Multi scale block histogram of template feature for pedestrian detection

Shaopeng Tang; Satoshi Goto

doi:10.1109/ICIP.2010.5654039

Multi scale block histogram of template feature for pedestrian detection

Shaopeng Tang^*, Satoshi Goto

^*Corresponding author for this work

Waseda University

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

4 Citations (Scopus)

Abstract

In this paper, a feature for human detection from still image is proposed. A multi scale block histogram of template feature (MB-HOT) is developed for human detection by extending the template level in the feature extraction. It integrates gray value information and gradient value information, and reflects relationship of three blocks. The feature is extracted from more macrostructures level and could represent more characteristic of human body. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time application.

Original language	English
Title of host publication	Proceedings - International Conference on Image Processing, ICIP
Pages	3493-3496
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2010.5654039
Publication status	Published - 2010
Event	2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong Duration: 2010 Sept 26 → 2010 Sept 29

Other

Other	2010 17th IEEE International Conference on Image Processing, ICIP 2010
City	Hong Kong
Period	10/9/26 → 10/9/29

Keywords

Human detection
Multi-scale block histogram of template

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2010.5654039

Cite this

@inproceedings{42926fe4c45745c08386a5e5e28c9969,

title = "Multi scale block histogram of template feature for pedestrian detection",

abstract = "In this paper, a feature for human detection from still image is proposed. A multi scale block histogram of template feature (MB-HOT) is developed for human detection by extending the template level in the feature extraction. It integrates gray value information and gradient value information, and reflects relationship of three blocks. The feature is extracted from more macrostructures level and could represent more characteristic of human body. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time application.",

keywords = "Human detection, Multi-scale block histogram of template",

author = "Shaopeng Tang and Satoshi Goto",

year = "2010",

doi = "10.1109/ICIP.2010.5654039",

language = "English",

isbn = "9781424479948",

pages = "3493--3496",

booktitle = "Proceedings - International Conference on Image Processing, ICIP",

note = "2010 17th IEEE International Conference on Image Processing, ICIP 2010 ; Conference date: 26-09-2010 Through 29-09-2010",

}

TY - GEN

T1 - Multi scale block histogram of template feature for pedestrian detection

AU - Tang, Shaopeng

AU - Goto, Satoshi

PY - 2010

Y1 - 2010

N2 - In this paper, a feature for human detection from still image is proposed. A multi scale block histogram of template feature (MB-HOT) is developed for human detection by extending the template level in the feature extraction. It integrates gray value information and gradient value information, and reflects relationship of three blocks. The feature is extracted from more macrostructures level and could represent more characteristic of human body. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time application.

AB - In this paper, a feature for human detection from still image is proposed. A multi scale block histogram of template feature (MB-HOT) is developed for human detection by extending the template level in the feature extraction. It integrates gray value information and gradient value information, and reflects relationship of three blocks. The feature is extracted from more macrostructures level and could represent more characteristic of human body. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time application.

KW - Human detection

KW - Multi-scale block histogram of template

UR - http://www.scopus.com/inward/record.url?scp=78651065718&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651065718&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5654039

DO - 10.1109/ICIP.2010.5654039

M3 - Conference contribution

AN - SCOPUS:78651065718

SN - 9781424479948

SP - 3493

EP - 3496

BT - Proceedings - International Conference on Image Processing, ICIP

T2 - 2010 17th IEEE International Conference on Image Processing, ICIP 2010

Y2 - 26 September 2010 through 29 September 2010

ER -

Multi scale block histogram of template feature for pedestrian detection

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this