Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pedestrian re-identification method based on deep learning

A person re-identification and deep learning technology, applied in the field of deep learning and pedestrian re-identification, can solve the problems of reducing the recognition accuracy, consuming resources, reducing the effectiveness of learning, etc., to speed up the training speed, easy to fit, and optimize the network. Effects of parameters

Active Publication Date: 2020-03-27
HANGZHOU DIANZI UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, calculating a large number of high-dimensional images will consume a lot of resources, and the effectiveness of learning will be reduced due to the redundancy of background information, and the accuracy of recognition will be reduced.

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
  • Pedestrian re-identification method based on deep learning
  • Pedestrian re-identification method based on deep learning
  • Pedestrian re-identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention is mainly aimed at the method and algorithm innovation of metric learning in the pedestrian re-identification technology. The training process of the entire model is introduced in detail. The specific implementation steps of the present invention, the purpose and summary of the present invention will be described in detail below in conjunction with the accompanying drawings. Fruits will become more apparent.

[0037] figure 1It is a flow chart of the implementation of the present invention, from which the structure of the convolutional neural network applied to pedestrian re-identification can be clearly seen. The dotted box is the operation in the convolutional neural network, including the layer1, layer2, layer3 of the convolution operation and the FullConnect of the full connection operation; the data not in the dotted box is the data we input and the neural network. The data. The connection lines in the figure indicate the order of data proce...

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 pedestrian re-identification method based on deep learning. The method comprises the following steps: calculating an Euclidean distance between two input data after each stepof dimension reduction or convolution operation while extracting features of a pair of data input into a twin neural network, thereby obtaining an Euclidean distance matrix; and designing a loss function by utilizing the Euclidean distance matrix, optimizing the Euclidean distance calculated by finally using a feature sequence by using the Euclidean distance calculated by an image pair or a high-dimensional feature image pair, and accelerating the training of the network through gradient return and parameter optimization of the network. According to the invention, pedestrian information in anoriginal image is fully utilized, complete image information is used to optimize blurred image features, and network parameters are further optimized, so that parameters between neural networks are easier to fit, and the network training speed is accelerated.

Description

technical field [0001] The invention belongs to pedestrian re-identification in computer vision, mainly to improve the accuracy of pedestrian re-identification, and specifically relates to a method based on deep learning and pedestrian re-identification. Background technique [0002] Pedestrian re-identification (Person Re-identification, also known as pedestrian re-identification, referred to as Re-ID, is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence. It is widely considered to be a sub-problem of image retrieval. Give Set a monitoring pedestrian image, and retrieve the pedestrian image under cross-device. In the monitoring video, due to the resolution of the camera and the shooting angle, it is usually impossible to get a very high-quality face picture. When the face recognition fails, Pedestrian re-identification has become a very important substitute technology. [0003] Computer vision ...

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
CPCG06V40/10G06V20/41G06V20/46
Inventor 颜成钢黄智坤王文铅高宇涵孙垚棋张继勇张勇东
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com