Multi-camera human body action recognition method and device
A human action recognition, multi-camera technology, applied in the field of action recognition, can solve the problems of low accuracy of human action recognition and easy occlusion of the human body.
Active Publication Date: 2021-01-29
SHANGHAI YITU NETWORK SCI & TECH
View PDF11 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In the prior art, when the human body movement in the video captured by the camera is recognized, the recognition is based on a monocular camera. Therefore, since the monocular camera can only capture a video from one angle, the human body in the video is very It is easily affected by occlusion, resulting in low accuracy of human motion recognition
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 Construction
[0088] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0089] At present, action recognition is one of the most challenging research directions in the field of computer vision, and it is widely used in the field of security.
[0090] In the prior art, when the human body movement in the video captured by the camera is recognized, the recognition is based on the monocular camera. Therefore, since the monocular camera can only capture video from one angle, when the human body is blocked, then It will lead...
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 relates to the technical field of action recognition, in particular to a multi-camera human body action recognition method and device, the method comprises the steps: performing human body detection on video images in each image set contained in a to-be-recognized video to obtain each human body region image; for each time point, associating the human body area images corresponding to the same human body; determining two-dimensional coordinates of the human body key points; converting the two-dimensional coordinates into three-dimensional coordinates through a preset conversion mode; converting the three-dimensional coordinates into three-dimensional coordinates under a world coordinate system, calculating a coordinate average value of the three-dimensional coordinates, respectively taking the determined coordinate average value as the three-dimensional key point coordinates of the human body key points in each time point; obtaining the human body action category of the human body according to the determined three-dimensional key point coordinates. The method recognizes the human body contained in the to-be-recognized video from multiple angles by recognizing the video under multiple cameras. Therefore, the recognition accuracy can be improved.
Description
technical field [0001] The present application relates to the technical field of motion recognition, and in particular to a multi-camera human body motion recognition method and device. Background technique [0002] At present, action recognition is one of the most challenging research directions in the field of computer vision, and it is widely used in the field of security. [0003] In the prior art, when the human body movement in the video captured by the camera is recognized, the recognition is based on a monocular camera. Therefore, since the monocular camera can only capture a video from one angle, the human body in the video is very It is easily affected by occlusion, resulting in low accuracy of human motion recognition. Contents of the invention [0004] Embodiments of the present application provide a multi-camera human action recognition method and device, so as to improve the accuracy of human action recognition. [0005] The specific technical scheme that t...
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 IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V40/23G06V20/46G06N3/045G06F18/214
Inventor 魏子昆聂学成王琦
Owner SHANGHAI YITU NETWORK SCI & TECH