TY - GEN
T1 - Matching Pixels Using Co-occurrence Statistics
AU - Kat, Rotal
AU - Jevnisek, Roy
AU - Avidan, Shai
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - We propose a new error measure for matching pixels that is based on co-occurrence statistics. The measure relies on a co-occurrence matrix that counts the number of times pairs of pixel values co-occur within a window. The error incurred by matching a pair of pixels is inversely proportional to the probability that their values co-occur together, and not their color difference. This measure also works with features other than color, e.g. deep features. We show that this improves the state-of-the-art performance of template matching on standard benchmarks. We then propose an embedding scheme that maps the input image to an embedded image such that the Euclidean distance between pixel values in the embedded space resembles the co-occurrence statistics in the original space. This lets us run existing vision algorithms on the embedded images and enjoy the power of co-occurrence statistics for free. We demonstrate this on two algorithms, the Lucas-Kanade image registration and the Kernelized Correlation Filter (KCF) tracker. Experiments show that performance of each algorithm improves by about 10%.
AB - We propose a new error measure for matching pixels that is based on co-occurrence statistics. The measure relies on a co-occurrence matrix that counts the number of times pairs of pixel values co-occur within a window. The error incurred by matching a pair of pixels is inversely proportional to the probability that their values co-occur together, and not their color difference. This measure also works with features other than color, e.g. deep features. We show that this improves the state-of-the-art performance of template matching on standard benchmarks. We then propose an embedding scheme that maps the input image to an embedded image such that the Euclidean distance between pixel values in the embedded space resembles the co-occurrence statistics in the original space. This lets us run existing vision algorithms on the embedded images and enjoy the power of co-occurrence statistics for free. We demonstrate this on two algorithms, the Lucas-Kanade image registration and the Kernelized Correlation Filter (KCF) tracker. Experiments show that performance of each algorithm improves by about 10%.
UR - http://www.scopus.com/inward/record.url?scp=85062851273&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00188
DO - 10.1109/CVPR.2018.00188
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85062851273
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1751
EP - 1759
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -