Abstract

In recent years, the development of robust Intelligent transportation systems (ITS) is tackled across the globe to provide better traffic efficiency by reducing frequent traffic problems. As an application of ITS, vehicle re-identification has gained ample interest in the domain of computer vision and robotics. Convolutional neural network (CNN) based methods are developed to perform vehicle re-identification to address key challenges such as occlusion, illumination change, scale, etc. The advancement of transformers in computer vision has opened an opportunity to explore the re-identification process further to enhance performance. In this paper, a framework is developed to perform the re-identification of vehicles across CCTV cameras. To perform re-identification, the proposed framework fuses the vehicle representation learned using a CNN and a transformer model. The framework is tested on a dataset that contains 81 unique vehicle identities observed across 20 CCTV cameras. From the experiments, the fused vehicle re-identification framework yields an mAP of 61.73% which is significantly better when compared with the standalone CNN or transformer model.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665497817
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2022 - Bangalore, India
Duration: 08-07-202210-07-2022

Publication series

Name2022 IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2022

Conference

Conference2022 IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2022
Country/TerritoryIndia
CityBangalore
Period08-07-2210-07-22

All Science Journal Classification (ASJC) codes

  • Control and Optimization
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Enhanced Vehicle Re-identification for ITS: A Feature Fusion approach using Deep Learning'. Together they form a unique fingerprint.

Cite this