Abnormal behavior recognition method and device, electronic equipment and storage medium
A recognition method and behavior technology, which is applied in the field of video processing, image recognition, and machine learning, and can solve the problem of low accuracy of abnormal behavior recognition.
Active Publication Date: 2021-05-28
UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST
View PDF16 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the embodiments of the present application is to provide a method, device, electronic device, and storage medium for identifying abnormal behaviors, which are used to improve the problem of low accuracy in identifying abnormal behaviors
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach
[0039] There are many implementations for extracting key points of the human body from the video stream in the above step S110, including but not limited to the following: In the first implementation, each video frame is directly extracted from the video stream, and the video The frame is used as a video image, and the key point detection neural network is used to extract the key points of the human body from the complete video image of the video frame; among them, the key point detection neural network that can be used includes: OpenPose network and cascaded pyramid network (CascadedPyramid Network, CPN) wait. The second implementation mode first uses the target detection network to detect video images including human body regions from each video frame of the video stream, wherein the target detection network that can be used includes: networks such as RCNN, fastRCNN and faster RCNN; and then Use the key point detection neural network to extract the key points of the human bo...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an abnormal behavior recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a video stream collected for a human body, and extracting human body key points from the video stream; carrying out dimension reduction processing on the key points of the human body to obtain feature values after dimension reduction; and using the trained single-class support vector machine to classify the feature values after dimension reduction to obtain a classification result. In the implementation process, the human body key points are extracted from the video stream, the feature values obtained after dimension reduction processing of the human body key points are classified through the single-class support vector machine, the feature values are classified through the single-class support vector machine through the hyper-sphere, and the spherical boundary of feature space data can be found more easily. Therefore, the influence caused by imbalance of positive and negative samples is reduced, and the accuracy of abnormal behavior recognition is effectively improved.
Description
technical field [0001] The present application relates to the technical fields of machine learning, video processing and image recognition, and specifically relates to an abnormal behavior recognition method, device, electronic equipment and storage medium. Background technique [0002] Abnormal behavior recognition refers to the identification of behaviors and activities of people who exceed the normal range in high-level semantic understanding from the monitored video stream, for example: the behavior of the elderly lying down, eating, sleeping, watching TV, etc. in the room , these behaviors are within the normal range; if the old man falls in the room, the behavior of the old man is considered to be an abnormal behavior beyond the normal range, and an early warning message needs to be issued for timely treatment; if the old man is lying down, sleeping or Rest, then the behavior of the elderly is considered to be a normal behavior that does not exceed the normal range, an...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V40/20G06V10/44G06F18/2135G06F18/2411Y02D10/00
Inventor 李赞张伟熙董帅邹昆李文生李悦乔
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST