We won the CVPR 2017 Multiple-Object Tracking Challenge

Our approach

Motion Segmentation and Multiple Object Tracking by Correlation Clustering, Margret Keuper, Siyu Tang Bjoern Andres, Thomas Brox and Bernt Schiele

won the

CVPR 2017 Multiple-Object Tracking Challenge.

A detailed method description is given in:  M. Keuper, S. Tang, Y. Zhongjie, B. Andres, T. Brox, B. Schiele. A multi-cut formulation for joint segmentation and tracking of multiple objects. In arXiv preprint arXiv:1607.06317, 2016.

 

Abstract: Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion
trajectory segmentation and multi-target tracking scenarios. Both tasks benefit from decomposing a graphical model
into an optimal number of connected components based on attractive and repulsive pairwise terms. The two tasks are
formulated on different levels of granularity and, accordingly, leverage mostly local information for motion segmentation and mostly high-level information for multi-target tracking. In this paper we argue that point trajectories and their local relationships can contribute to the high-level task of multi-target tracking and also argue that high-level cues from object detection and tracking are helpful to solve motion segmentation. We propose a joint graphical model for point trajectories and object detections whose Multicuts are solutions to motion segmentation and multi-target tracking problems at once.