TY - GEN
T1 - Robust fragments-based tracking using the integral histogram
AU - Adam, Amit
AU - Rivlin, Ehud
AU - Shimshoni, Ilan
PY - 2006
Y1 - 2006
N2 - We present a novel algorithm (which we call "Frag-Track")for tracking an object in a video sequence. The template object is represented by multiple image fragments or patches. The patches are arbitrary and are not based on an object model (in contrast with traditional use of model-based parts e.g. limbs and torso in human tracking). Every patch votes on the possible positions and scales of the object in the current frame, by comparing its histogram with the corresponding image patch histogram. We then minimize a robust statistic in order to combine the vote maps of the multiple patches. A key tool enabling the application of our algorithm to tracking is the integral histogram data structure [18]. Its use allows to extract histograms of multiple rectangular regions in the image in a very efficient manner. Our algorithm overcomes several difficulties which cannot be handled by traditional histogram-based algorithms [8, 6]. First, by robustly combining multiple patch votes, we are able to handle partial occlusions or pose change. Second, the geometric relations between the template patches allow us to take into account the spatial distribution of the pixel intensities - information which is lost in traditional histogram-based algorithms. Third, as noted by [18], tracking large targets has the same computational cost as tracking small targets. We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (non-color) information).
AB - We present a novel algorithm (which we call "Frag-Track")for tracking an object in a video sequence. The template object is represented by multiple image fragments or patches. The patches are arbitrary and are not based on an object model (in contrast with traditional use of model-based parts e.g. limbs and torso in human tracking). Every patch votes on the possible positions and scales of the object in the current frame, by comparing its histogram with the corresponding image patch histogram. We then minimize a robust statistic in order to combine the vote maps of the multiple patches. A key tool enabling the application of our algorithm to tracking is the integral histogram data structure [18]. Its use allows to extract histograms of multiple rectangular regions in the image in a very efficient manner. Our algorithm overcomes several difficulties which cannot be handled by traditional histogram-based algorithms [8, 6]. First, by robustly combining multiple patch votes, we are able to handle partial occlusions or pose change. Second, the geometric relations between the template patches allow us to take into account the spatial distribution of the pixel intensities - information which is lost in traditional histogram-based algorithms. Third, as noted by [18], tracking large targets has the same computational cost as tracking small targets. We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (non-color) information).
UR - http://www.scopus.com/inward/record.url?scp=33845596140&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2006.256
DO - 10.1109/CVPR.2006.256
M3 - Conference contribution
AN - SCOPUS:33845596140
SN - 0769525970
SN - 9780769525976
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 798
EP - 805
BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Y2 - 17 June 2006 through 22 June 2006
ER -