Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering.
IEEE Trans Pattern Anal Mach Intell
; 2018 Oct 16.
Article
in En
| MEDLINE
| ID: mdl-30334779
ABSTRACT
Models for computer vision are commonly defined either w.r.t. low-level concepts such as pixels that are to be grouped, or w.r.t. high-level concepts such as semantic objects that are to be detected and tracked. Combining bottom-up grouping with top-down detection and tracking, although highly desirable, is a challenging problem. We state this joint problem as a co-clustering problem that is principled and tractable by existing algorithms. We demonstrate the effectiveness of this approach by combining bottom-up motion segmentation by grouping of point trajectories with high-level multiple object tracking by clustering of bounding boxes. We show that solving the joint problem is beneficial at the low-level, in terms of the FBMS59 motion segmentation benchmark, and at the high-level, in terms of the Multiple Object Tracking benchmarks MOT15, MOT16 and the MOT17 challenge, and is state-of-the-art in some metrics.
Full text:
1
Database:
MEDLINE
Language:
En
Journal:
IEEE Trans Pattern Anal Mach Intell
Journal subject:
INFORMATICA MEDICA
Year:
2018
Type:
Article