TY - GEN
T1 - Evaluation of super-voxel methods for early video processing
AU - Xu, Chenliang
AU - Corso, Jason J.
PY - 2012
Y1 - 2012
N2 - Supervoxel segmentation has strong potential to be incorporated into early video analysis as superpixel segmentation has in image analysis. However, there are many plausible supervoxel methods and little understanding as to when and where each is most appropriate. Indeed, we are not aware of a single comparative study on supervoxel segmentation. To that end, we study five supervoxel algorithms in the context of what we consider to be a good supervoxel: namely, spatiotemporal uniformity, object/region boundary detection, region compression and parsimony. For the evaluation we propose a comprehensive suite of 3D volumetric quality metrics to measure these desirable supervoxel characteristics. We use three benchmark video data sets with a variety of content-types and varying amounts of human annotations. Our findings have led us to conclusive evidence that the hierarchical graph-based and segmentation by weighted aggregation methods perform best and almost equally-well on nearly all the metrics and are the methods of choice given our proposed assumptions.
AB - Supervoxel segmentation has strong potential to be incorporated into early video analysis as superpixel segmentation has in image analysis. However, there are many plausible supervoxel methods and little understanding as to when and where each is most appropriate. Indeed, we are not aware of a single comparative study on supervoxel segmentation. To that end, we study five supervoxel algorithms in the context of what we consider to be a good supervoxel: namely, spatiotemporal uniformity, object/region boundary detection, region compression and parsimony. For the evaluation we propose a comprehensive suite of 3D volumetric quality metrics to measure these desirable supervoxel characteristics. We use three benchmark video data sets with a variety of content-types and varying amounts of human annotations. Our findings have led us to conclusive evidence that the hierarchical graph-based and segmentation by weighted aggregation methods perform best and almost equally-well on nearly all the metrics and are the methods of choice given our proposed assumptions.
UR - http://www.scopus.com/inward/record.url?scp=84866688605&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866688605&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6247802
DO - 10.1109/CVPR.2012.6247802
M3 - Conference contribution
AN - SCOPUS:84866688605
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1202
EP - 1209
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -