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

Neural network for pedestrian re-identification and pedestrian re-identification algorithm based on deep learning

A pedestrian re-identification and neural network technology, applied in the field of pedestrian re-identification algorithm, can solve problems such as large posture changes, increased pedestrian difficulty, complex viewing angle changes, etc., to reduce false recognition rate, improve correct recognition rate, and robust pedestrian characteristics The effect of matching ability

Active Publication Date: 2019-09-13
PEKING UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are usually large pose changes and complex viewing angle changes between different images of pedestrians acquired by different cameras, which greatly increases the difficulty of pedestrian re-identification algorithms to match pedestrians

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
  • Neural network for pedestrian re-identification and pedestrian re-identification algorithm based on deep learning
  • Neural network for pedestrian re-identification and pedestrian re-identification algorithm based on deep learning
  • Neural network for pedestrian re-identification and pedestrian re-identification algorithm based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0030] figure 1 A conceptual schematic diagram of a first neural network 100 for pedestrian re-identification according to an embodiment of the present invention is shown.

[0031] Such as figure 1 As shown, the first neural network 100 for pedestrian re-identification includes a first neural network 101 and a second neural network 103 .

[0032] Such as figure 1 As shown, the first neural network 101 uses the original full-body...

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 neural network for pedestrian re-identification and a pedestrian re-identification algorithm based on deep learning. The neural network includes: a first neural network using an original full-body image of a pedestrian as a first input and outputting a first recognition feature; using an affine transformed image of a human body part image extracted from the original full-body image of a pedestrian as a second input and outputting The second neural network of the second recognition feature, wherein the human body part includes at least the head, torso and limbs, and the combination of the first recognition feature and the second recognition feature is the total recognition feature. It has a more robust pedestrian feature matching capability, which can improve the correct recognition rate and / or reduce the false recognition rate.

Description

technical field [0001] The invention relates to the fields of convolutional neural networks and image recognition. More specifically, the present invention relates to a neural network for pedestrian re-identification and a pedestrian re-identification algorithm based on deep learning. Background technique [0002] With the popularity of video surveillance technology, the role of pedestrian re-identification technology has become increasingly important, it can help people automatically complete the task of searching for specific people from massive image or video data. [0003] The use of convolutional neural networks for feature extraction and feature matching are two important components of person re-identification technology. However, there are usually large pose changes and complex viewing angle changes between different images of pedestrians acquired by different cameras, which greatly increases the difficulty of pedestrian re-identification algorithms to match pedestri...

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): G06K9/00G06K9/62G06N3/04G06T3/00
CPCG06T3/0075G06V40/103G06N3/045G06F18/214
Inventor 张史梁田奇高文李佳宁苏驰
Owner PEKING 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