CUED Publications database

Bi-label propagation for generic multiple object tracking

Luo, W and Kim, TK and Stenger, B and Zhao, X and Cipolla, R (2014) Bi-label propagation for generic multiple object tracking. In: UNSPECIFIED pp. 1290-1297..

Full text not available from this repository.


© 2014 IEEE. In this paper, we propose a label propagation framework to handle the multiple object tracking (MOT) problem for a generic object type (cf. pedestrian tracking). Given a target object by an initial bounding box, all objects of the same type are localized together with their identities. We treat this as a problem of propagating bi-labels, i.e. a binary class label for detection and individual object labels for tracking. To propagate the class label, we adopt clustered Multiple Task Learning (cMTL) while enforcing spatio-temporal consistency and show that this improves the performance when given limited training data. To track objects, we propagate labels from trajectories to detections based on affinity using appearance, motion, and context. Experiments on public and challenging new sequences show that the proposed method improves over the current state of the art on this task.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:28
Last Modified: 22 May 2018 06:57