Browsing by Author "Alatan, A. A."

Now showing 1 - 3 of 3

Metadata only
Occlusion-aware 3D multiple object tracker with two cameras for visual surveillance
(IEEE, 2014) Topçu, O.; Alatan, A. A.; Ercan, Ali Özer; Electrical & Electronics Engineering; ERCAN, Ali Özer
An occlusion-aware multiple deformable object tracker for visual surveillance from two cameras is presented. Each object is tracked by a separate particle filter tracker, which is initiated upon detection of a new person and terminated when s/he leaves the scene. Objects are considered as 3D points at their centre of masses as if their mass density is uniform. Point objects and corresponding silhouette centroids in two views together with the epipolar geometry they satisfy resulted in a practical tracking methodology. An occlusion filter is described, that provides the tracker filters conditional occlusion probabilities of the objects, given their estimated positions. Advances over the previous work; in the computation of conditional occlusion probabilities, in incorporation of these probabilities in the particle filter, and in maintaining tracking of separating objects after long periods of moving close-by, are presented on PETS 2006, PETS 2009 and EPFL datasets.
Metadata only
Rao-Blackwell parçacık süzgeci ile 3 boyutlu insan takibi
(IEEE, 2014) Topçu, O.; Orguner, U.; Alatan, A. A.; Ercan, Ali Özer; Electrical & Electronics Engineering; ERCAN, Ali Özer
Visual tracking has an important place among computer vision applications. Visual tracking with particle filters is a well-known methodology. The performance of particle filters is dependent on efficient sampling of the state space, which in turn, is dependent on number of particles. In this paper, Rao-Blackwell technique is applied to particle filters to improve sampling efficiency. Both algorithms are applied to people tracking problem. Under the same circumstances, the resulting algorithm is demonstrated to perform better than the original algorithm via experiments on the PETS2009 benchmark dataset.
Metadata only
Recovery of temporal synchronization error through online 3D tracking with two cameras
(ACM, 2014) Topçu, O.; Ercan, Ali Özer; Alatan, A. A.; Electrical & Electronics Engineering; ERCAN, Ali Özer
Multiple object tracking within a network of cameras with overlapping fields of views has gained interest. The acquisition of images in an asynchronous manner hinders the practical implementation of such systems. Most of the previous work reported tests over short intervals, leaving the performance degradation due to asynchronous image acquisition unknown. In this work, we propose an online method to recover the synchronization error while tracking objects. The recovered error is fed back to trackers so as to restore their performance. The time synchronization error is measured by the mismatch in the epipolar constraint between the two cameras. We show that successful recovery of the synchronization error is possible when its product with the object motion speeds are within some limits.