CN-116863448-B - Behavior detection method, behavior detection device, vehicle, electronic device and storage medium

Abstract

The disclosure provides a behavior detection method, a behavior detection device, a vehicle, an electronic device and a storage medium, wherein the behavior detection method comprises the following steps: and acquiring an image to be detected, identifying target object information and image area information in the image to be detected, and determining human behavior information according to the target object information and the image area information. According to the method and the device, the behavior detection is carried out on the image to be detected by combining the target object information and the image area information in the image to be detected, so that the accuracy and the detection and identification efficiency of behavior detection and identification can be effectively improved, and the robustness and the applicability of the behavior detection method can be effectively improved.

Inventors

• WEI TAO

Assignees

• 北京罗克维尔斯科技有限公司

Dates

Publication Date

20260508

Application Date

20220321

Claims (17)

1. 1. A behavior detection method, comprising: Acquiring an image to be detected; Identifying target object information and image area information in the image to be detected, and Determining human behavior information according to the target object information and the image area information; The method further comprises the steps of: inputting the target object information and the image area information into a behavior information classification model; determining that a set condition is met between a relationship to be matched between the target object information and the image area information and a candidate association relationship based on the behavior information classification model; the relationship to be matched is an association relationship between the target object information and the image area information; the determining the human behavior information according to the target object information and the image area information includes: When a set condition is met between the candidate association relation between the candidate object information and the candidate region information corresponding to the candidate behavior information and the target association relation, the candidate behavior information is used as the human body behavior information; Wherein the target association relationship is an association relationship between the target object information and the image area information.
2. 2. The method of claim 1, wherein the identifying target object information and image region information in the image to be detected comprises: identifying a target object area and a part image area in the image to be detected; Determining the target object information according to the target object area; and determining the image area information according to the part image area.
3. 3. The method of claim 2, wherein said determining said target object information from said target object region comprises: acquiring region category information of the target object region; and taking the region category information as the target object information.
4. 4. The method of claim 2, wherein said determining said image area information from said region image area comprises: determining a part category according to the part image area; and taking the part category as the image area information.
5. 5. The method of claim 2, wherein the identifying the target object region in the image to be detected comprises: Inputting the image to be detected into a pre-trained object area detection model, and detecting the object area of the image to be detected by the object area detection model to obtain the target object area.
6. 6. The method of claim 2, wherein the identifying a region of the site image in the image to be detected comprises: Inputting the image to be detected into a pre-trained key point detection model, and performing key point detection on the image to be detected by using the key point detection model to obtain a plurality of key point information; and cutting the image to be detected based on the plurality of key point information to obtain the part image area.
7. 7. The method of claim 1, wherein the acquiring the image to be detected comprises: acquiring an initial image, wherein the initial image is captured by a camera device of a vehicle, and the initial image corresponds to driving area annotation information; inputting the initial image into a face detection model, and carrying out face detection on the initial image by the face detection model to obtain a face detection result; And if the face detection result indicates that the face exists in the initial image, determining the image to be detected from the initial image according to the driving area labeling information.
8. 8. A behavior detection apparatus, the apparatus comprising: the acquisition module is used for acquiring the image to be detected; an identification module for identifying the target object information and the image area information in the image to be detected, and The determining module is used for determining human behavior information according to the target object information and the image area information; The determining module is further used for inputting the target object information and the image area information into a behavior information classification model; determining that a set condition is met between a relationship to be matched between the target object information and the image area information and a candidate association relationship based on the behavior information classification model; the relationship to be matched is an association relationship between the target object information and the image area information; The determining module is further configured to: When a set condition is met between the candidate association relation between the candidate object information and the candidate region information corresponding to the candidate behavior information and the target association relation, the candidate behavior information is used as the human body behavior information; Wherein the target association relationship is an association relationship between the target object information and the image area information.
9. 9. The apparatus of claim 8, wherein the identification module comprises: The identification sub-module is used for identifying a target object area and a part image area in the image to be detected; The first determining submodule is used for determining the target object information according to the target object area; and the second determining submodule is used for determining the image area information according to the part image area.
10. 10. The apparatus of claim 9, wherein the first determination submodule is further to: acquiring region category information of the target object region; and taking the region category information as the target object information.
11. 11. The apparatus of claim 9, wherein the second determination submodule is further to: determining a part category according to the part image area; and taking the part category as the image area information.
12. 12. The apparatus of claim 9, wherein the identification sub-module is further configured to: Inputting the image to be detected into a pre-trained object area detection model, and detecting the object area of the image to be detected by the object area detection model to obtain the target object area.
13. 13. The apparatus of claim 9, wherein the identification sub-module is further configured to: Inputting the image to be detected into a pre-trained key point detection model, and performing key point detection on the image to be detected by using the key point detection model to obtain a plurality of key point information; and cutting the image to be detected based on the plurality of key point information to obtain the part image area.
14. 14. The apparatus of claim 8, wherein the acquisition module is further to: acquiring an initial image, wherein the initial image is captured by a camera device of a vehicle, and the initial image corresponds to driving area annotation information; inputting the initial image into a face detection model, and carrying out face detection on the initial image by the face detection model to obtain a face detection result; And if the face detection result indicates that the face exists in the initial image, determining the image to be detected from the initial image according to the driving area labeling information.
15. 15. A vehicle, characterized by comprising: behavior detection apparatus according to any of the preceding claims 8-14.
16. 16. An electronic device, comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the behavior detection method of any one of claims 1-7.
17. 17. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are for causing the computer to perform the behavior detection method of any one of claims 1-7.

Description

Behavior detection method, behavior detection device, vehicle, electronic device and storage medium Technical Field The disclosure relates to the technical field of artificial intelligence, and in particular relates to a behavior detection method, a behavior detection device, a vehicle, electronic equipment and a storage medium. Background In a vehicle driving scenario, normalizing the driving behavior of a driver is an important aspect of solving the potential safety hazard of the vehicle, and thus, it is highly desirable to propose a behavior detection method for detecting the non-normalized behavior (such as smoking behavior, drinking behavior, and calling behavior) of the driver in the vehicle driving scenario, so as to normalize the behavior of the driver accordingly. In the related art, when the behavior detection is performed, the accuracy of the behavior detection is poor, and the behavior detection effect is poor. Disclosure of Invention The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art. Therefore, an object of the present disclosure is to provide a behavior detection method, apparatus, vehicle, electronic device, and storage medium, which are capable of effectively improving accuracy and efficiency of behavior detection and identification due to behavior detection of an image to be detected by combining target object information and image area information in the image to be detected, so as to effectively improve robustness and applicability of the behavior detection method. The behavior detection method provided by the embodiment of the first aspect of the disclosure comprises the steps of obtaining an image to be detected, identifying target object information and image area information in the image to be detected, and determining human body behavior information according to the target object information and the image area information. According to the behavior detection method provided by the embodiment of the first aspect of the disclosure, the human body behavior information is determined by acquiring the image to be detected, identifying the target object information and the image area information in the image to be detected and according to the target object information and the image area information. Therefore, the behavior detection is carried out on the image to be detected by combining the target object information and the image area information in the image to be detected, so that the accuracy and the detection and identification efficiency of behavior detection and identification can be effectively improved, and the robustness and the applicability of the behavior detection method can be effectively improved. The behavior detection device provided by the embodiment of the second aspect of the disclosure comprises an acquisition module, a recognition module and a determination module, wherein the acquisition module is used for acquiring an image to be detected, the recognition module is used for recognizing target object information and image area information in the image to be detected, and the determination module is used for determining human body behavior information according to the target object information and the image area information. According to the behavior detection device provided by the embodiment of the second aspect of the disclosure, the human body behavior information is determined by acquiring the image to be detected, identifying the target object information and the image area information in the image to be detected and according to the target object information and the image area information. Therefore, the behavior detection is carried out on the image to be detected by combining the target object information and the image area information in the image to be detected, so that the accuracy and the detection and identification efficiency of behavior detection and identification can be effectively improved, and the robustness and the applicability of the behavior detection method can be effectively improved. According to a third aspect of the present disclosure, there is provided a vehicle including the behavior detection apparatus set forth in the embodiment of the second aspect of the present disclosure. According to a fourth aspect of the present disclosure there is provided an electronic device comprising at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the behavior detection method of the first aspect embodiment of the present disclosure. According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a behavior detection method of an embodiment of the first aspect of the present disclosure is presented. According to a sixth aspe