• Home
  • Search
  • Suitable Clustering for Multi-shot Person Re-identification
  • https://doi.org/10.19026/rjaset.15.5286Copy DOI Icon

Suitable Clustering for Multi-shot Person Re-identification

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

This study address the problem of selecting the most informative images for multi-shot person re-identification approaches. Actually, clustering algorithms have been one of the most proposed solutions. The objective of this study is to propose a suitable clustering method for most discriminative images selection in person re-identification. Clustering methods aim to divide huge data amount into groups depending on their characteristics, so that further data processing can be easier and more manageable. Actually, clustering is concerned in multiple fields such as document treatments, video summery and image processing. Person re-identification, a new area of research deeply investigated by the vision community, would be an interest application of the clustering algorithms. Person re-identification can be defined as the process of finding the identity of an unknown person who has already been observed in a camera view. Recently, re-identifying people over large public cameras networks has become a crucial task of great importance to ensure public security. Person Re-identification approaches can be either single shot, using one image to model a person’s appearance, or multiple shot, using many images to identify a person. Actually, the real person re-identification framework is a multi-shot scenario. However, redundant images remain a challenging problem because execution time and memory consumption are significantly affected. In this study, an extensive comparison of clustering algorithms of state of art associated to a person re-identification framework is studied. Specifically, we evaluate the impact of clustering algorithms in re-identification rates. A standard re- identification framework is detailed and a synthesis of state of art methods comparison is conducted, using personal images and two standard datasets PRID_2011 and iLIDS-VID. Performing results are achieved in both person re-id rates (67.1% and 59.2%) and memory gain (92.7% and 97.8%) for Prid_2011 and iLIDS-VID datasets respectively.

Similar Papers
  • Research Article

Recent progress in person re-ID

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Zhang Yongfei +10
  • Research Article
  • Citations10

Effective multi-shot person re-identification through representative frames selection and temporal feature pooling

  • Oct 12, 2019
  • Multimedia Tools and Applications
  • Thuy-Binh Nguyen +4
  • PDF
  • Research Article
  • Citations11

An Effective Adversarial Attack on Person Re-Identification in Video Surveillance via Dispersion Reduction

  • Jan 01, 2020
  • IEEE Access
  • Yu Zheng +2
  • Conference Article
  • Citations14

A Unified Generative Adversarial Framework for Image Generation and Person Re-identification

  • Oct 15, 2018
  • Yaoyu Li +3
  • Research Article
  • Citations63

Pose-driven attention-guided image generation for person re-Identification

  • Dec 13, 2022
  • Pattern Recognition
  • Amena Khatun +3
  • Conference Article
  • Citations4

Exploiting low-rank structures from cross-camera images for robust person re-identification

  • Oct 01, 2014
  • Ming-Hang Fu +2
  • Research Article
  • Citations732

End-to-End Comparative Attention Networks for Person Re-Identification.

  • May 03, 2017
  • IEEE Transactions on Image Processing
  • Hao Liu +4
  • Conference Article
  • Citations32

SHaPE: A Novel Graph Theoretic Algorithm for Making Consensus-Based Decisions in Person Re-identification Systems

  • Oct 01, 2017
  • Arko Barman +1
  • Research Article
  • Citations55

HOReID: Deep High-Order Mapping Enhances Pose Alignment for Person Re-Identification.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Pingyu Wang +4
  • Research Article
  • Citations360

Person Re-Identification by Camera Correlation Aware Feature Augmentation.

  • Feb 09, 2017
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Ying-Cong Chen +3
  • Conference Article
  • Citations3

How feature fusion can help to improve multi-shot person re-identification performance?

  • Oct 01, 2020
  • Thuy-Binh Nguyen +4
  • Research Article
  • Citations14

A Versatile Framework for Multi-Scene Person Re-Identification.

  • Mar 01, 2025
  • IEEE transactions on pattern analysis and machine intelligence
  • Wei-Shi Zheng +2
  • Research Article
  • Citations20

Cross-dataset person re-identification using deep convolutional neural networks: effects of context and domain adaptation

  • Jul 19, 2018
  • Multimedia Tools and Applications
  • Anıl Genç +1
  • PDF
  • Research Article
  • Citations27

A Multi-Attention Approach for Person Re-Identification Using Deep Learning

  • Apr 02, 2023
  • Sensors (Basel, Switzerland)
  • Shimaa Saber +4
  • Research Article
  • Citations3

Weakly supervised end-to-end domain adaptation for person re-identification

  • Dec 28, 2023
  • Computers and Electrical Engineering
  • Lei Zhang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.