• Home
  • Search
  • Reidentification by Relative Distance Comparison
  • Open Access IconOpen Access
  • Cite Icon767
  • https://doi.org/10.1109/tpami.2012.138Copy DOI Icon

Reidentification by Relative Distance Comparison

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Matching people across nonoverlapping camera views at different locations and different times, known as person reidentification, is both a hard and important problem for associating behavior of people observed in a large distributed space over a prolonged period of time. Person reidentification is fundamentally challenging because of the large visual appearance changes caused by variations in view angle, lighting, background clutter, and occlusion. To address these challenges, most previous approaches aim to model and extract distinctive and reliable visual features. However, seeking an optimal and robust similarity measure that quantifies a wide range of features against realistic viewing conditions from a distance is still an open and unsolved problem for person reidentification. In this paper, we formulate person reidentification as a relative distance comparison (RDC) learning problem in order to learn the optimal similarity measure between a pair of person images. This approach avoids treating all features indiscriminately and does not assume the existence of some universally distinctive and reliable features. To that end, a novel relative distance comparison model is introduced. The model is formulated to maximize the likelihood of a pair of true matches having a relatively smaller distance than that of a wrong match pair in a soft discriminant manner. Moreover, in order to maintain the tractability of the model in large scale learning, we further develop an ensemble RDC model. Extensive experiments on three publicly available benchmarking datasets are carried out to demonstrate the clear superiority of the proposed RDC models over related popular person reidentification techniques. The results also show that the new RDC models are more robust against visual appearance changes and less susceptible to model overfitting compared to other related existing models.

Similar Papers
  • Conference Article
  • Citations745

Person re-identification by probabilistic relative distance comparison

  • Jun 01, 2011
  • Wei-Shi Zheng +2
  • Book Chapter
  • Citations2

Adaptive Margin Nearest Neighbor for Person Re-Identification

  • Jan 01, 2015
  • Lei Yao +6
  • Research Article
  • Citations11

Structured learning of metric ensembles with application to person re-identification

  • Oct 27, 2016
  • Computer Vision and Image Understanding
  • Sakrapee Paisitkriangkrai +3
  • PDF
  • Research Article
  • Citations17

Bodyprint—A Meta-Feature Based LSTM Hashing Model for Person Re-Identification

  • Sep 18, 2020
  • Sensors (Basel, Switzerland)
  • Danilo Avola +5
  • Research Article
  • Citations4

Grandma, what a big beard you have! an exploration of the client's reaction to a change in the art therapist's appearance

  • Jul 01, 1998
  • Inscape
  • Barrie Damarell
  • Conference Article
  • Citations9

Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation

  • Oct 12, 2020
  • Yiheng Liu +4
  • Research Article
  • Citations7

Person re-identification with dictionary learning regularized by stretching regularization and label consistency constraint

  • Nov 05, 2019
  • Neurocomputing
  • Huafeng Li +4
  • Research Article
  • Citations23

PRISM: Person Reidentification via Structured Matching

  • Mar 01, 2017
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Ziming Zhang +1
  • Research Article
  • Citations11

Cross-view kernel collaborative representation classification for person re-identification

  • Mar 09, 2021
  • Multimedia Tools and Applications
  • Guoqing Zhang +4
  • Research Article
  • Citations10

Dissociable Neural Mechanisms Underlie the Effects of Attention on Visual Appearance and Response Bias.

  • Aug 24, 2023
  • The Journal of neuroscience : the official journal of the Society for Neuroscience
  • Sirawaj Itthipuripat +7
  • 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
  • Citations101

Learning Invariant Color Features for Person Reidentification.

  • Feb 18, 2016
  • IEEE Transactions on Image Processing
  • Rahul Rama Varior +3
  • Research Article
  • Citations1

Biodegradability of corn starch films containing nanocellulose fiber and thymol

  • Nov 22, 2024
  • Nanotechnology Reviews
  • Norhazirah Nordin +4
  • Book Chapter
  • Citations698

Person Re-identification by Video Ranking

  • Jan 01, 2014
  • Taiqing Wang +3
  • Research Article
  • Citations1

(42) Sun Exposures Impact the Postharvest Quality and Firmness of Harvested Bell Peppers

  • Jul 01, 2005
  • HortScience
  • Maria Dolores Muy-Rangel +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.