Vehicle re-identification method based on feature enhancement

A feature enhancement and re-recognition technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as information loss, improve network width, avoid sub-optimal results, and improve the ability to extract features.

Pending Publication Date: 2022-02-01
HEBEI UNIV OF TECH
View PDF1 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of the present invention can not only overcome complex environmental changes, such as the problem of local significant information loss caused by drastic changes in illumination and obstructions, but also meet the needs of efficient and fast search for target vehicles in safety supervision and intelligent transportation systems. The knowledge distillation method processes the feature-enhanced vehicle re-identification network to make the network more lightweight and efficient

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
  • Vehicle re-identification method based on feature enhancement
  • Vehicle re-identification method based on feature enhancement
  • Vehicle re-identification method based on feature enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] The vehicle re-identification method based on feature enhancement of the present invention extracts vehicle global feature vectors and local feature vectors through different attention and reduces the amount of network parameters through knowledge distillation. The specific steps are as follows:

[0089] The first step, vehicle image preprocessing:

[0090] First, the original image set X={x 1 , x 2 ,...,x m} is divided into training set F={x 1 , x 2 ,...,x t ;tt+1 ,...,x q ;tq+1 ,...,x m ;qi Represents each original vehicle image, the division of the vehicle re-identification data set is random, i∈[1, m] only represents the subscript of each image, t, q, g represent the training set, query set, gallery The index of the last image in the set, with no special ordering. The classification label of the training set T is defined as Y T ={y 1 ,y 2 ,...,y N}. Among them, y i Represents the label of the vehicle image in the training set, and N represents that the...

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 vehicle re-identification method based on feature enhancement, and the method comprises the steps: constructing a feature enhancement network based on multi-attention guidance, wherein the feature enhancement network is provided with a self-adaptive feature erasing module with space attention guidance and a multi-receptive field residual attention module; helping a backbone network to obtain rich vehicle appearance features under receptive fields of different sizes through multi-receptive-field residual attention, and utilizing a self-adaptive feature erasing module guided by space attention to selectively erase the most significant features of a vehicle, so the local branches of the multi-attention-guided feature enhancement network can mine potential local features, and the global features of the global branches and the potential local features of the erasure branches are fused to complete the vehicle re-identification process. The method of the invention not only can overcome the problem of local significant information loss caused by complex environmental changes, such as violent illumination changes and barrier shielding, but also can meet the requirements of efficiently and quickly searching the target vehicle in safety supervision and intelligent traffic systems.

Description

Technical field: [0001] The present invention relates to the technical field of recording carrier processing for identifying graphics, in particular to a vehicle re-identification method based on feature enhancement, more preferably a vehicle re-identification method combining feature enhancement and knowledge distillation. Background technique: [0002] Vehicle re-identification can be viewed as an instance-level object search task. Different from the traditional vehicle detection problem, the vehicle re-identification problem refers to the retrieval problem of judging whether vehicle images captured in non-overlapping areas belong to the same vehicle in a traffic monitoring scene within a specific range. At present, surveillance cameras are installed in areas with developed traffic both at home and abroad. How to make better use of surveillance cameras for traffic supervision and criminal investigation and build a safe and complete intelligent surveillance system is a very...

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): G06V20/54G06V10/46G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/082G06N3/048G06N3/045G06F18/253
Inventor 于明何坤于洋阎刚朱叶师硕郝小可郭迎春刘依吕华
Owner HEBEI UNIV OF TECH
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