Person detection and re-identification across multiple images and videos obtained via crowdsourcing

Yu Zheng, Zhenhua Chen, Senem Velipasalar, Jian Tang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Person re-identification is indispensable for consistent labeling across different camera views. Most existing studies use static cameras, apply background subtraction to detect moving people, and then focus on the matching of detection results. However, if cameras are mobile or only single image frames (not videos) are available, then background subtraction cannot be used, and human detection needs to be performed on entire images. In this paper, different from most of the existing work, we focus on a crowdsourcing scenario to find and follow person(s) of interest in the collected images/videos. We propose a novel approach combining R-CNN based person detection with the GPU implementation of color histogram and SURF- based re-identification. Moreover, GeoTags are extracted from the EXIF data of videos captured by smart phones, and are displayed on a map together with the time-stamps. All the processing is performed on a GPU, and the average processing time is 5 ms per frame.

Original languageEnglish (US)
Title of host publicationICDSC 2016 - 10th International Conference on Distributed Smart Cameras
PublisherAssociation for Computing Machinery
Pages178-183
Number of pages6
Volume12-15-September-2016
ISBN (Electronic)9781450347860
DOIs
StatePublished - Sep 12 2016
Event10th International Conference on Distributed Smart Cameras, ICDSC 2016 - Paris, France
Duration: Sep 12 2016Sep 15 2016

Other

Other10th International Conference on Distributed Smart Cameras, ICDSC 2016
CountryFrance
CityParis
Period9/12/169/15/16

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'Person detection and re-identification across multiple images and videos obtained via crowdsourcing'. Together they form a unique fingerprint.

  • Cite this

    Zheng, Y., Chen, Z., Velipasalar, S., & Tang, J. (2016). Person detection and re-identification across multiple images and videos obtained via crowdsourcing. In ICDSC 2016 - 10th International Conference on Distributed Smart Cameras (Vol. 12-15-September-2016, pp. 178-183). [2967421] Association for Computing Machinery. https://doi.org/10.1145/2967413.2967421