Title :
Event detection based on "common fate" principle: application to vehicles detection from aerial sequences of road traffic
Author :
Kaâniche, Khaled ; Vasseur, Pascal
Author_Institution :
Center of Robotics & Electr. Eng. & Autom., Univ. of Picardie Jules Verne, Amiens, France
Abstract :
This paper introduces a vision system for road traffic surveillance from sequences acquired from an unmanned aerial vehicle (UAV). During the navigation of the UAV, the vision system acquires sequences which are treated in order to detect vehicles. The dynamic behavior of the UAV-camera system makes a fixed background impossible : we present a new approach based on the "common fate" principle : image primitives which have the same type of movement (or displacement) are grouped. The detection of vehicles is then based on the spatiotemporal grouping of primitives formulated as a normalized cuts problem. A verification step based on the Dempster-Shafer theory is also proposed in order to recognize vehicles.
Keywords :
image sequences; inference mechanisms; remotely operated vehicles; road traffic; Dempster-Shafer theory; aerial sequences; common fate principle; event detection; road traffic surveillance; vehicles detection; Cameras; Equations; Event detection; Image edge detection; Machine vision; Road vehicles; Surveillance; Unmanned aerial vehicles; Vehicle detection; Vehicle dynamics; Aerial Video Analysis; Dempster-Shafer Theory; Matching Process; Perceptual Organization; Spatio-Temporal Grouping;
Conference_Titel :
Image Processing, 2005. ICIP 2005. IEEE International Conference on
Print_ISBN :
0-7803-9134-9
DOI :
10.1109/ICIP.2005.1529948