A Vehicle Comparison and Re-Identification System Based on Residual Network
In the highway intelligent monitoring system, it is difficult to find the target vehicle through millions of pictures because of the presence of fake-licensed vehicles. In order to solve this problem, a vehicle comparison and re-identification (Re-ID) system is built in this paper. By introducing Ci...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Machines |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-1702/10/9/799 |
_version_ | 1797485591003136000 |
---|---|
author | Weifeng Yin Yusong Min Junyong Zhai |
author_facet | Weifeng Yin Yusong Min Junyong Zhai |
author_sort | Weifeng Yin |
collection | DOAJ |
description | In the highway intelligent monitoring system, it is difficult to find the target vehicle through millions of pictures because of the presence of fake-licensed vehicles. In order to solve this problem, a vehicle comparison and re-identification (Re-ID) system is built in this paper. By introducing Circle loss and Generalized-Mean(GeM) pooling, vehicle feature extraction and storage, vehicle comparison and vehicle search can be realized. Experimental results show that the proposed algorithm reaches 95.79% of the mean Average Precision (mAP) on the vehicle search task, which meets the requirements of practical applications. |
first_indexed | 2024-03-09T23:21:00Z |
format | Article |
id | doaj.art-f036d13439834db7a5c097a4a2cba32b |
institution | Directory Open Access Journal |
issn | 2075-1702 |
language | English |
last_indexed | 2024-03-09T23:21:00Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Machines |
spelling | doaj.art-f036d13439834db7a5c097a4a2cba32b2023-11-23T17:27:05ZengMDPI AGMachines2075-17022022-09-0110979910.3390/machines10090799A Vehicle Comparison and Re-Identification System Based on Residual NetworkWeifeng Yin0Yusong Min1Junyong Zhai2School of Automation, Southeast University, Nanjing 210096, ChinaSchool of Automation, Southeast University, Nanjing 210096, ChinaSchool of Automation, Southeast University, Nanjing 210096, ChinaIn the highway intelligent monitoring system, it is difficult to find the target vehicle through millions of pictures because of the presence of fake-licensed vehicles. In order to solve this problem, a vehicle comparison and re-identification (Re-ID) system is built in this paper. By introducing Circle loss and Generalized-Mean(GeM) pooling, vehicle feature extraction and storage, vehicle comparison and vehicle search can be realized. Experimental results show that the proposed algorithm reaches 95.79% of the mean Average Precision (mAP) on the vehicle search task, which meets the requirements of practical applications.https://www.mdpi.com/2075-1702/10/9/799vehicle re-identificationdeep learningconvolutional neural network (CNN)residual network |
spellingShingle | Weifeng Yin Yusong Min Junyong Zhai A Vehicle Comparison and Re-Identification System Based on Residual Network Machines vehicle re-identification deep learning convolutional neural network (CNN) residual network |
title | A Vehicle Comparison and Re-Identification System Based on Residual Network |
title_full | A Vehicle Comparison and Re-Identification System Based on Residual Network |
title_fullStr | A Vehicle Comparison and Re-Identification System Based on Residual Network |
title_full_unstemmed | A Vehicle Comparison and Re-Identification System Based on Residual Network |
title_short | A Vehicle Comparison and Re-Identification System Based on Residual Network |
title_sort | vehicle comparison and re identification system based on residual network |
topic | vehicle re-identification deep learning convolutional neural network (CNN) residual network |
url | https://www.mdpi.com/2075-1702/10/9/799 |
work_keys_str_mv | AT weifengyin avehiclecomparisonandreidentificationsystembasedonresidualnetwork AT yusongmin avehiclecomparisonandreidentificationsystembasedonresidualnetwork AT junyongzhai avehiclecomparisonandreidentificationsystembasedonresidualnetwork AT weifengyin vehiclecomparisonandreidentificationsystembasedonresidualnetwork AT yusongmin vehiclecomparisonandreidentificationsystembasedonresidualnetwork AT junyongzhai vehiclecomparisonandreidentificationsystembasedonresidualnetwork |