Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle

Min Wang; Jian Qing Wang; Hong Qiao; Xian Bin Cao

doi:10.1109/IVS.2009.5164464

Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle

Min Wang
, Jian Qing Wang
, Hong Qiao
, Xian Bin Cao

CAS - Institute of Automation
University of Manchester
University of Science and Technology of China
Anhui Province Key Laboratory of Software in Computing and Communication

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

1 Scopus citations

Abstract

Shape Context algorithm is a recently proposed good method for object recognition. It is robust under small geometrical distortions and occlusion, invariant under scaling, translation, and change of illumination. However, because of its computational complexity, this algorithm is not suitable for online recognition. In this paper, we proposed an improved Shape Context algorithm which introduces an optimal hierarchical structure and gives new reference points selection criteria. Compared with the original Shape Context algorithm, the improved algorithm keeps the recognition accuracy and reduces the computational cost greatly. The good experimental results reveal that, this new algorithm can be applied to the pedestrian detection system online, which is an important research topic in intelligent transportation.

Original language	English
Title of host publication	2009 IEEE Intelligent Vehicles Symposium
Pages	1260-1264
Number of pages	5
DOIs	https://doi.org/10.1109/IVS.2009.5164464
State	Published - 2009
Externally published	Yes
Event	2009 IEEE Intelligent Vehicles Symposium - Xi'an, China Duration: 3 Jun 2009 → 5 Jun 2009

Publication series

Name	IEEE Intelligent Vehicles Symposium, Proceedings

Conference

Conference	2009 IEEE Intelligent Vehicles Symposium
Country/Territory	China
City	Xi'an
Period	3/06/09 → 5/06/09

Access to Document

10.1109/IVS.2009.5164464

Cite this

@inproceedings{d8bf4614e2944827a964d7b417a62109,

title = "Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle",

abstract = "Shape Context algorithm is a recently proposed good method for object recognition. It is robust under small geometrical distortions and occlusion, invariant under scaling, translation, and change of illumination. However, because of its computational complexity, this algorithm is not suitable for online recognition. In this paper, we proposed an improved Shape Context algorithm which introduces an optimal hierarchical structure and gives new reference points selection criteria. Compared with the original Shape Context algorithm, the improved algorithm keeps the recognition accuracy and reduces the computational cost greatly. The good experimental results reveal that, this new algorithm can be applied to the pedestrian detection system online, which is an important research topic in intelligent transportation.",

author = "Min Wang and Wang, \{Jian Qing\} and Hong Qiao and Cao, \{Xian Bin\}",

year = "2009",

doi = "10.1109/IVS.2009.5164464",

language = "英语",

isbn = "9781424435043",

series = "IEEE Intelligent Vehicles Symposium, Proceedings",

pages = "1260--1264",

booktitle = "2009 IEEE Intelligent Vehicles Symposium",

note = "2009 IEEE Intelligent Vehicles Symposium ; Conference date: 03-06-2009 Through 05-06-2009",

}

Wang, M, Wang, JQ, Qiao, H & Cao, XB 2009, Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle. in 2009 IEEE Intelligent Vehicles Symposium., 5164464, IEEE Intelligent Vehicles Symposium, Proceedings, pp. 1260-1264, 2009 IEEE Intelligent Vehicles Symposium, Xi'an, China, 3/06/09. https://doi.org/10.1109/IVS.2009.5164464

Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle. / Wang, Min; Wang, Jian Qing; Qiao, Hong et al.
2009 IEEE Intelligent Vehicles Symposium. 2009. p. 1260-1264 5164464 (IEEE Intelligent Vehicles Symposium, Proceedings).

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

TY - GEN

T1 - Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle

AU - Wang, Min

AU - Wang, Jian Qing

AU - Qiao, Hong

AU - Cao, Xian Bin

PY - 2009

Y1 - 2009

N2 - Shape Context algorithm is a recently proposed good method for object recognition. It is robust under small geometrical distortions and occlusion, invariant under scaling, translation, and change of illumination. However, because of its computational complexity, this algorithm is not suitable for online recognition. In this paper, we proposed an improved Shape Context algorithm which introduces an optimal hierarchical structure and gives new reference points selection criteria. Compared with the original Shape Context algorithm, the improved algorithm keeps the recognition accuracy and reduces the computational cost greatly. The good experimental results reveal that, this new algorithm can be applied to the pedestrian detection system online, which is an important research topic in intelligent transportation.

AB - Shape Context algorithm is a recently proposed good method for object recognition. It is robust under small geometrical distortions and occlusion, invariant under scaling, translation, and change of illumination. However, because of its computational complexity, this algorithm is not suitable for online recognition. In this paper, we proposed an improved Shape Context algorithm which introduces an optimal hierarchical structure and gives new reference points selection criteria. Compared with the original Shape Context algorithm, the improved algorithm keeps the recognition accuracy and reduces the computational cost greatly. The good experimental results reveal that, this new algorithm can be applied to the pedestrian detection system online, which is an important research topic in intelligent transportation.

UR - https://www.scopus.com/pages/publications/70449591804

U2 - 10.1109/IVS.2009.5164464

DO - 10.1109/IVS.2009.5164464

M3 - 会议稿件

AN - SCOPUS:70449591804

SN - 9781424435043

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 1260

EP - 1264

BT - 2009 IEEE Intelligent Vehicles Symposium

T2 - 2009 IEEE Intelligent Vehicles Symposium

Y2 - 3 June 2009 through 5 June 2009

ER -

Improved shape context algorithm for online fast recognition - An application in pedestrian detection from a moving vehicle

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this