Title :
Robust object tracking using correspondence voting for smart surveillance visual sensing nodes
Author :
Al Najjar, Mayssaa ; Ghosh, Soumik ; Bayoumi, Magdy
Author_Institution :
Center for Adv. Comput. Studies, Univ. of Louisiana at Lafayette, Lafayette, LA, USA
Abstract :
This paper presents a bottom-up tracking algorithm for surveillance applications where speed and reliability in the case of multiple matches and occlusions are major concerns. The algorithm is divided into four steps. First, moving objects are detected using an accurate hybrid scheme with selective Gaussian modeling. Simple object features balancing speed, reliability, and complexity are then extracted. Objects are matched based on their spatial proximity and feature similarity. Finally, correspondence voting solves multiple match conflicts, segmentation errors, and occlusion cases. This approach is very simple, which makes it suitable for implementation at smart surveillance visual sensing nodes. Moreover, the simulation results demonstrate its robustness in detecting occlusions and correcting segmentation errors without any prior knowledge about the objects models or constraints on the direction of their motion.
Keywords :
object detection; tracking; bottom-up tracking algorithm; correspondence voting; feature similarity; moving object detection; object matching; occlusion detection; robust object tracking; segmentation error correcting; selective Gaussian modeling; smart surveillance visual sensing nodes; surveillance applications; Cameras; Error correction; Layout; Lighting; Monitoring; Object detection; Robustness; Surveillance; Target tracking; Voting; Object tracking; similarity matching;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5414523