Radar-based road-traffic monitoring in urban environments
Digital Signal Processing
Online learned discriminative part-based appearance models for multi-human tracking
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
GMCP-Tracker: global multi-object tracking using generalized minimum clique graphs
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
To track or to detect? an ensemble framework for optimal selection
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
(MP)2T: multiple people multiple parts tracker
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Re-identification of pedestrians in crowds using dynamic time warping
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Exploiting pedestrian interaction via global optimization and social behaviors
Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
Accurate pedestrian counting system based on local features
PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
Tracking with a mixed continuous-discrete Conditional Random Field
Computer Vision and Image Understanding
Multi-target tracking on confidence maps: An application to people tracking
Computer Vision and Image Understanding
Pattern Recognition Letters
Multiple human tracking system for unpredictable trajectories
Machine Vision and Applications
Multimedia Tools and Applications
| Hi-index | 0.00 |
The majority of existing pedestrian trackers concentrate on maintaining the identities of targets, however systems for remote biometric analysis or activity recognition in surveillance video often require stable bounding-boxes around pedestrians rather than approximate locations. We present a multi-target tracking system that is designed specifically for the provision of stable and accurate head location estimates. By performing data association over a sliding window of frames, we are able to correct many data association errors and fill in gaps where observations are missed. The approach is multi-threaded and combines asynchronous HOG detections with simultaneous KLT tracking and Markov-Chain Monte-Carlo Data Association (MCM-CDA) to provide guaranteed real-time tracking in high definition video. Where previous approaches have used ad-hoc models for data association, we use a more principled approach based on a Minimal Description Length (MDL) objective which accurately models the affinity between observations. We demonstrate by qualitative and quantitative evaluation that the system is capable of providing precise location estimates for large crowds of pedestrians in real-time. To facilitate future performance comparisons, we make a new dataset with hand annotated ground truth head locations publicly available.