Improving night-time pedestrian retrieval with distribution alignment and contextual distance

Mang Ye, Yi Cheng, Xiangyuan LAN*, Hongyuan Zhu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

Night-time pedestrian retrieval is a cross-modality retrieval task of retrieving person images between day-time visible images and night-time thermal images. It is a very challenging problem due to modality difference, camera variations, and person variations, but it plays an important role in night-time video surveillance. The existing cross-modality retrieval usually focuses on learning modality sharable feature representations to bridge the modality gap. In this article, we propose to utilize auxiliary information to improve the retrieval performance, which consistently improves the performance with different baseline loss functions. Our auxiliary information contains two major parts: cross-modality feature distribution and contextual information. The former aligns the cross-modality feature distributions between two modalities to improve the performance, and the latter optimizes the cross-modality distance measurement with the contextual information. We also demonstrate that abundant annotated visible pedestrian images, which are easily accessible, help to improve the cross-modality pedestrian retrieval as well. The proposed method is featured in two aspects: the auxiliary information does not need additional human intervention or annotation; it learns discriminative feature representations in an end-to-end deep learning manner. Extensive experiments on two cross-modality pedestrian retrieval datasets demonstrate the superiority of the proposed method, achieving much better performance than the state-of-the-arts.

Original languageEnglish
Article number8861378
Pages (from-to)615-624
Number of pages10
JournalIEEE Transactions on Industrial Informatics
Volume16
Issue number1
DOIs
Publication statusPublished - Jan 2020

Scopus Subject Areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

User-Defined Keywords

  • contextual distance
  • Cross modality
  • distribution alignment
  • pedestrian retrieval

Fingerprint

Dive into the research topics of 'Improving night-time pedestrian retrieval with distribution alignment and contextual distance'. Together they form a unique fingerprint.

Cite this