Person Re-identification with a Body Orientation-Specific Convolutional Neural Network

Abstract : Person re-identification consists in matching images of a particular person captured in a network of cameras with non-overlapping fields of view. The challenges in this task arise from the large variations of human appearance. In particular, the same person could show very different appearances from different points of view. To address this challenge, in this paper we propose an Orientation-Specific Convolutional Neural Network (OSCNN) framework which jointly performs body orientation regression and extracts orientation-specific deep representations for person re-identification. A robust joint embedding is obtained by combining feature representations under different body orientations. We experimentally show on two public benchmarks that taking into account body orientations improves the person re-identification performance. Moreover , our approach outperforms most of the previous state-of-the-art re-identification methods on these benchmarks.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01895374
Contributor : Yiqiang Chen <>
Submitted on : Monday, October 15, 2018 - 10:48:00 AM
Last modification on : Monday, December 10, 2018 - 5:47:37 PM
Long-term archiving on : Wednesday, January 16, 2019 - 2:05:45 PM

File

ACIVS_OSCNN.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01895374, version 1

Citation

Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt. Person Re-identification with a Body Orientation-Specific Convolutional Neural Network. Advanced Concepts for Intelligent Vision systems, Sep 2018, Poitiers, France. ⟨hal-01895374⟩

Share

Metrics

Record views

59

Files downloads

171