Title :
New moving human detecting and tracking algorithm
Author :
Li, Ling ; Hu, Wentao
Author_Institution :
Coll. of Math. & Phys., Chongqing Univ. of Posts & Telecommun., Chongqing, China
Abstract :
For the inevitable factors in the practical scene such as illumination chance and background interference, a new method is obtained to achieve the detection of human movement in this paper. This algorithm can remove most of the shadow and apply Gaussian filter to reduce interference. Then the moving targets under different conditions can be accurately tracked by combination of tracking algorithm and the detecting human body. The related experiments show that this method can eliminate the shadows, and it has the advantage of high anti-noise performance.
Keywords :
Gaussian processes; filtering theory; image motion analysis; interference; optical tracking; Gaussian filter; anti-noise performance; background interference; human detecting algorithm; human movement detection; human tracking algorithm; illumination chance; moving targets; Humans; Image color analysis; Image edge detection; Noise; Pixel; Target tracking; adaptive background update; human movement tracking; shadow elimination;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5648126