No Cover Image

Conference contribution 271 views 35 downloads

Detecting humans in RGB-D data with CNNs / Kaiyang Zhou; Adeline Paiement; Majid Mirmehdi

Pages: 306 - 309

Swansea University Author: Paiement, Adeline

DOI (Published version): 10.23919/MVA.2017.7986862

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...

Full description

Published: The Fifteenth IAPR International Conference on Machine Vision Applications 2017
Online Access: http://www.mva-org.jp/mva2017/
URI: https://cronfa.swan.ac.uk/Record/cronfa31971
Tags: Add Tag
No Tags, Be the first to tag this record!
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.
College: College of Science
Start Page: 306
End Page: 309