fitting the points of the second point cloud data into a second plane and calculating the curvature of the second plane, calculating the difference between the curvatures of the first plane and the second plane to obtain a curvature deviation value, and determining the rotation angle of the object model of the object according to the curvature deviation value.

[0064] 106, determining the position of the object in the three-dimensional space.

[0065] In at least one embodiment of the present application, the direction of the object model in the three-dimensional space is determined according to the rotation angle, and the position of the object model in the three-dimensional space is determined according to the direction of the object model in the three-dimensional space, the distance from the depth camera to the object model, and the three-dimensional bounding box of the object model. Specifically, the object category and the position of the object in the three-dimensional space are output as the position of the object in the three-dimensional space. For example, the object category and the position of the object in the three-dimensional space are displayed in the form of a three-dimensional bounding box on a display screen.

[0066] The above merely describes specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Those skilled in the art can make improvements without departing from the inventive concept of the present application, and these improvements are within the protection scope of the present application.

[0067] As shown in Figure 4 As shown in Figure 4 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown. The electronic device 4 includes a memory 401, at least one processor 402, a computer program 403 stored in the memory 401 and executable on the at least one processor 402, and at least one communication bus 404.

[0068] Those skilled in the art can understand that Figure 4 The schematic diagram shown is merely an example of the electronic device 4 and does not constitute a limitation on the electronic device 4, and can include more or fewer components than shown, or combine certain components, or different components, for example, the electronic device 4 can also include an input / output device, a network access device, etc.

[0069] The at least one processor 402 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The at least one processor 402 can be a microprocessor or the at least one processor 402 can also be any conventional processor or the like, and the at least one processor 402 is a control center of the electronic device 4, which connects various parts of the entire electronic device 4 through various interfaces and lines.

[0070] The memory 401 can be used to store the computer program 403, and the at least one processor 402 realizes various functions of the electronic device 4 by running or executing the computer program 403 stored in the memory 401 and calling data stored in the memory 401. The memory 401 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data (such as audio data) created according to the use of the electronic device 4, etc. In addition, the memory 401 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash storage device, or other non-volatile solid-state storage device.

[0071] The modules / units integrated in the electronic device 4, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be implemented by a computer program instructing related hardware to complete, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, and read-only memory (ROM).

[0072] It is obvious for those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be regarded as limiting the claims to which they relate.

[0073] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A three-dimensional object detection method, characterized by, The three-dimensional object detection method comprises: acquiring a detection image and a depth image corresponding to the detection image, wherein the depth image is acquired by a depth camera; inputting the detection image into a trained object detection model, and determining an object category of an object in the detection image and a two-dimensional edge frame of the object by using the object detection model; determining, according to the object category, an object model corresponding to the object from a three-dimensional object model library and a three-dimensional edge frame corresponding to the object model; calculating, according to the depth image and the two-dimensional edge frame, point cloud data of the object framed by the two-dimensional edge frame and a distance from the depth camera to the object model; determining a rotation angle of the object model according to the object model and the point cloud data, comprising: obtaining first point cloud data of an object contour according to the point cloud data; converting the object model into second point cloud data; performing point cloud matching on the first point cloud data and the second point cloud data to obtain the rotation angle of the object model, comprising: fitting points of the object contour in the first point cloud data into a first plane and calculating a curvature of the first plane, fitting points of the second point cloud data into a second plane and calculating a curvature of the second plane; calculating a difference between the curvature of the first plane and the curvature of the second plane to obtain a curvature deviation value, and determining the rotation angle of the object model according to the curvature deviation value; determining a position of the object model in a three-dimensional space according to the distance from the depth camera to the object model, the rotation angle and the three-dimensional edge frame.

2. The three-dimensional object detection method of claim 1, wherein, The calculating, according to the depth image and the two-dimensional edge frame, of the point cloud data of the object framed by the two-dimensional edge frame and the distance from the depth camera to the object model comprises: acquiring a depth value and coordinates of the object framed by the two-dimensional edge frame according to the depth image, and determining the distance from the depth camera to the object model according to the depth value; obtaining the point cloud data according to the coordinates and an internal and external parameter matrix transformation formula of the depth camera.

3. The three-dimensional object detection method of claim 1, wherein, The method further comprises: acquiring a training image; constructing an object detection model based on a You Only Look Once (YOLO) network; inputting the training image into the object detection model for training, and obtaining feature value data of the training image by performing convolution and mean pooling alternately on the object detection model; processing the feature value data by using a full connection layer of the object detection model to obtain a two-dimensional edge frame of an object in the training image and an object category, and adjusting parameters of the object detection model to minimize a loss function, thereby obtaining the trained object detection model.

4. The three-dimensional object detection method of claim 3, wherein, The processing of the feature value data by using the full connection layer of the object detection model to obtain the two-dimensional edge frame of the object in the training image and the object category comprises: The full connection layer of the target detection model is used to process the feature value data, to obtain a plurality of candidate two-dimensional edge line frames of the object in the training image, and non-maximum suppression operation is performed on the plurality of candidate two-dimensional edge line frames to obtain a two-dimensional edge line frame and an object category of the object in the training image.

5. The three-dimensional object detection method of claim 1, wherein, The method further comprises: establishing the three-dimensional object model library, wherein the three-dimensional object model library comprises a plurality of object models corresponding to different object categories and a three-dimensional edge line frame corresponding to each object model, and the three-dimensional edge line frame comprises length, width and height corresponding to each object category.

6. The three-dimensional object detection method of claim 1, wherein, The determining of the position of the object model in the three-dimensional space according to the distance from the depth camera to the object model, the rotation angle and the three-dimensional edge line frame comprises: determining a direction of the object model in the three-dimensional space according to the rotation angle; determining the position of the object model in the three-dimensional space according to the direction of the object model in the three-dimensional space, the distance from the depth camera to the object model and the three-dimensional edge line frame of the object model.

7. The three-dimensional object detection method of claim 6, wherein, The method further comprises: outputting the object category and the position of the object in the three-dimensional space by taking the position of the object model in the three-dimensional space as the position of the object in the three-dimensional space.

8. An electronic device, comprising: The electronic device comprises a processor and a memory, and the processor is configured to execute a computer program stored in the memory to implement the three-dimensional target detection method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one instruction, and the at least one instruction is executed by the processor to implement the three-dimensional target detection method according to any one of claims 1 to 7.

Images