A pedestrian re-identification method based on a random erasure pedestrian alignment network

A pedestrian re-identification and pedestrian technology, applied in the field of computer vision, can solve problems such as network over-fitting and reduced matching accuracy

Pending Publication Date: 2019-04-05
CHANGZHOU UNIV
View PDF1 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the huge scale of the network, it is easy to cause network overfitting, thereby reducing the final matching accuracy.

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 a random erasure pedestrian alignment network
  • A pedestrian re-identification method based on a random erasure pedestrian alignment network
  • A pedestrian re-identification method based on a random erasure pedestrian alignment network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the accompanying drawings.

[0027] Such as Figure 1-9 As shown, a pedestrian re-identification method based on random erasing pedestrian alignment network, including the following steps:

[0028] Step 1, preprocessing the original pictures in the data set by random erasing data enhancement;

[0029] Random erasing is performed with a certain probability, for small batches of images I , assuming that the probability of its random erasure is , the probability that the image is not erased randomly is , images with different degrees of occlusion will be produced during the random erasing process.

[0030] Randomly select a rectangular area in an image , and then erase the original pixel with a random value.

[0031] The area of ​​the image is

[0032] , (1)

[0033] in: W is the width of the pedestrian image, H is the height of the pedestrian image.

[0034] Erase the height and widt...

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 a random erasure pedestrian alignment network, and the method comprises the following steps: 1, carrying out the preprocessing ofan original image in a data set through employing a random erasure data enhancement algorithm, increasing the shielding, and reducing the influence caused by the overfitting; Step 2, sending the preprocessed image into a basic branch of the network; Step 3, enabling the images with the image dislocation phenomenon to enter an affine estimation branch to be aligned; 4, the aligned image enters analignment branch to be repositioned and subjected to feature extraction; 5, pedestrian re-identification is carried out in the three large pedestrian re-identification databases, and values of Rank-1and Map are used for representing effects of the re-identification test; According to the method, the image dislocation phenomenon is well improved, the overfitting influence is reduced, and the pedestrian re-identification rate can be well improved through the trained network.

Description

technical field [0001] The invention relates to a pedestrian re-identification method based on a random erasing pedestrian alignment network, which belongs to the technical field of computer vision. Background technique [0002] Pedestrian re-identification refers to the recognition of pedestrians in different camera images, that is, given a monitored pedestrian image, retrieve the pedestrian image under cross-device. The current research on pedestrian re-identification is mainly based on two categories: deep learning and non-deep learning. In recent years, pedestrian re-identification methods have mainly focused on the following two aspects: the first is the extraction of features; the second is the processing of lighting, background clutter, camera angles, and occlusions. The methods to solve these two problems are based on non-deep learning methods (such as metric learning, transfer learning, sparse representation, etc.) and methods based on deep learning. The methods us...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/10G06N3/045G06F18/214
Inventor 王洪元金翠陈首兵
Owner CHANGZHOU UNIV
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