Image detection method and apparatus, vehicle and computer-readable storage medium

Abstract

Disclosed in the present application are an image detection method and apparatus, a vehicle and a computer-readable storage medium. The method comprises: acquiring an image to be processed corresponding to a vehicle; on the basis of a long-distance image feature corresponding to the image to be processed, cropping the image to be processed so as to obtain a cropped image; acquiring a first detection result corresponding to the image to be processed, and a second detection result corresponding to the cropped image; and performing data fusion on the first detection result and the second detection result to obtain a target detection result. The present application directly performs distant object detection on the basis of cropped images, improving the accuracy of distant object detection, reducing the probability of missed detection of distant objects, and improving the distant object detection performance of vehicles, thus improving the driving safety of vehicles.

Description

Image detection method, device, vehicle, and computer-readable storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 22, 2023, with application number 2023117899273 and application name “Image detection method, device, vehicle and computer-readable storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of image detection technology, and in particular to an image detection method, device, vehicle, and computer-readable storage medium. Background Art

[0003] Autonomous driving technology has developed rapidly in recent years. It not only holds enormous economic potential but also offers significant advantages in improving traffic efficiency and driving safety. To improve nighttime driving safety, autonomous driving requires early identification of distant objects. This allows the vehicle to perform subsequent fusion predictions and path planning based on these distant objects.

[0004] In related technologies, vehicles perform object detection based on images captured by a single 8M camera. After cropping and downsampling the 8M images, the detection results obtained contain limited information about distant objects, especially objects beyond 120m to 180m. This can result in missed detections of distant objects or inaccurate detection information, which in turn affects vehicle driving safety. Summary of the Invention

[0005] In order to solve or partially solve the problems existing in the related art, the present application provides an image detection method, device, vehicle and computer-readable storage medium, which can improve the accuracy of long-distance object detection and reduce the probability of missed detection of long-distance objects, thereby improving the vehicle's long-distance object detection performance and thus improving the safety of vehicle driving.

[0006] To achieve the above objectives, the present application provides an image detection method, which includes the following steps:

[0007] Obtain the image to be processed corresponding to the vehicle;

[0008] performing a cropping operation on the image to be processed based on long-distance image features corresponding to the image to be processed to obtain a cropped image;

[0009] Obtaining a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image;

[0010] The first detection result and the second detection result are subjected to data fusion to obtain a target detection result.

[0011] In one embodiment, the step of obtaining the first detection result corresponding to the image to be processed and the second detection result corresponding to the cropped image includes:

[0012] Downsampling the image to be processed to obtain a sampling result;

[0013] Inputting the sampling result into a detection algorithm to obtain a first detection result;

[0014] The cropped image is input into the detection algorithm to obtain a second detection result.

[0015] In one embodiment, the step of performing data fusion on the first detection result and the second detection result to obtain a target detection result includes:

[0016] determining whether the second detection result matches the first detection result;

[0017] If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

[0018] In one embodiment, if the second detection result matches the first detection result, the step of updating the first detection result based on the second detection result to obtain the target detection result includes:

[0019] If the second detection result matches the first detection result, determining a long-distance detection result corresponding to the long-distance image feature in the first detection result;

[0020] The long-distance detection result is replaced by the second detection result in the first detection result to obtain the target detection result.

[0021] In one embodiment, after the step of determining whether the second test result matches the first test result, the method further includes:

[0022] If the second detection result does not match the first detection result, the second detection result is added to the first detection result to obtain the target detection result.

[0023] In one embodiment, the step of performing a cropping operation on the image to be processed based on the long-distance image features corresponding to the image to be processed to obtain the cropped image includes:

[0024] Performing feature extraction on the image to be processed to obtain image features corresponding to the image to be processed;

[0025] Acquiring long-range image features from the image features;

[0026] A cropping operation is performed on the image to be processed based on the long-distance image feature to obtain a cropped image.

[0027] In one embodiment, the step of obtaining the long-distance image features among the image features includes:

[0028] Obtaining the distance between each image feature and the vehicle;

[0029] A target distance greater than a preset distance is acquired, and an image feature corresponding to the target distance is used as the long-distance image feature.

[0030] In addition, to achieve the above-mentioned purpose, the present application further provides a vehicle, comprising:

[0031] An acquisition module, used to acquire the image to be processed corresponding to the vehicle;

[0032] a cropping module, configured to perform a cropping operation on the image to be processed based on long-distance image features corresponding to the image to be processed to obtain a cropped image;

[0033] a detection module, configured to obtain a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image;

[0034] The fusion module is used to perform data fusion on the first detection result and the second detection result to obtain a target detection result.

[0035] In one embodiment, the detection module downsamples the image to be processed to obtain a sampling result;

[0036] Inputting the sampling result into a detection algorithm to obtain a first detection result;

[0037] The cropped image is input into the detection algorithm to obtain a second detection result.

[0038] In one embodiment, the fusion module determines whether the second detection result matches the first detection result;

[0039] If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

[0040] In one embodiment, the cropping module performs feature extraction on the image to be processed to obtain image features corresponding to the image to be processed;

[0041] Acquiring long-range image features from the image features;

[0042] A cropping operation is performed on the image to be processed based on the long-distance image feature to obtain a cropped image.

[0043] In addition, to achieve the above-mentioned purpose, the present application also provides an image detection device, which includes: a memory, a processor, and an image detection program stored on the memory and runnable on the processor. When the image detection program is executed by the processor, the steps of the aforementioned image detection method are implemented.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which an image detection program is stored. When the image detection program is executed by a processor, the steps of the aforementioned image detection method are implemented.

[0045] The present application obtains an image to be processed corresponding to a vehicle; then crops the image to be processed based on the long-distance image features corresponding to the image to be processed to obtain a cropped image; then obtains a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image; then performs data fusion on the first detection result and the second detection result to obtain a target detection result. The present application improves the accuracy of long-distance object detection and reduces the probability of missed detection of long-distance objects by cropping the long-distance image features in the image to be processed and directly detecting long-distance objects based on the cropped image, thereby improving the long-distance object detection performance of the vehicle and thereby improving the safety of vehicle driving.

[0046] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0048] FIG1 is a schematic diagram of the structure of an image detection device in a hardware operating environment according to an embodiment of the present application;

[0049] FIG2 is a schematic diagram of a flow chart of a first embodiment of the image detection method of the present application;

[0050] FIG3 is a schematic diagram of functional modules of an embodiment of a vehicle of the present application. DETAILED DESCRIPTION

[0051] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although the accompanying drawings illustrate embodiments of the present application, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0052] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0053] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly defined in an embodiment.

[0054] As shown in FIG1 , FIG1 is a structural diagram of an image detection device in a hardware operating environment involved in an embodiment of the present application.

[0055] The terminal in the embodiment of the present application may be a vehicle, such as a vehicle with an automatic driving function.

[0056] As shown in Figure 1, the image detection device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Wherein, the communication bus 1002 is used to realize the connection communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or it may be a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0057] Optionally, the image detection device may further include a camera, RF (Radio Frequency) circuits, sensors, audio circuits, WiFi modules, and the like. Sensors include light sensors, motion sensors, and other sensors. Specifically, light sensors may include ambient light sensors and proximity sensors. Of course, the image detection device may also be configured with other sensors, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which are not described in detail here.

[0058] Those skilled in the art will understand that the terminal structure shown in FIG1 does not constitute a limitation on the image detection device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0059] As shown in FIG1 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an image detection program.

[0060] In the image detection device shown in Figure 1, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the image detection program stored in the memory 1005.

[0061] In this embodiment, the image detection device includes: a memory 1005, a processor 1001, and an image detection program stored on the memory 1005 and executable on the processor 1001, wherein when the processor 1001 calls the image detection program stored in the memory 1005, it executes the steps of the image detection method in each of the following embodiments.

[0062] The present application also provides an image detection method, referring to FIG2 , which is a flow chart of a first embodiment of the image detection method of the present application.

[0063] The image detection method includes:

[0064] Step S101: Acquire the image to be processed corresponding to the vehicle.

[0065] When performing image detection, an image to be processed corresponding to the vehicle is obtained, and the image to be processed is an image in front of the vehicle captured by a single 8M camera device of the vehicle.

[0066] It should be noted that, in other possible implementations, the image to be processed may be an image in front of the vehicle captured by a camera device with other parameters.

[0067] Step S102 : performing a cropping operation on the image to be processed based on the long-distance image features corresponding to the image to be processed to obtain a cropped image.

[0068] After acquiring the image to be processed, long-distance image features corresponding to the image to be processed are obtained. In one embodiment, feature extraction is first performed on the image to be processed to obtain image features corresponding to the image to be processed. Feature extraction can be performed on the image to be processed using a feature extraction algorithm or feature extraction model known in the relevant art. For example, the image to be processed is input into a feature extraction model for prediction. The output of the feature extraction model is the image features corresponding to the image to be processed. The image features are feature information corresponding to each object in the image to be processed. Long-distance image features are then determined from the image features based on the feature information.

[0069] After acquiring the long-range image features, a cropping operation is performed on the image to be processed based on the long-range image features to obtain a cropped image. In one embodiment, the cropping operation can be performed on the image to be processed based on position information in the feature information of the long-range image features to obtain a cropped image including the object corresponding to the long-range image features, wherein the cropped image may include one or more.

[0070] It should be noted that if the long-distance image features are not obtained, for example, there are no objects (pedestrians, vehicles or obstacles, etc.) on the road in front of the vehicle's driving direction, the first detection result corresponding to the image to be processed is obtained, and the first detection result is used as the target detection result.

[0071] Step S103: Obtain a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image.

[0072] After obtaining the cropped image, a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image are obtained. In one embodiment, the image to be processed is first downsampled to obtain a sampling result, and the sampling result is input into a detection algorithm or detection model for prediction to obtain the first detection result. Simultaneously, the cropped image is directly input into the detection algorithm or detection model for prediction to obtain the second detection result.

[0073] Step S104: performing data fusion on the first detection result and the second detection result to obtain a target detection result.

[0074] After obtaining the first and second detection results, data fusion is performed on the first and second detection results to obtain a target detection result. In one embodiment, if the second detection result matches the first detection result, the detection result corresponding to the long-range image feature in the first detection result is replaced with the second detection result to obtain the target detection result. If the second detection result does not match the first detection result, the second detection result is added to the first detection result to obtain the target detection result. That is, the target detection result includes the detection result corresponding to the long-range image feature in the first detection result, the detection result corresponding to the short-range image feature, and the second detection result.

[0075] By cropping the long-distance image features in the processed image and directly detecting long-distance objects based on the cropped image, the detection distance of objects in front of the vehicle during driving is increased from approximately 120 meters to 180 meters or more, thereby improving the accuracy of long-distance object detection and reducing the probability of missed detection of long-distance objects.

[0076] The present application obtains an image to be processed corresponding to a vehicle; then crops the image to be processed based on the long-distance image features corresponding to the image to be processed to obtain a cropped image; then obtains a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image; then performs data fusion on the first detection result and the second detection result to obtain a target detection result. The present application improves the accuracy of long-distance object detection and reduces the probability of missed detection of long-distance objects by cropping the long-distance image features in the image to be processed and directly detecting long-distance objects based on the cropped image, thereby improving the long-distance object detection performance of the vehicle and thereby improving the safety of vehicle driving.

[0077] Based on the first embodiment, a second embodiment of the image detection method of the present application is proposed, wherein step S103 includes:

[0078] Step S201 : down-sample the image to be processed to obtain a sampling result.

[0079] Step S202: input the sampling result into a detection algorithm to obtain a first detection result.

[0080] Step S203: input the cropped image into the detection algorithm to obtain a second detection result.

[0081] After obtaining the cropped image, the image to be processed is downsampled to obtain a sampling result, that is, the image to be processed is downsampled using an algorithm in the relevant technology. After obtaining the sampling result, the sampling result is input into the detection algorithm or detection model for prediction to obtain a first detection result.

[0082] At the same time, the cropped image is input into the detection algorithm to obtain a second detection result. In one embodiment, the cropped image is directly input into the detection algorithm or detection model for prediction to obtain the second detection result.

[0083] By downsampling the image to be processed to obtain a sampling result; then inputting the sampling result into a detection algorithm to obtain a first detection result; and then inputting the cropped image into the detection algorithm to obtain a second detection result, the detection results of the image to be processed and the cropped image can be accurately obtained, further improving the accuracy of long-distance object detection and reducing the probability of missed detection of long-distance objects, thereby improving the safety of vehicle driving.

[0084] Based on the first embodiment, a third embodiment of the image detection method of the present application is proposed, wherein step S104 includes:

[0085] Step S301: Determine whether the second detection result matches the first detection result.

[0086] Step S302: If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

[0087] After obtaining the first and second detection results, a determination is made as to whether the second detection result matches the first detection result. For example, the determination as to whether the second detection result matches the first detection result can be made based on the first area of ​​the detection contour corresponding to each long-range image feature in the second detection result and the second area of ​​the detection contour corresponding to each long-range image feature in the first detection result. If the absolute value of the difference between the first area and the second area corresponding to each long-range image feature is less than a preset threshold, or the ratio between the absolute value of the difference and the second area is less than a preset ratio, then the second detection result can be determined to match the first detection result.

[0088] If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

[0089] Furthermore, in one possible implementation, step S302 includes:

[0090] Step S3021: If the second detection result matches the first detection result, determine the long-distance detection result corresponding to the long-distance image feature in the first detection result.

[0091] Step S3022: Replace the long-distance detection result with the second detection result in the first detection result to obtain the target detection result.

[0092] If the second detection result matches the first detection result, the long-distance detection result corresponding to the long-distance image feature in the first detection result is obtained, and the long-distance detection result is replaced with the second detection result in the first detection result to obtain the target detection result. In one embodiment, for each long-distance image feature, the long-distance detection result of the long-distance image feature in the first detection result is replaced with the detection result of the long-distance image feature in the second detection result, so that the long-distance image feature in the target detection result is a more accurate detection result, thereby improving the accuracy of long-distance object detection and reducing the probability of missed detection of long-distance objects, improving the long-distance object detection performance of the vehicle, and thereby improving the safety of vehicle driving.

[0093] Furthermore, in a possible implementation, after step S301, the image detection method further includes:

[0094] Step S303: If the second detection result does not match the first detection result, the second detection result is added to the first detection result to obtain the target detection result.

[0095] If the second detection result does not match the first detection result, the second detection result is added to the first detection result to obtain the target detection result, that is, the target detection result includes the detection result corresponding to the long-distance image feature in the first detection result, the detection result corresponding to the close-range image feature and the second detection result.

[0096] By determining whether the second detection result matches the first detection result; then if the second detection result matches the first detection result, updating the first detection result based on the second detection result to obtain the target detection result, the detection accuracy of long-distance objects in the target detection result is improved, the accuracy of long-distance object detection is further improved and the probability of missed detection of long-distance objects can be reduced, thereby improving the vehicle's long-distance object detection performance and thereby improving the safety of vehicle driving.

[0097] Based on the above embodiments, a fourth embodiment of the image detection method of the present application is proposed, wherein step S102 includes:

[0098] Step S401 : performing feature extraction on the image to be processed to obtain image features corresponding to the image to be processed.

[0099] Step S402: Acquire long-distance image features from the image features.

[0100] Step S403 : performing a cropping operation on the image to be processed based on the long-distance image feature to obtain a cropped image.

[0101] After obtaining the image to be processed, feature extraction is performed on the image to be processed to obtain image features corresponding to the image to be processed. In one embodiment, a feature extraction algorithm or feature extraction model in related technology can be used to extract features of the image to be processed. For example, the image to be processed is input into the feature extraction model for prediction, and the output of the feature extraction model is the image feature corresponding to the image to be processed, and the image feature is the feature information corresponding to each object in the image to be processed.

[0102] After obtaining the image features corresponding to the image to be processed, the long-distance image features in the image features are obtained; wherein the long-distance image features can be screened according to the position information corresponding to each image feature and the position information of the vehicle.

[0103] Furthermore, in one possible implementation, step S402 includes:

[0104] Step S4021: Obtain the distance between each image feature and the vehicle.

[0105] Step S4022: Acquire a target distance that is greater than a preset distance, and use an image feature corresponding to the target distance as the long-distance image feature.

[0106] After obtaining the image features corresponding to the image to be processed, the position information of the object corresponding to the image features can be obtained through the image features, and the position information of the vehicle at the time of shooting of the image to be processed can be obtained. According to the position information of the object corresponding to the image features and the position information of the vehicle at the time of shooting, the distance between the object corresponding to each image feature and the vehicle is calculated respectively.

[0107] After obtaining the distance between the object corresponding to each image feature and the vehicle, determine whether each distance is greater than the preset distance, that is, determine whether each distance is greater than the preset distance separately to determine whether there is a target distance greater than the preset distance in each distance, and obtain the target distance greater than the preset distance in each distance. The preset distance can be reasonably set, for example, the preset distance is 120 meters, 100 meters, etc.

[0108] If there is a target distance greater than the preset distance in each distance, the image feature corresponding to the target distance is obtained, and the image feature corresponding to the target distance is used as the long-distance image feature to accurately obtain the long-distance image feature corresponding to the long-distance object in the image to be processed.

[0109] After acquiring the long-distance image features, a cropping operation is performed on the image to be processed according to the long-distance image features to obtain a cropped image. In one embodiment, a cropping operation can be performed on the image to be processed according to the position information in the feature information of the long-distance image features to obtain a cropped image including the object corresponding to the long-distance image features, wherein the cropped image may include one or more.

[0110] By performing feature extraction on the image to be processed, image features corresponding to the image to be processed are obtained; then, long-distance image features in the image features are obtained; and then, based on the long-distance image features, a cropped image is obtained for the image to be processed. The image to be processed can be accurately cropped according to the long-distance image features to obtain a cropped image including long-distance objects, so as to facilitate detection of long-distance objects based on the cropped image, further improving the accuracy of long-distance object detection and reducing the probability of missed detection of long-distance objects, thereby improving the long-distance object detection performance of the vehicle and thereby improving the safety of vehicle driving.

[0111] In addition, the present application also proposes a vehicle, referring to FIG3 , which includes:

[0112] An acquisition module 10 is used to acquire an image to be processed corresponding to the vehicle;

[0113] A cropping module 20 is configured to perform a cropping operation on the image to be processed based on long-range image features corresponding to the image to be processed to obtain a cropped image;

[0114] A detection module 30 is configured to obtain a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image;

[0115] The fusion module 40 is configured to perform data fusion on the first detection result and the second detection result to obtain a target detection result.

[0116] In one embodiment, the detection module 30 downsamples the image to be processed to obtain a sampling result;

[0117] Inputting the sampling result into a detection algorithm to obtain a first detection result;

[0118] The cropped image is input into the detection algorithm to obtain a second detection result.

[0119] In one embodiment, the fusion module 40 determines whether the second detection result matches the first detection result;

[0120] If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

[0121] In one embodiment, the cropping module 20 performs feature extraction on the image to be processed to obtain image features corresponding to the image to be processed;

[0122] Acquiring long-range image features from the image features;

[0123] A cropping operation is performed on the image to be processed based on the long-distance image feature to obtain a cropped image.

[0124] The methods executed by the above-mentioned program units can refer to the various embodiments of the image detection method of this application and will not be repeated here.

[0125] In addition, the present application also proposes a computer-readable storage medium, on which an image detection program is stored. When the image detection program is executed by a processor, the steps of the image detection method described above are implemented.

[0126] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0127] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0129] The embodiments of the present application have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to the technology in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

Claims

1. An image detection method, characterized in that: The image detection method comprises: Obtain the image to be processed corresponding to the vehicle; Performing a cropping operation on the image to be processed based on the long-distance image feature corresponding to the image to be processed to obtain a cropped image; Obtaining a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image; The first detection result and the second detection result are subjected to data fusion to obtain a target detection result.

2. The image detection method according to claim 1, characterized in that: The step of obtaining the first detection result corresponding to the image to be processed and the second detection result corresponding to the cropped image includes: Down-sampling the image to be processed to obtain a sampling result; Inputting the sampling result into a detection algorithm to obtain a first detection result; The cropped image is input into the detection algorithm to obtain a second detection result.

3. The image detection method according to claim 1, characterized in that: The step of fusing the first detection result and the second detection result to obtain the target detection result comprises: determining whether the second detection result matches the first detection result; If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

4. The image detection method according to claim 3, characterized in that: If the second detection result matches the first detection result, the step of updating the first detection result based on the second detection result to obtain the target detection result includes: If the second detection result matches the first detection result, determining the long-distance detection result corresponding to the long-distance image feature in the first detection result; The long-distance detection result is replaced by the second detection result in the first detection result to obtain the target detection result.

5. The image detection method according to claim 3, characterized in that: After the step of determining whether the second detection result matches the first detection result, the method further includes: If the second detection result does not match the first detection result, the second detection result is added to the first detection result to obtain the target detection result.

6. The image detection method according to any one of claims 1 to 5, characterized in that: The step of performing a cropping operation on the image to be processed based on the long-distance image feature corresponding to the image to be processed to obtain the cropped image comprises: Extracting features of the image to be processed to obtain image features corresponding to the image to be processed; Acquire long-distance image features from the image features; A cropping operation is performed on the image to be processed based on the long-distance image feature to obtain a cropped image.

7. The image detection method according to claim 6, characterized in that: The step of acquiring the long-distance image features in the image features comprises: Obtaining the distance between each image feature and the vehicle; A target distance whose distance is greater than a preset distance is acquired, and an image feature corresponding to the target distance is used as the long-distance image feature.

8. A vehicle, characterized in that: The vehicle comprises: An acquisition module, used for acquiring an image to be processed corresponding to the vehicle; A cropping module, used for performing a cropping operation on the image to be processed based on the long-distance image features corresponding to the image to be processed to obtain a cropped image; A detection module, used to obtain a first detection result corresponding to the image to be processed and a second detection result corresponding to the cropped image; The fusion module is used to perform data fusion on the first detection result and the second detection result to obtain a target detection result.

9. The vehicle according to claim 8, characterized in that: The detection module downsamples the image to be processed to obtain a sampling result; Inputting the sampling result into a detection algorithm to obtain a first detection result; The cropped image is input into the detection algorithm to obtain a second detection result.

10. The vehicle according to claim 8, characterized in that: The fusion module determines whether the second detection result matches the first detection result; If the second detection result matches the first detection result, the first detection result is updated based on the second detection result to obtain the target detection result.

11. The vehicle according to claim 8, characterized in that: The cropping module extracts features from the image to be processed to obtain image features corresponding to the image to be processed; Acquire long-distance image features from the image features; A cropping operation is performed on the image to be processed based on the long-distance image feature to obtain a cropped image.

12. An image detection device, characterized in that: The image detection device comprises: a memory, a processor, and an image detection program stored in the memory and executable on the processor. When the image detection program is executed by the processor, the steps of the image detection method according to any one of claims 1 to 7 are implemented.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an image detection program, and when the image detection program is executed by a processor, the steps of the image detection method according to any one of claims 1 to 7 are implemented.

Images