TWI855331B - Method for detecting three-dimensional object, electronic device and storage medium - Google Patents

Abstract

The present application provides a method for detect three-dimensional (3D) objects, an electronic device and a storage medium. The method includes: acquiring a detection image; inputting the detection image into a trained target detection model, and determining an object in the detection image and a category of the object, a two-dimensional bounding box of the object and a rotation angle of the object by using the trained target detection model; according to the category of the object, searching a 3D object model library for an object model corresponding to the object and a 3D bounding box corresponding to the object model; determining a distance from a camera to the object model according to a size of the 2D bounding box of the object, image information of the detected image and focal length of the camera. A position of the object model in the 3D space is determined according to the rotation angle of the object, the distance from the camera to the object model, and the 3D bounding box, and the position of the object model in the 3D space is determined to be a position of the object in the 3D space. This application can quickly determine a position of an object in the 3D space.

Description

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

This application relates to computer vision and deep learning technology, and in particular to a three-dimensional target detection method, electronic equipment, and computer-readable storage medium.

In the field of autonomous driving, different sensors can detect objects in front of or near the vehicle, so that the autonomous driving system can make corresponding decisions. Therefore, the autonomous driving system needs to quickly and accurately detect the type and position of the object to ensure driving safety. Currently, most three-dimensional target detection algorithms need to use regression operations to obtain the three-dimensional position of the object. However, the use of regression operations causes the three-dimensional target detection algorithm to spend a long time on prediction processing. In addition, when detecting the distance between the vehicle and the object in front, the current three-dimensional target detection algorithm uses 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.

In view of the above, it is necessary to provide a three-dimensional target detection method, electronic equipment and computer-readable storage medium to solve the problem of slow speed in detecting the type and three-dimensional position of objects and reduce the detection cost.

The present application embodiment provides a three-dimensional target detection method, which includes: obtaining a detection image taken by a camera; inputting the detection image into a trained target detection model, and using the target detection model to determine the object category of the object in the detection image, the two-dimensional boundary frame of the object, and the rotation angle of the object; according to the object category, searching a three-dimensional object model library to determine the object model corresponding to the object and the object model corresponding to the object; The three-dimensional boundary frame corresponding to the object model is obtained; the distance from the camera to the object model is determined according to the size of the two-dimensional boundary frame of the object, the image information of the detection image and the focal length of the camera; the position of the object model in three-dimensional space is determined according to the rotation angle of the object, the distance from the camera to the object model and the three-dimensional boundary frame, and the value of the object model in three-dimensional space is used as the position of the object in three-dimensional space.

In an optional implementation, the method further includes: constructing the target detection model, improving the target detection model based on the Single Shot MultiBox Detector (SSD) network, wherein the SSD network includes a backbone network and a first head network; the improvement based on the SSD network includes: adding a second head network after the backbone network in the SSD network; after the improvement, the target detection model includes the backbone network, the first head network and the second head network.

In an optional implementation, the method further includes: obtaining a training sample image; using the backbone network in the target detection model to extract features from the training sample image to obtain a plurality of training feature maps of different scales of the training sample image; generating a plurality of first default frames on the plurality of training feature maps of different scales and inputting each of the training feature maps of different scales into the first head network for convolution, and outputting the scores of the object categories of the objects in the plurality of first default frames and the positions of the plurality of first default frames. ; Perform non-maximum suppression operation on the multiple first default frames, and output the two-dimensional boundary frame of the object in the training sample image, wherein the two-dimensional boundary frame of the object in the training sample image includes the object category in the two-dimensional boundary frame and the position of the two-dimensional boundary frame; input each training feature map of different scales into the second head network for convolution, and output the rotation angle of the object in the training sample image; minimize the loss value of the first head network and the second head network, and obtain the trained target detection model.

In an optional implementation, the method further includes: performing data enhancement processing on the training sample image to increase the training sample image, wherein the data enhancement processing includes flipping, rotating, scaling, and shifting the training sample image.

In an optional implementation, searching a three-dimensional object model library to determine an object model corresponding to the object and a three-dimensional boundary frame corresponding to the object model according to the object category includes: establishing a three-dimensional object model library, wherein the three-dimensional object model library includes multiple object models corresponding to different object categories and a three-dimensional boundary frame corresponding to each object model, and the three-dimensional boundary frame includes the length, width, and height corresponding to the object category.

In an optional implementation, determining the distance from the camera to the object model according to the size of the two-dimensional bounding box of the object, the image information of the detection image, and the focal length of the camera includes: calculating the distance from the camera to the object model according to the width and/or length of the two-dimensional bounding box of the object, the focal length of the camera, the resolution of the detection image, and the pixel width.

In an optional implementation, determining the position of the object model in the three-dimensional space according to the rotation angle of the object, the distance from the camera to the object model, and the three-dimensional boundary frame includes: using the rotation angle of the object as the rotation angle of the object model; determining the direction of the object model in the three-dimensional space according to the rotation angle of the object model; 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 camera to the object model, and the three-dimensional boundary frame.

In an optional implementation, the method further includes: outputting the object category and the position of the object in three-dimensional space and displaying the object category and the position of the object in three-dimensional space on a display screen.

This application embodiment also provides an electronic device, which includes a processor and a memory, and the processor is used to implement the three-dimensional target detection method when executing a computer program stored in the memory.

This application embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the three-dimensional target detection method is implemented.

By utilizing the technical solutions provided by each embodiment of this application, there is no need to perform complex calculations, which reduces labor costs and can quickly obtain the three-dimensional position of an object.

5: Electronic equipment

501: Memory

502:Processor

503:Computer program

504: Communication bus

X: Pixel width of the detected image

G: represents the optical center of the camera

Y: The width of the two-dimensional border frame

f: Focal length of the camera

d: distance from camera to object model

101-106: Steps

21-24: Steps

Figure 1 is a flow chart of a three-dimensional target detection method provided in an embodiment of this application.

Figure 2 is a flow chart of the non-maximum value suppression method provided in the embodiment of this application.

Figure 3 is a schematic diagram of the three-dimensional object model library provided in this application embodiment.

FIG4 is a schematic diagram of a method for calculating the distance from a camera to an object model of an object provided in an embodiment of the present application.

Figure 5 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

In order to more clearly understand the above-mentioned purpose, features and advantages of this application, the following is a detailed description of this application in conjunction with the attached drawings and specific embodiments. It should be noted that the specific embodiments described here are only used to explain this application and are not intended to limit this application.

In the following description, many specific details are explained to facilitate a full understanding of this application. The embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative labor are within the scope of protection of this application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application. The terms used in this specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

In the field of autonomous driving, different sensors can detect objects in front of or near the vehicle, and the autonomous driving system can make corresponding decisions. Therefore, the autonomous driving system needs to quickly and accurately detect the type and position of the object to ensure driving safety. Currently, most three-dimensional target detection algorithms use regression operations to obtain the three-dimensional position of the object after detecting the type and position information of the object. However, the use of regression operations causes the three-dimensional target detection algorithm to spend a long time on prediction processing. In addition, when detecting the distance between the vehicle and the object in front, the current three-dimensional target detection algorithm uses 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.

Based on the above problems, the embodiment of the present application provides a three-dimensional target detection method, which can quickly obtain the category and three-dimensional position of the object without using regression operation, and when obtaining the distance between the detection vehicle and the object in front, it is not necessary to use lidar or radar to obtain depth information, thereby reducing costs. The three-dimensional target detection method will be described in detail below.

Refer to FIG. 1, which is a flow chart of a three-dimensional target detection method provided in an embodiment of the present application. The method is applied to an electronic device (e.g., the electronic device 5 shown in FIG. 5), 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 network television (IPTV), a smart wearable device, etc.

The electronic device is a device that can automatically perform numerical calculations and/or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to: microprocessors, application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

The electronic device may also include network equipment and/or user equipment. The network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

The network where the electronic device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

The method specifically includes the following steps.

Step 101, obtain training sample images and detection images taken by the camera.

In at least one embodiment of the present application, the training sample images include, but are not limited to: various scene images on urban roads and rural roads at different time periods. The detection images taken by the camera include, but are not limited to scene images on urban roads and rural roads taken by a monocular camera at different time periods. It should be noted that although the training sample images and the images taken by the monocular camera are both scene images of cities and rural areas at different time periods, the training sample images are not the same as the images taken by the camera.

In at least one embodiment of the present application, the step of obtaining the training sample images further includes: performing a data enhancement operation on the training sample images to obtain more different training sample images, and the data enhancement operation includes, but is not limited to, flipping the image, rotating the image, scaling the image, and cropping the image. The data enhancement operation can effectively expand the sample data, use more training sample images in different scenes to train and optimize the target detection model, and make the target detection model more robust.

Step 102, construct a target detection model, and use the training sample images to train the target detection model to obtain a trained target detection model.

In at least one embodiment of the present application, the constructing of the target detection model includes: improving the target detection model based on a Single Shot MultiBox Detector (SSD) network, wherein the SSD network includes a backbone network and a first head network. In this embodiment, the improving of the target detection model based on the SSD network includes: adding a second head network after the backbone network in the SSD network. After the improvement, the target detection model includes the backbone network, the first head network, and the second head network.

In at least one embodiment of the present application, the target detection model is trained using the training sample image to obtain the trained target detection model, including: using the backbone network in the target detection model to extract features from the training sample image to obtain a plurality of training feature maps of different scales of the training sample image; generating a plurality of first default frames on the plurality of training feature maps of different scales and inputting each of the training feature maps of different scales into the first head network for convolution, outputting the scores of the object categories of the objects in the plurality of default frames and the The positions of multiple first default frames; the multiple first default frames are subjected to non-maximum suppression operation to output the two-dimensional boundary frame of the object in the training sample image, wherein the two-dimensional boundary frame of the object in the training sample image includes the object category in the two-dimensional boundary frame and the position of the two-dimensional boundary frame; each training feature map of different scales is input into the second head network for convolution, and the rotation angle of the object in the training sample image is output; the loss values of the first head network and the second head network are minimized to obtain a trained target detection model.

In at least one embodiment of the present application, the first head network includes multiple convolutional layers.

In at least one embodiment of the present application, the second head network includes a plurality of convolutional layers and a fully connected layer. After each training feature map of different scales is input into the convolutional layer of the second head network for convolution, the fully connected layer outputs the rotation angle of the object in the training sample image.

In at least one embodiment of the present application, the loss function of the SSD network is used as the loss function of the first head network. The loss function of the SSD network is a prior art and will not be further described in this application.

其中，LOSS為第二head網路的損失函數，Y _i 表示第二head網路的物體的旋轉角度輸出值，f(x _i )表示物體的旋轉角度的實際值。 In at least one embodiment of the present application, the loss function of the second head network is:

Wherein, LOSS is the loss function of the second head network, Yi represents the rotation angle output value of the object of the second head network, _and f ( xi ₎ represents the actual value of the rotation angle of the object.

In at least one embodiment of the present application, the target detection model is trained using the loss functions of the first head network and the second head network, and the target detection model is trained by iterative training until the target detection model converges and the loss value is minimized to obtain a trained target detection model.

In at least one embodiment of the present application, the method of performing non-maximum suppression operation on the multiple first default frames to output the two-dimensional boundary frame of the object in the training sample image includes: As can be seen from the above, the scores of the object categories of the objects in the multiple first default frames and the positions of the multiple default frames. The method of performing non-maximum suppression operation (NMS) refers to the flowchart shown in Figure 2, which specifically includes:

Step 21, sort multiple first default boxes according to their scores, and select the first default box with the highest score.

Step 22, traverse other first default frames, calculate the intersection over union (IOU) between other first default frames and the selected first default frame, and delete the first default frames corresponding to the IOU greater than the preset threshold. In this embodiment, the IOU is the degree of overlap between the selected first default frame (i.e., the frame with the highest score) and other first default frames.

Step 23, determine whether there are other first default frames besides the selected first default frame. If there are other first default frames, the process returns to step 21. If there are no other first default frames, execute step 24, output the selected first default frame as the two-dimensional boundary frame of the object in the training image.

Step 103, input the detection image into the trained target detection model, and use the target detection model to determine the object category, the two-dimensional boundary frame and the rotation angle of the object in the detection image.

In at least one embodiment of the present application, the detection image is input into a trained target detection model, and features of the detection image are extracted through a backbone network to obtain feature maps of multiple scales. Multiple second default frames are generated on the feature maps of multiple scales, and each feature map of different scales is input into the first head network for convolution, and the scores of the object categories of the objects in the multiple second default frames and the positions of the multiple second default frames are output. The multiple second default frames are subjected to non-maximum suppression operations to output the two-dimensional boundary frame of the object in the detection image, wherein the two-dimensional boundary frame of the object in the detection image includes the object category in the two-dimensional boundary frame and the position of the two-dimensional boundary frame. Each feature map of different scales is input into the second head network for convolution, and the rotation angle of the object in the detection image is output. At this point, the detection image is input into the trained target detection model, and the object category, the two-dimensional boundary frame of the object and the rotation angle of the object in the detection image are output.

Step 104, according to the object category, search the three-dimensional object model library to determine the object model corresponding to the object and the three-dimensional boundary frame corresponding to the object model.

In at least one embodiment of the present application, the method further includes: establishing a three-dimensional object model library, wherein the three-dimensional object model library includes multiple object models corresponding to different object categories and a three-dimensional border frame corresponding to each object model, wherein the three-dimensional border frame includes the length, width, and height corresponding to the object category.

In this embodiment, the object model is determined based on the object category and the three-dimensional object model library, and the three-dimensional boundary frame of the object model is determined based on the object model. For example, as shown in FIG3 , it is a schematic diagram of determining the three-dimensional boundary frame provided in the embodiment of this application. When the object category is a car, the object model of the car is searched based on the three-dimensional object model library, and the three-dimensional boundary frame of the car is searched based on the object model of the 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 boundary frame of the small truck is searched based on the object model of the small truck; when the object category is an electric car, the object model of the electric car is searched based on the three-dimensional object model library, and the three-dimensional boundary frame of the electric car is searched based on the object model of the electric car; 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 boundary frame of the bus is searched based on the object model of the bus. In this embodiment, the object model includes, but is not limited to, a three-dimensional model.

Step 105, determining the distance from the camera to the object model according to the size of the two-dimensional boundary frame of the object, the image information of the detection image and the focal length of the camera.

In at least one embodiment of the present application, the size of the two-dimensional border frame of the object includes the width and/or length of the two-dimensional border frame of the object, and the image information of the detection image includes the resolution of the detection image and the pixel width of the detection image.

為：

公式

為：

其中Y表示二維邊線框的寬度，X表示檢測圖像的像素寬度，P表示檢測圖像的分辨率。 In at least one embodiment of the present application, the distance from the camera to the object model is calculated based on the width and/or length of the two-dimensional border frame of the object, the focal length of the camera, the resolution of the detection image, and the pixel width of the detection image. For example, refer to FIG. 4, which is a schematic diagram of a method for calculating the distance from the camera to the object model of the object provided in an embodiment of the present application. Where X represents the pixel width of the detection image, f represents the focal length of the camera, G represents the optical center of the camera, d represents the distance from the camera to the object model, and Y represents the width of the two-dimensional border frame. According to the triangle similarity principle, the formula

for:

formula

for:

Where Y represents the width of the two-dimensional bounding box, X represents the pixel width of the detection image, and P represents the resolution of the detection image.

可求得所述相機到所述物件模型的距離。 According to the above formula

The distance from the camera to the object model can be obtained.

Step 106, determine the position of the object model in three-dimensional space according to the rotation angle of the object, the distance from the camera to the object model and the three-dimensional boundary frame, and use the position of the object model in three-dimensional space as the position of the object in three-dimensional space.

In at least one embodiment of the present application, the rotation angle of the object is used as the rotation angle of the object model.

In at least one embodiment of the present application, determining the position of the object model in three-dimensional space according to the rotation angle of the object, the distance from the camera to the object model, and the three-dimensional boundary frame includes: Determining the direction of the object model in the three-dimensional space according to the rotation angle of the object model, 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 camera to the object model, and the three-dimensional boundary frame.

In at least one embodiment of the present application, the position of the object model in the three-dimensional space is used as the position of the object in the three-dimensional space, the object category and the position of the object in the three-dimensional space are output, and the object category and the position of the object in the three-dimensional space are displayed on a display screen.

The above is only the specific implementation method of this application, but the protection scope of this application is not limited to this. For ordinary technical personnel in this field, improvements can be made without departing from the creative concept of this application, but these are all within the protection scope of this application.

As shown in FIG5 , FIG5 is a schematic diagram of an electronic device structure provided in an embodiment of the present application. The electronic device 5 includes a memory 501, at least one processor 502, a computer program 503 stored in the memory 501 and executable on the at least one processor 502, and at least one communication bus 504.

Those skilled in the art can understand that the schematic diagram shown in FIG5 is only an example of the electronic device 5 and does not constitute a limitation on the electronic device 5. The electronic device 5 may include more or fewer components than shown in the diagram, or may combine certain components, or may include different components. For example, the electronic device 5 may also include input and output devices, network access devices, etc.

The at least one processor 502 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The at least one processor 502 may be a microprocessor or any conventional processor, etc. The at least one processor 502 is the control center of the electronic device 5, and uses various interfaces and lines to connect the various parts of the entire electronic device 5.

The memory 501 can be used to store the computer program 503. The at least one processor 502 realizes various functions of the electronic device 5 by running or executing the computer program 503 stored in the memory 501 and calling the data stored in the memory 501. The memory 501 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device 5 (such as audio data), etc. In addition, the memory 501 may include non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk memory device, a flash memory device, or other non-volatile solid-state memory devices.

If the module/unit integrated in the electronic device 5 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, a flash drive, a removable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments and can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of this application and are not limiting. Although this application is described in detail with reference to the preferred embodiments, ordinary technicians in this field should understand that the technical solution of this application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of this application.

101-106: Steps

Claims (8)

A three-dimensional target detection method is applied to electronic equipment, wherein the three-dimensional target detection method includes: obtaining a training sample image and a detection image taken by a camera; constructing a target detection model, and improving the target detection model based on an SSD network, wherein the SSD network includes a backbone network and a first head network; the improving the target detection model based on the SSD network includes: adding a second head network after the backbone network in the SSD network; the improved target detection model includes the backbone network, the first head network and the second head network; using the training sample image to train the improved target detection model to obtain a trained target detection model; inputting the detection image into the trained target detection model, and using the target detection model to determine the location of the object in the detection image The method comprises: inputting the detection image into a trained target detection model, extracting the features of the detection image through the backbone network to obtain feature maps of multiple different scales; inputting each feature map of different scales into the second head network for convolution, and outputting the rotation angle of the object in the detection image; searching the three-dimensional object model library to determine the object according to the object category; The object model corresponding to the object and the three-dimensional border frame corresponding to the object model; determining the distance from the camera to the object model according to the size of the two-dimensional border frame of the object, the image information of the detection image and the focal length of the camera, including: calculating the distance from the camera to the object model according to the width and/or length of the two-dimensional border frame of the object, the focal length of the camera, the resolution and pixel width of the detection image, wherein the formula is used

The distance from the camera to the object model can be obtained: Formula

for:

;formula

for:

; wherein X represents the pixel width of the detection image, f represents the focal length of the camera, d represents the distance from the camera to the object model, Y represents the width of the two-dimensional boundary frame, and P represents the resolution of the detection image; the position of the object model in the three-dimensional space is determined according to the rotation angle of the object, the distance from the camera to the object model and the three-dimensional boundary frame, and the position of the object model in the three-dimensional space is used as the position of the object in the three-dimensional space. A three-dimensional target detection method as described in claim 1, wherein the method further comprises: using the backbone network in the target detection model to extract features from the training sample image to obtain a plurality of training feature maps of different scales of the training sample image; generating a plurality of first default frames on the plurality of training feature maps of different scales and inputting each of the training feature maps of different scales into the first head network for convolution, and outputting the scores of the object categories of the objects in the plurality of first default frames and the positions of the plurality of first default frames. ; Perform non-maximum suppression operation on the multiple first default frames, and output the two-dimensional boundary frame of the object in the training sample image, wherein the two-dimensional boundary frame of the object in the training sample image includes the object category in the two-dimensional boundary frame and the position of the two-dimensional boundary frame; input each training feature map of different scales into the second head network for convolution, and output the rotation angle of the object in the training sample image; minimize the loss value of the first head network and the second head network, and obtain the trained target detection model. The three-dimensional target detection method as described in claim 2, wherein the method further comprises: Performing data enhancement processing on the training sample image to increase the training sample image, wherein the data enhancement processing comprises flipping, rotating, scaling, and shifting the training sample image. The three-dimensional target detection method as described in claim 1, wherein the step of searching the three-dimensional object model library to determine the object model corresponding to the object and the three-dimensional boundary frame corresponding to the object model according to the object category includes: establishing a three-dimensional object model library, wherein the three-dimensional object model library includes multiple object models corresponding to different object categories and a three-dimensional boundary frame corresponding to each object model, and the three-dimensional boundary frame includes the length, width, and height corresponding to the object category. A three-dimensional target detection method as described in any one of claims 1 to 3, wherein the determining the position of the object model in the three-dimensional space according to the rotation angle of the object, the distance from the camera to the object model, and the three-dimensional boundary frame comprises: using the rotation angle of the object as the rotation angle of the object model; determining the direction of the object model in the three-dimensional space according to the rotation angle of the object model; 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 camera to the object model, and the three-dimensional boundary frame. The three-dimensional target detection method as described in claim 5, wherein the method further comprises: outputting the object category and the position of the object in the three-dimensional space and displaying the object category and the position of the object in the three-dimensional space on a display screen. An electronic device, wherein the electronic device includes a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement a three-dimensional target detection method as described in any one of claims 1 to 6. A computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, a three-dimensional target detection method as described in any one of claim items 1 to 6 is implemented.

Images