A method for pedestrian re-identification based on siamese network

A pedestrian re-identification and network technology, applied in the field of pedestrian re-identification, can solve the problems of low reliability of results, increase the workload of manual research and judgment, reduce the degree of automation of video analysis, etc., achieve the effect of reducing query time and improving the degree of discrimination

Active Publication Date: 2020-04-10
海优(南京)科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This processing method not only increases the workload of manual research and judgment, and reduces the automation of video analysis, but also, due to differences in viewing angles and lighting, the appearance characteristics of pedestrians will change greatly, which may cause the provided top results to be inconsistent. Reliability is lower

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 method for pedestrian re-identification based on siamese network
  • A method for pedestrian re-identification based on siamese network
  • A method for pedestrian re-identification based on siamese network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention utilizes the pre-trained ResNet-50 network to extract features from images. In order to measure the similarity between images, two identical ResNet-50 networks are used to form a Siamese network, and then the Siamese network is trained using the training data set. After training, this Siamese network can classify the input image with labels, and can also complete the measurement of the similarity between two images.

[0032] combine Figure 1~2 , the present invention is based on the method for pedestrian re-identification of Siamese network, comprises the following steps:

[0033] Step 1: Pre-train the ResNet-50 network: use the ImageNet data set as the training data set, train a ResNet-50 network, so that the ResNet-50 network has an ideal initial value; the ideal initial value refers to the ability to learn image features ;

[0034] Step 2: Fine-tune the ResNet-50 network: Replace the softmax output layer of the ResNet-50 network with a convol...

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 discloses a method for pedestrian re-identification based on Siamese network. The method is: first use two identical ResNet-50 convolutional neural networks to form a Siamese network, including pre-training the ResNet-50 network, adjusting the ResNet-50 network, building a Siamese network, and improving the Siamese network; then preprocessing training Data set, and use the training data set to train the Siamese network, and finally match the image to be checked with the image in the training data set to form an image pair for pedestrian re-identification, and use the classification results of the two images and whether the two images are consistent as the discrimination condition to judge Which images in the training dataset belong to the same pedestrian as the query image. The invention improves the degree of differentiation of image depth features and the accuracy of re-identification of pedestrians, and reduces the query time for searching images in a large-scale image set.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for pedestrian re-identification based on a Siamese network. Background technique [0002] In recent years, with the popularization of video surveillance systems, video surveillance systems are playing an increasingly important role in combating crime and maintaining stability. Video investigation has become a new method for public security organs to investigate and handle cases. In video surveillance applications, the retrieval of specific suspects (especially people) is an important requirement. At present, this process is mainly completed manually, which consumes a lot of manpower, material resources and time, and affects the efficiency of investigation and case handling. The core key problem of specific target surveillance video retrieval - pedestrian re-identification refers to judging whether pedestrian images appearing under different surveillance cameras...

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
CPCG06V40/10G06F18/2413G06F18/24147
Inventor 伏长虹高梽强
Owner 海优(南京)科技有限公司
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