7 June 2004 Human detection in outdoor video
Author Affiliations +
Abstract
A novel approach for detection of multiple pedestrians from binocular video sequences is reported. First foreground is segmented using an efficient algorithm [3]. Then Ω shape is used to detect head-shoulder contour. We propose a Simplified Fourier Descriptor to represent transformed 1-D shape in phasor notation. A probabilistic model is introduced to evaluate the distribution of SFD in frequency domain. Clues from motion flow and object depth is used to filter out false detection. The proposed system has been tested on several indoor and outdoor sequences. Preliminary experiments have shown that it can robustly detect multiple pedestrians. Experimental results show that the approach is a suitable for real time pedestrian detection.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chunyu Ran, Chunyu Ran, Ji Huang, Ji Huang, Jie Song, Jie Song, } "Human detection in outdoor video", Proc. SPIE 5292, Human Vision and Electronic Imaging IX, (7 June 2004); doi: 10.1117/12.526197; https://doi.org/10.1117/12.526197
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

The CPHD and R RANSAC trackers applied to the VIVID...
Proceedings of SPIE (June 13 2014)
An improved Camshift algorithm for target recognition
Proceedings of SPIE (December 14 2015)
Target velocity measurements from speckled images
Proceedings of SPIE (September 30 1994)
Long Wavelength Radar; Its Purpose And Applications
Proceedings of SPIE (September 08 1976)
Minimalist Light Striping for a Mobile Robot
Proceedings of SPIE (March 01 1990)

Back to Top