Pedestrian detection of road scenes using depth and intensity features

Sisay Shimelis Gurmu; Min Woo Park; Soon Ki Jung

doi:10.1145/2663761.2664226

Pedestrian detection of road scenes using depth and intensity features

Sisay Shimelis Gurmu
, Min Woo Park
, Soon Ki Jung

Kyungpook National University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we present pedestrian detection method using fusion of intensity and depth features. Complementary fusion of these features significantly boosts the detection performance. Histogram of Oriented gradient (HOG) is applied for feature extraction in both intensity and depth images and trained by linear SVM. Our approach has an advantage over the conventional intensity image based methods, since depth features are robust against illumination, complex background and human pose variations. The experimental result shows that our proposed method has better detection performance.

Original language	English
Title of host publication	Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014
Publisher	Association for Computing Machinery
Pages	144-148
Number of pages	5
ISBN (Electronic)	9781450330602
DOIs	https://doi.org/10.1145/2663761.2664226
State	Published - 5 Oct 2014
Event	2014 Conference on Research in Adaptive and Convergent Systems, RACS 2014 - Towson, United States Duration: 5 Oct 2014 → 8 Oct 2014

Publication series

Name	Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014

Conference

Conference	2014 Conference on Research in Adaptive and Convergent Systems, RACS 2014
Country/Territory	United States
City	Towson
Period	5/10/14 → 8/10/14

Keywords

Depth feature and intensity feature
Detection
Histogram of Oriented gradient (HOG)
Pedestrian

Access to Document

10.1145/2663761.2664226

Cite this

Gurmu, S. S., Park, M. W., & Jung, S. K. (2014). Pedestrian detection of road scenes using depth and intensity features. In Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014 (pp. 144-148). (Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014). Association for Computing Machinery. https://doi.org/10.1145/2663761.2664226

@inproceedings{1dcd8ecf92d547e4b19cce032d29ba0a,

title = "Pedestrian detection of road scenes using depth and intensity features",

abstract = "In this paper, we present pedestrian detection method using fusion of intensity and depth features. Complementary fusion of these features significantly boosts the detection performance. Histogram of Oriented gradient (HOG) is applied for feature extraction in both intensity and depth images and trained by linear SVM. Our approach has an advantage over the conventional intensity image based methods, since depth features are robust against illumination, complex background and human pose variations. The experimental result shows that our proposed method has better detection performance.",

keywords = "Depth feature and intensity feature, Detection, Histogram of Oriented gradient (HOG), Pedestrian",

author = "Gurmu, \{Sisay Shimelis\} and Park, \{Min Woo\} and Jung, \{Soon Ki\}",

note = "Publisher Copyright: {\textcopyright} 2014 ACM.; 2014 Conference on Research in Adaptive and Convergent Systems, RACS 2014 ; Conference date: 05-10-2014 Through 08-10-2014",

year = "2014",

month = oct,

day = "5",

doi = "10.1145/2663761.2664226",

language = "English",

series = "Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014",

publisher = "Association for Computing Machinery",

pages = "144--148",

booktitle = "Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014",

}

Gurmu, SS, Park, MW & Jung, SK 2014, Pedestrian detection of road scenes using depth and intensity features. in Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014. Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014, Association for Computing Machinery, pp. 144-148, 2014 Conference on Research in Adaptive and Convergent Systems, RACS 2014, Towson, United States, 5/10/14. https://doi.org/10.1145/2663761.2664226

Pedestrian detection of road scenes using depth and intensity features. / Gurmu, Sisay Shimelis; Park, Min Woo; Jung, Soon Ki.
Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014. Association for Computing Machinery, 2014. p. 144-148 (Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Pedestrian detection of road scenes using depth and intensity features

AU - Gurmu, Sisay Shimelis

AU - Park, Min Woo

AU - Jung, Soon Ki

PY - 2014/10/5

Y1 - 2014/10/5

N2 - In this paper, we present pedestrian detection method using fusion of intensity and depth features. Complementary fusion of these features significantly boosts the detection performance. Histogram of Oriented gradient (HOG) is applied for feature extraction in both intensity and depth images and trained by linear SVM. Our approach has an advantage over the conventional intensity image based methods, since depth features are robust against illumination, complex background and human pose variations. The experimental result shows that our proposed method has better detection performance.

AB - In this paper, we present pedestrian detection method using fusion of intensity and depth features. Complementary fusion of these features significantly boosts the detection performance. Histogram of Oriented gradient (HOG) is applied for feature extraction in both intensity and depth images and trained by linear SVM. Our approach has an advantage over the conventional intensity image based methods, since depth features are robust against illumination, complex background and human pose variations. The experimental result shows that our proposed method has better detection performance.

KW - Depth feature and intensity feature

KW - Detection

KW - Histogram of Oriented gradient (HOG)

KW - Pedestrian

UR - https://www.scopus.com/pages/publications/84910000335

U2 - 10.1145/2663761.2664226

DO - 10.1145/2663761.2664226

M3 - Conference contribution

AN - SCOPUS:84910000335

T3 - Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014

SP - 144

EP - 148

BT - Proceedings of the 2014 Research in Adaptive and Convergent Systems, RACS 2014

PB - Association for Computing Machinery

T2 - 2014 Conference on Research in Adaptive and Convergent Systems, RACS 2014

Y2 - 5 October 2014 through 8 October 2014

ER -

Pedestrian detection of road scenes using depth and intensity features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this