Detecting humans in RGB-D data with CNNs

Kaiyang Zhou, Adeline Paiement, Majid Mirmehdi

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

24 Citations (Scopus)

Abstract

We address the problem of people detection in RGB-D data where we leverage depth information to develop a region-of-interest (ROI) selection method that provides proposals to two color and depth CNNs. To combine the detections produced by the two CNNs, we propose a novel fusion approach based on the characteristics of depth images. We also present a new depth-encoding scheme, which not only encodes depth images into three channels but also enhances the information for classification. We conduct experiments on a publicly available RGB-D people dataset and show that our approach outperforms the baseline models that only use RGB data.

Original languageEnglish
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
PublisherIEEE
Pages306-309
Number of pages4
ISBN (Electronic)9784901122160
ISBN (Print)9781538604953
DOIs
Publication statusPublished - May 2017
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: 8 May 201712 May 2017
https://ieeexplore.ieee.org/xpl/conhome/7981294/proceeding

Publication series

NameProceedings of the IAPR International Conference on Machine Vision Applications, MVA

Conference

Conference15th IAPR International Conference on Machine Vision Applications, MVA 2017
Country/TerritoryJapan
CityNagoya
Period8/05/1712/05/17
Internet address

Scopus Subject Areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Detecting humans in RGB-D data with CNNs'. Together they form a unique fingerprint.

Cite this