• Home
  • Search
  • Person Re-identification Based on Feature Fusion
  • Cite Icon6
  • https://doi.org/10.1007/978-3-030-26766-7_7Copy DOI Icon

Person Re-identification Based on Feature Fusion

  • Jan 1, 2019
  • Qiang-Qiang Ren +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Person re-identification is a matching task of person images captured from different camera views. In the real scene, This task is extremely challenging due to changes in pedestrian poses, camera angles and lighting. How to extract robust pedestrian features has become a key step in Person re-identification. In this paper, we propose an person re-identification model based on combined visual features. Our features consist of traditional visual features and convolutional neural network (CNN) features. We extract the CNN feature of person image and fuse them with robust Local Maximal Occurrence (LOMO) features. This fused feature has better performance. Before extracting features, we use the Retinex algorithm to preprocess person images. Finally adopt a random sampling softmax loss to effectively train the model. We experimentally show the effectiveness and accuracy of the proposed method on the VIPeR and PRID450s datasets.

Similar Papers
  • Research Article
  • Citations3

Person re-identification transformer with patch attention and pruning

  • Nov 26, 2024
  • Journal of Visual Communication and Image Representation
  • Fabrice Ndayishimiye +3
  • PDF
  • Research Article
  • Citations3

Tensor-Based Emotional Category Classification via Visual Attention-Based Heterogeneous CNN Feature Fusion

  • Apr 10, 2020
  • Sensors (Basel, Switzerland)
  • Yuya Moroto +3
  • Conference Article
  • Citations23

Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations

  • Jan 01, 2018
  • Yiqiang Chen +4
  • Conference Article

Improved Local Maximal Occurrence Feature Representation for Person Re-Identification

  • Nov 01, 2018
  • Yuanxin Zhu +4
  • Research Article
  • Citations18

Multilinear subspace learning for Person Re-Identification based fusion of high order tensor features

  • Nov 18, 2023
  • Engineering Applications of Artificial Intelligence
  • Ammar Chouchane +5
  • Research Article

Dynamic locally connected layer for person re-identification

  • Feb 27, 2018
  • Cluster Computing
  • Faping Li +2
  • Research Article

Recent progress in person re-ID

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Zhang Yongfei +10
  • Conference Article
  • Citations2

Visualization for neural-network-based person re-identification

  • Apr 01, 2022
  • Teng-Yok Lee
  • Research Article
  • Citations28

Combining multilevel feature extraction and multi-loss learning for person re-identification

  • Jan 17, 2019
  • Neurocomputing
  • Weilin Zhong +4
  • 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
  • Conference Article
  • Citations169

Person re-identification using CNN features learned from combination of attributes

  • Dec 01, 2016
  • Tetsu Matsukawa +1
  • Conference Article
  • Citations33

Human Illegal Activity Recognition Based on Deep Learning Techniques

  • Feb 24, 2023
  • S G Shivaprasad Yadav +4
  • Research Article
  • Citations1

Visual tracking with complementary deep feature optimization

  • Aug 27, 2018
  • Journal of Electronic Imaging
  • Wei Wang +2
  • Conference Article
  • Citations2498

Person re-identification by Local Maximal Occurrence representation and metric learning

  • Jun 01, 2015
  • Shengcai Liao +3
  • PDF
  • Research Article
  • Citations2

Person re-ID while Crossing Different Cameras: Combination of Salient-Gaussian Weighted BossaNova and Fisher Vector Encodings

  • Jan 01, 2017
  • International Journal of Advanced Computer Science and Applications
  • Mahmoud Mejdoub +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.