DocumentCode :
2838239
Title :
Pose Robust Human Detection in Depth Image Using Four Directional 2D Elliptical Filters
Author :
Kim, Taewan ; Cho, Sangho ; Yoon, Jongmin ; Kim, Daijin
Author_Institution :
Dept. of Comput. Sci. & Eng., Pohang Univ. of Sci. & Technol., Pohang, South Korea
fYear :
2009
fDate :
14-16 Dec. 2009
Firstpage :
130
Lastpage :
135
Abstract :
This paper proposes a pose robust human detection method for sequences of stereo images using four directional 2D elliptical filters (4D2DEFs), which can detect humans regardless of scale and pose. Four 2D elliptical filters with specific orientations are applied to a 2D spatial depth histogram, and threshold values are used to detect human candidates. These candidates are verified by either detecting the face or matching head-shoulder shapes. Experimental results show that human detection using the proposed method outperforms that of using the existing Object Oriented Scale Adaptive Filter (OOSAF) by 15~20%, especially in the case of posed humans.
Keywords :
adaptive filters; object detection; stereo image processing; 2D spatial depth histogram; depth image; directional 2D elliptical filters; object oriented scale adaptive filter; pose robust human detection; stereo images; Biological system modeling; Cameras; Face detection; Filters; Histograms; Humans; Mobile robots; Robustness; Shape; Vehicle detection; Human detection; People detection; elliptical filter; four directional 2d elliptical filter; robust human detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia, 2009. ISM '09. 11th IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-5231-6
Electronic_ISBN :
978-0-7695-3890-7
Type :
conf
DOI :
10.1109/ISM.2009.106
Filename :
5364587
Link To Document :
بازگشت