A pedestrian re-identification method based on deep multi-view feature distance learning

A technology of pedestrian re-identification and feature distance, which is applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as pollution and insufficient application of pedestrian re-identification.

Active Publication Date: 2019-06-18
青岛类认知人工智能有限公司
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since features from higher layers have large receptive fields and are easily polluted by human poses and background clutter, they cannot be adequately applied to person re-identification

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 deep multi-view feature distance learning
  • A pedestrian re-identification method based on deep multi-view feature distance learning
  • A pedestrian re-identification method based on deep multi-view feature distance learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0057] The framework diagram of the pedestrian re-identification method algorithm based on deep multi-view feature distance learning, such as figure 1 As shown, from the input and output of the algorithm, the present invention inputs two image libraries (query image library, image library to be processed), wherein the two images are passed through in the stages of CNN feature area aggregation and LOMO feature extraction, and N similar target areas are obtained .

[0058] From the algorithm flow point of view. For the regional feature vector, the fine-tuned Resnet-50 model is used to extract the three-dimensional convolution feature vector, and the sliding frame technology is used to process the convolution feature, that is, the weight of the target area is increased by a certain weight adaptive method, while Reduce the weight of non-target...

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 pedestrian re-identification method based on deep multi-view feature distance learning is specifically implemented according to the following steps: step 1, extracting region feature vectors; Step2, region division: according to all the feature vectors of the image obtained in the step 1, carrying out normalization through a normalization algorithm l2 norm; Representing a vector set of the image in a summation mode, and performing l2 norm normalization processing on image representation; dividing One image into N regions, and obtaining depth region aggregation characteristics; Step 3, LOMO feature extraction: respectively extracting traditional LOMO features from pedestrian images in the reference set and the test set; 4, carrying out multi-view feature distance learning, and obtaining two distances from the two aspects of depth region aggregation features and LOMO features through XQDA training of the two features; Step 5, a weighted fusion strategy: carrying out parameter weighted fusion on the two distances obtained in the step 4 to obtain a final distance, and obtaining a matched grade according to the final distance; The robustness of pedestrian re-identification can be obviously improved; And the pedestrian re-identification performance is improved.

Description

technical field [0001] The invention belongs to the technical field of image analysis and image recognition, and in particular relates to a pedestrian re-identification method for deep multi-view feature distance learning. Background technique [0002] In recent years, the demand for surveillance camera networks in public security, commercial activities, smart transportation, national defense, and military applications has increased, such as: installing surveillance camera networks in airports, subways, stations, banks, schools, and military facilities. It is based on automatic unmanned monitoring for safety, so as to effectively ensure the safety of national facilities and the public. Just because the surveillance camera network has such a great application prospect, the intelligent video surveillance system has attracted the attention of many countries, and invested a lot of money to carry out extensive research work. [0003] The problem of person re-identification is th...

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 Applications(China)
IPC IPC(8): G06K9/00
Inventor 廖开阳邓轩郑元林章明珠雷浩刘山林
Owner 青岛类认知人工智能有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap