Pedestrian re-identification method and system based on multi-scheme parallel attention mechanism
A pedestrian re-identification and multi-scheme technology, applied in the field of pedestrian re-identification method and system based on multi-scheme parallel attention mechanism, can solve the problem of insufficient performance of pedestrian re-identification
Pending Publication Date: 2021-04-20
SUN YAT SEN UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the above-mentioned technical problems, the object of the present invention is to provide a pedestrian re-identification method and system based on a multi-scheme parallel attention mechanism, so as to solve the problem of insufficient pedestrian re-identification performance of the existing technology using the attention mechanism
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
[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. For the step numbers in the following embodiments, it is only set for the convenience of illustration and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art sexual adjustment.
[0039] refer to figure 1 and figure 2 , the present invention provides a method for pedestrian re-identification based on a multi-scheme parallel attention mechanism, the method comprising the following steps:
[0040] Input the pedestrian picture a to be identified and the image g in the library to the feature extraction network and feature enhancement network respectively, and extract the corresponding original pedestrian feature vector t a and t g ;
[0041] The original pedestrian feature vector t a and 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 pedestrian re-identification method and system based on a multi-scheme parallel attention mechanism, and the method comprises the steps: respectively inputting a to-be-identified pedestrian image a and an in-library image g into a feature extraction network and a feature enhancement network, and obtaining corresponding original pedestrian feature vectors ta and tg through extraction; respectively inputting the original pedestrian feature vectors ta and tg into a full connection layer to obtain pedestrian categories ca and cg; and carrying out feature comparison on the pedestrian categories ca and cg, solving an Euclidean distance, and comparing the Euclidean distance with a threshold value to obtain a judgment result. The system comprises a feature vector extraction module, a category extraction module and a feature comparison module. By using the pedestrian re-identification method and system, the feature enhancement effect of the attention mechanism can be amplified, and the pedestrian re-identification method and system has good identification performance in a pedestrian re-identification task. The pedestrian re-identification method and system based on the multi-scheme parallel attention mechanism can be widely applied to the field of pedestrian image processing in computer vision.
Description
technical field [0001] The invention relates to the field of pedestrian image processing in computer vision, in particular to a pedestrian re-identification method and system based on a multi-scheme parallel attention mechanism. Background technique [0002] Pedestrian re-identification under cross-camera is a research hotspot in the field of computer vision. It performs pedestrian matching under a non-overlapping multi-camera network, that is, to confirm whether the pedestrian targets captured by cameras in different positions at different times are the same person. Factors such as the brightness and darkness of the shooting scene, the difference in the angle of view of the camera, and the change of the pedestrian's own posture will cause visual ambiguity, which brings a major difficulty to pedestrian re-identification; at the same time, the time and place of the pedestrian's appearance are also Random and uncertain, this spatio-temporal uncertainty also brings challenges ...
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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
Inventor 胡海峰刘柏宏卢泽丰
Owner SUN YAT SEN UNIV