Motion segmentation & multiple object tracking by correlation co-clustering

Keuper, Margret ; Tang, Siyu ; Andres, Björn ; Brox, Thomas ; Schiele, Bernt

Document Type: Article
Year of publication: 2020
The title of a journal, publication series: IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume: 42
Issue number: 1
Page range: 140-153
Place of publication: New York, NY
Publishing house: IEEE Computer Society
ISSN: 0162-8828 , 2160-9292 , 1939-3539
Publication language: English
Institution: School of Business Informatics and Mathematics > Bildverarbeitung (Juniorprofessur) (Keuper 2017-)
Subject: 004 Computer science, internet
Keywords (English): Clustering algorithms , Computer vision , Correlation , Motion segmentation , Object tracking , Trajectory
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.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Metadata export


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item