 |
HAL UPEC - UPEM Portal |  |
 |
Journal articles
Consistency-constrained Non-negative Coding for Tracking
Abstract : A novel visual object tracking method based on consistency-constrained non-negative coding (CNC) is proposed in this paper. For the purpose of computational efficiency, superpixels are firstly extracted from each observed video frame. And then CNC is performed based on those obtained superpixels, where the locality on manifold is preserved by enforcing the temporal and spatial smoothness. The coding result is achieved via an iterative update scheme, which is proved to converge. The proposed method enhances the coding stability and makes the tracker more robust for object tracking. The tracking performance has been evaluated based on ten challenging benchmark sequences involving drastic motion, partial or severe occlusions, large variation in pose, and illumination variation. The experimental results demonstrate the superior performance of our method in comparison with ten state-of-art trackers.
Cited literature [45 references]
https://hal-upec-upem.archives-ouvertes.fr/hal-01624657
Contributor : Chaohui Wang <>
Submitted on : Thursday, October 26, 2017 - 3:58:07 PM
Last modification on : Tuesday, April 28, 2020 - 6:10:35 PM
Long-term archiving on: : Saturday, January 27, 2018 - 2:18:03 PM
Contributor : Chaohui Wang <>
Submitted on : Thursday, October 26, 2017 - 3:58:07 PM
Last modification on : Tuesday, April 28, 2020 - 6:10:35 PM
Long-term archiving on: : Saturday, January 27, 2018 - 2:18:03 PM
File
Consistency-constrained Non-ne...
Files produced by the author(s)