Title :
Tracking Vehicles Through Shadows and Occlusions in Wide-Area Aerial Video
Author :
Aeschliman, Chad ; Park, Jongho ; Kak, Avinash C.
Author_Institution :
Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
Abstract :
We present a new approach for simultaneous tracking and segmentation of multiple targets in low frame rate aerial video. We focus on building an accurate background model that accounts for both global camera motion and moving objects in the scene. We then apply a probabilistic framework for simultaneous tracking and segmentation that incorporates this background model. By using a background model, we are able to track the object through dramatic appearance changes caused by shadows and lighting changes. Furthermore, the incorporation of segmentation into the tracking algorithm reduces the impact of common tracking problems, such as drift and partial occlusion. Results are shown for the Columbus Large Image Format (CLIF) 2007 data set, demonstrating successful tracking under significant occlusions, target appearance changes, and near similar moving objects.
Keywords :
cameras; image motion analysis; image segmentation; object tracking; probability; target tracking; CLIF 2007 data set; Columbus Large Image Format 2007 data set; background model; drift occlusion; global camera motion; low frame rate aerial video; multiple target segmentation; multiple target tracking; object tracking; partial occlusion; probabilistic framework; vehicle tracking; wide-area aerial video; Algorithm design and analysis; Calibration; Global Positioning System; Image segmentation; Target tracking;
Journal_Title :
Aerospace and Electronic Systems, IEEE Transactions on
DOI :
10.1109/TAES.2013.120404