DocumentCode :
581338
Title :
Fast human detection based on parallelogram haar-like features
Author :
Hoang, Van-Dung ; Vavilin, Andrey ; Jo, Kang-Hyun
Author_Institution :
Sch. of Electr. Eng., Univ. of Ulsan, Ulsan, South Korea
fYear :
2012
fDate :
25-28 Oct. 2012
Firstpage :
4220
Lastpage :
4225
Abstract :
Inspired by a recent image descriptors for object detection, this paper proposed the feature description method based on set of modified Haar-like features which have parallelogram shapes. Using the proposed feature descriptors to develop a rapid detection system for human detection based on cascade structure used for boosting classifier. Specially, human detection in omnidirectional image as well as unwrap omnidirectional to panoramic image were described in this paper. The experimental results showed that the proposed method could produce high accuracy detection rate with lower false positive rate and higher recall rate than Haar-like features, and faster than HOG feature. It is efficiency with different resolutions and poses under a variety conditional such as flare illumination, clutter backgrounds, and so on.
Keywords :
Haar transforms; computational geometry; feature extraction; image classification; object detection; HOG feature; boosting classifier; cascade structure; clutter backgrounds; detection rate; detection system; feature description method; feature descriptors; flare illumination; human detection; image descriptors; object detection; omnidirectional image; panoramic image; parallelogram Haar-like features; parallelogram shapes; positive rate; recall rate; unwrap omnidirectional; Humans; Image resolution; Training; Haar-like feature; Parallelogram; cascade classification; human detection; omnidirectional image; panoramic image;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society
Conference_Location :
Montreal, QC
ISSN :
1553-572X
Print_ISBN :
978-1-4673-2419-9
Electronic_ISBN :
1553-572X
Type :
conf
DOI :
10.1109/IECON.2012.6389212
Filename :
6389212
Link To Document :
بازگشت