Title :
A Novel Approach to Analyzing Object Motion Behavior
Author :
Deng, Yali ; Wu, Lifang ; He, Yulong
Author_Institution :
Sch. of Electron. Inf. & Control Eng., Beijing Univ. of Technol., Beijing, China
Abstract :
Object behavior analysis is important in traffic behavior analysis. In this paper, we propose a novel approach to analyzing object motion behavior. First we build the background probability model, then background subtraction, binarization, median filtering and morphological operation are implemented in sequence to obtain the candidate regions. Next, the sum of gradient is used for shadow removal. In the candidate region the true object is detect and their behavior is analyzed. The experimental results confirm the efficiency of proposed approach.
Keywords :
hidden feature removal; median filters; object detection; probability; traffic engineering computing; background probability model; background subtraction; binarization; candidate region; median filtering; morphological operation; object motion behavior analysis; shadow removal; sum of gradient; traffic behavior analysis; Algorithm design and analysis; Analytical models; Educational institutions; Filtering; Image edge detection; Morphological operations; Vehicles; object behavior analysis; probability model; shadow removal; vehicle;
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2012 Eighth International Conference on
Conference_Location :
Piraeus
Print_ISBN :
978-1-4673-1741-2
DOI :
10.1109/IIH-MSP.2012.102