DocumentCode :
2985845
Title :
Probabilistic camera hand-off for visual surveillance
Author :
Kim, Jiman ; Kim, Daijin
Author_Institution :
Dept. of Comput. Sci. & Eng., POSTECH, Pohang
fYear :
2008
fDate :
7-11 Sept. 2008
Firstpage :
1
Lastpage :
8
Abstract :
Continuous object tracking for visual surveillance using multiple cameras is a difficult task because several problems must be solved such as the randomness of object movement, the uncertainty of external environment, and the hand-off among cameras. To overcome these problems, a novel continuous object tracking using the probabilistic camera hand-off, which does not require the complicated pre-processing such as the camera calibration, has been proposed as follows. First, we obtain the foreground objects using the SKDA (sequential kernel density approximation)-based background subtraction. Second, we compute the proximity probabilities based on the number of foreground blocks and the angle distance between the camera and the object and find the dominant camera by selecting the highest proximity probability. And we perform a probabilistic camera hand-off using the dominant camera probabilities between two frames. Finally, we estimate the object trajectories using the homography between the dominant camera and the map. Experiment results show that (1) the accuracy and stability of the dominant camera selection using the ratio of foreground blocks and the ratio of the angle distance are more precise than those of using the ratio of foreground block only, (2) the position error between the ground-truth position and the tracked position is approximately 40 cm on average.
Keywords :
image fusion; image sensors; object detection; probability; surveillance; target tracking; angle distance ratio; background subtraction; camera selection accuracy; continuous object tracking; dominant camera probabilities; dominant camera selection stability; foreground objects; homography; object trajectories; probabilistic camera hand-off; proximity probabilities computation; sequential kernel density approximation; shadow elimination; visual surveillance; Brightness; Cameras; Computer science; Histograms; Information analysis; Kernel; Object detection; Power engineering and energy; Surveillance; Uncertainty; Dominant Camera; Probabilistic Camera Hand-off; Sequential Kernel Density Approximation; Shadow Elimination; Trajectory Estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Distributed Smart Cameras, 2008. ICDSC 2008. Second ACM/IEEE International Conference on
Conference_Location :
Stanford, CA
Print_ISBN :
978-1-4244-2664-5
Electronic_ISBN :
978-1-4244-2665-2
Type :
conf
DOI :
10.1109/ICDSC.2008.4635705
Filename :
4635705
Link To Document :
بازگشت