Unlock instant, AI-driven research and patent intelligence for your innovation.

A pedestrian re-identification method based on multi-directional multi-channel strip structure

An identification method and multi-directional technology, which is applied in the field of pedestrian re-identification based on multi-directional multi-channel strip structure, can solve the problems of complex training model, poor performance of pedestrian re-identification, and limited selection of pedestrian attributes, so as to reduce the The feature dimension is too high, the effect of superior identification, and the effect of good robustness

Inactive Publication Date: 2019-03-01
TONGJI UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Patent CN104992142A proposes a pedestrian recognition method based on the combination of deep learning and attribute learning, which can describe pedestrian features from a higher semantic level. However, the training model is too complicated and limited by the selection of pedestrian attributes
Furthermore, due to the influence of various factors such as illumination changes, posture, viewing angle, occlusion, image resolution, etc., this makes the performance of pedestrian re-identification in the intelligent analysis of surveillance video still poor.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A pedestrian re-identification method based on multi-directional multi-channel strip structure
  • A pedestrian re-identification method based on multi-directional multi-channel strip structure
  • A pedestrian re-identification method based on multi-directional multi-channel strip structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] In order to make the object, technical scheme and advantages of the present invention clearer, below in conjunction with embodiment, specifically as figure 1 The shown algorithm flow chart further describes the present invention in detail. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention.

[0061] Step 1: Two-channel strip structure feature representation, the specific description is as follows: there are many strip structures in the appearance of pedestrians, and these strip structures of 0°, 45°, 90°, and 135°, such as figure 2 As shown, it has obvious salience in the human visual system, and it can better describe the spatial correlation between adjacent points. In order to incorporate more information, the present invention selects the Lab color space that is more suitable for the human visual system. In order to describe this strip structure under the color...

Embodiment approach

[0108] figure 1 It is a flowchart of the implementation of the MMLBD algorithm of the present invention, and the specific implementation is as follows:

[0109] 1. Transform the color image from RGB color space to Lab color space;

[0110] 2. Obtain single-channel barcoded BSV in different directions c，θ (A);

[0111] 3. Obtain the color difference weight WBSV of the single-channel bar structure in different directions c，θ ;

[0112] 4. According to the binary interaction mechanism, obtain the dual-channel bar structure coding B used in different directions θ =BSV' θ，1 ,BSV' θ，2 ,BSV' θ，3 ;

[0113] 5. Obtain the color difference weight corresponding to the dual-channel bar structure in different directions

[0114] 6. By WBSV' i，j，θ Redefine the color difference weights of the two-channel bar structure in different directions;

[0115] 7. Using overlapping strategy and sliding window to extract bar structure color difference weighted histogram descriptor in multi...

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

No PUM Login to View More

Abstract

The invention relates to a pedestrian re-identification method based on a multi-directional multi-channel strip structure, comprising the following steps: 1) Obtaining the multi-directional dual-color channel strip structure feature set B corresponding to the pixel points in the image of the pedestrian to be identified and the comparison image respectively θ ; 2) Obtain the weighted color difference weight set W of the multi-directional dual-channel strip structure weighted color difference of the pixel point by using color difference θ ; 3) Use the sliding window to obtain the histogram descriptor H in different directions respectively θ ; 4) According to the Canberra distance calculation based on the histogram descriptor H θ The distance set D of the pedestrian image to be identified and the comparison image s ; 5) Select the distance set D s The optimal triplet distance pair, ELF descriptor and HOG descriptor are used as the feature code, and the final distance between the pedestrian image to be identified and the comparison image is obtained; 6) According to the nearest neighbor theory, the distances are sorted, and finally obtained Compared with the matching rate of the pedestrian image to be identified and the comparison image compared with the prior art, the present invention has the advantages of being fast, accurate, and robust.

Description

technical field [0001] The invention relates to the field of monitoring video intelligent analysis, in particular to a pedestrian re-identification method based on a multi-directional multi-channel strip structure. Background technique [0002] Pedestrian re-identification refers to the problem of matching pedestrians from different camera perspectives in a multi-camera system. It provides critical assistance in the analysis of different aspects such as pedestrian identity and behavior, and has developed into a key component in the field of intelligent video surveillance. [0003] The main methods in the field of person re-ID can be divided into the following two categories: 1) Appearance-based methods for person re-ID; 2) Methods based on metric learning. Low-level features, such as: color (color space, histogram, dominant color, etc.) and texture (LBP, Gabor, co-occurrence matrix, etc.) have been widely used in appearance-based feature representation methods. Among them,...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/20G06V10/751
Inventor 赵才荣王学宽苗夺谦章宗彦
Owner TONGJI UNIV