Portrait gait identification cross comparison method and system
A cross-comparison and portrait technology, applied to instruments, character and pattern recognition, computer components, etc., can solve the problems of lack of quantitative analysis technology and achieve the effect of a robust and accurate calculation method
Pending Publication Date: 2022-03-01
曾锦飞
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Aiming at the demand for new technologies and methods for portrait gait quantitative inspection in the fields of gait recognition and judicial appraisal, the present invention provides a cross-comparison method and system for portrait gait appraisal to solve the lack of quantitative analysis technology and methods in portrait gait inspection. Quantitatively analyze the problems supported by data to improve the accuracy and application value of gait characteristic inspection
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
[0018] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings.
[0019] This embodiment provides a cross-comparison method for portrait gait identification. The whole workflow is as figure 1 shown, including the following steps:
[0020] Step a, select several videos JV[i](i=1,...,M) containing the gait of the portrait to be checked and several videos YV[j](j=1,...,M) containing the gait of the portrait for comparison ., N), wherein, M is the number of video objects in the video JV, and N is the number of video objects in the video YV. Here, the concept of a video object covers video objects such as video files, image sequences, video segments, or image sequence tag information. The video JV[i](i=1,...,M) of the gait of the person to be checked can be derived from the gait videos of the person to be checked t...
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 discloses a portrait gait identification cross comparison method and system, and the method mainly comprises the steps: calculating a to-be-detected portrait gait feature vector data set JT [i] (i = 1,..., M) in a selected to-be-detected portrait gait video, calculating a to-be-compared portrait gait feature vector data set YT [j] (j = 1,..., N) in a selected to-be-compared portrait gait video, and calculating a to-be-compared portrait gait feature vector data set YT [j] (j = 1,..., N) in the selected to-be-compared portrait gait video. According to the method, similarity quantized values S [i] [j] (i = 1,..., M) (j = 1,..., N) of all gait feature vectors in YT [j] (j = 1,..., N) and all gait feature vectors in YT [j] (j = 1,..., N) are obtained, and finally, the largest one in S [i] [j] (i = 1,..., M) (j = 1,..., N) is selected as a similarity quantized calculation result of the to-be-detected portrait gait and the to-be-compared portrait gait.
Description
technical field [0001] The invention relates to gait recognition and portrait identification technology, in particular to a cross-comparison method and system for portrait gait identification. Background technique [0002] Gait recognition is an important biometric technology, which has important application value in the fields of intelligent security monitoring and judicial identification. In the field of forensic identification of portraits, gait features are a very important dynamic feature of portraits. Gait features contain rich individual identity information. By comparing the gait of the portrait to be checked and the gait of the portrait for comparison, it can be effectively used for Identify whether the two are the same person. At present, the portrait gait feature extraction method based on the deep learning network has become the mainstream technology in the field of pattern recognition. The output results of the extracted portrait gait features are usually prese...
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): G06V40/20G06V20/40G06V10/74G06K9/62
CPCG06F18/22
Inventor 曾锦飞
Owner 曾锦飞