Detecting humans in RGB-D data with CNNs

Kaiyang Zhou; Adeline Paiement; Majid Mirmehdi

doi:10.23919/MVA.2017.7986862

Detecting humans in RGB-D data with CNNs

Kaiyang Zhou, Adeline Paiement, Majid Mirmehdi

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-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 language	English
Title of host publication	Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
Publisher	IEEE
Pages	306-309
Number of pages	4
ISBN (Electronic)	9784901122160
ISBN (Print)	9781538604953
DOIs	https://doi.org/10.23919/MVA.2017.7986862
Publication status	Published - May 2017
Event	15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan Duration: 8 May 2017 → 12 May 2017 https://ieeexplore.ieee.org/xpl/conhome/7981294/proceeding

Publication series

Name	Proceedings of the IAPR International Conference on Machine Vision Applications, MVA

Conference

Conference	15th IAPR International Conference on Machine Vision Applications, MVA 2017
Country/Territory	Japan
City	Nagoya
Period	8/05/17 → 12/05/17
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7981294/proceeding

Access to Document

10.23919/MVA.2017.7986862

Cite this

@inproceedings{91f419011e9b40b58bb732c94934def1,

title = "Detecting humans in RGB-D data with CNNs",

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.",

author = "Kaiyang Zhou and Adeline Paiement and Majid Mirmehdi",

note = "Publisher Copyright: {\textcopyright} 2017 MVA Organization All Rights Reserved.; 15th IAPR International Conference on Machine Vision Applications, MVA 2017 ; Conference date: 08-05-2017 Through 12-05-2017",

year = "2017",

month = may,

doi = "10.23919/MVA.2017.7986862",

language = "English",

isbn = "9781538604953",

series = "Proceedings of the IAPR International Conference on Machine Vision Applications, MVA",

publisher = "IEEE",

pages = "306--309",

booktitle = "Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/7981294/proceeding",

}

Zhou, K, Paiement, A & Mirmehdi, M 2017, Detecting humans in RGB-D data with CNNs. in Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Proceedings of the IAPR International Conference on Machine Vision Applications, MVA, IEEE, pp. 306-309, 15th IAPR International Conference on Machine Vision Applications, MVA 2017, Nagoya, Japan, 8/05/17. https://doi.org/10.23919/MVA.2017.7986862

Detecting humans in RGB-D data with CNNs. / Zhou, Kaiyang; Paiement, Adeline; Mirmehdi, Majid.
Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. IEEE, 2017. p. 306-309 (Proceedings of the IAPR International Conference on Machine Vision Applications, MVA).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Detecting humans in RGB-D data with CNNs

AU - Zhou, Kaiyang

AU - Paiement, Adeline

AU - Mirmehdi, Majid

PY - 2017/5

Y1 - 2017/5

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85027854712&partnerID=8YFLogxK

U2 - 10.23919/MVA.2017.7986862

DO - 10.23919/MVA.2017.7986862

M3 - Conference proceeding

AN - SCOPUS:85027854712

SN - 9781538604953

T3 - Proceedings of the IAPR International Conference on Machine Vision Applications, MVA

SP - 306

EP - 309

BT - Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

PB - IEEE

T2 - 15th IAPR International Conference on Machine Vision Applications, MVA 2017

Y2 - 8 May 2017 through 12 May 2017

ER -

Detecting humans in RGB-D data with CNNs

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this