Bi-label Propagation for Generic Multiple Object Tracking

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...

Full description

Saved in:
Bibliographic Details
Published in:2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1290 - 1297
Main Authors: Wenhan Luo, Tae-kyun Kim, Stenger, Bjorn, Xiaowei Zhao, Cipolla, Roberto
Format: Conference Proceeding Journal Article
Language:English
Published: IEEE 01.06.2014
Subjects:
clustered multi-task learning
Computer vision
Context
Detectors
Hidden Markov models
Labels
Multiple object tracking
Object detection
Pattern recognition
Propagation
State of the art
Tasks
Tracking
Training
Training data
Trajectories
Trajectory
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2014.168