Pedestrian Tracking by Associating Tracklets using Detection Residuals

Singh, Vivek Kumar; Wu, Bo; Nevatia, Ramakant

doi:10.1109/wmvc.2008.4544058

Cited by 44 publications

(30 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our multi-target tracking formulation follows the philosophy of [30], where tracks are obtained by associating corresponding tracklets. Unlike other methods, we leverage the contextual information provided by interaction activities to make target association more robust.…”

Section: Multiple Target Trackingmentioning

confidence: 99%

A Unified Framework for Multi-target Tracking and Collective Activity Recognition

Choi

Savarese

2012

Lecture Notes in Computer Science

273

270

View full text Add to dashboard Cite

Abstract. We present a coherent, discriminative framework for simultaneously tracking multiple people and estimating their collective activities. Instead of treating the two problems separately, our model is grounded in the intuition that a strong correlation exists between a person's motion, their activity, and the motion and activities of other nearby people. Instead of directly linking the solutions to these two problems, we introduce a hierarchy of activity types that creates a natural progression that leads from a specific person's motion to the activity of the group as a whole. Our model is capable of jointly tracking multiple people, recognizing individual activities (atomic activities), the interactions between pairs of people (interaction activities), and finally the behavior of groups of people (collective activities). We also propose an algorithm for solving this otherwise intractable joint inference problem by combining belief propagation with a version of the branch and bound algorithm equipped with integer programming. Experimental results on challenging video datasets demonstrate our theoretical claims and indicate that our model achieves the best collective activity classification results to date.

show abstract

Section: Multiple Target Trackingmentioning

confidence: 99%

A Unified Framework for Multi-target Tracking and Collective Activity Recognition

Choi

Savarese

2012

Lecture Notes in Computer Science

273

270

View full text Add to dashboard Cite

show abstract

“…The tracklet association problem can be formulated as one of optimally connecting a bipartite graph [33], [34], [35], [36], [37] using the Hungarian algorithm. The main differences between these algorithms reside in the way the tracklets are constructed and the similarity measure between them.…”

Section: Multiple Target Trackingmentioning

confidence: 99%

“…Tracklets have been extensively used for people tracking [34], [36] and they are usually created on the basis of appearance being preserved over consecutive frames. In this work, we assume that appearance information may be unavailable over long periods of time and we therefore create our tracklets without reference to it.…”

Section: Grouping Nodes Into Trackletsmentioning

confidence: 99%

Multi-Commodity Network Flow for Tracking Multiple People

Shitrit

Berclaz

Fleuret

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

155

160

View full text Add to dashboard Cite

Abstract-In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a multi-commodity network flow problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being exploitable from frame to frame. Furthermore, our algorithm lends itself to a real-time implementation. We validate our approach on three publicly available datasets that contain long and complex sequences, the APIDIS basketball dataset, the ISSIA soccer dataset and the PETS'09 pedestrian dataset. We also demonstrate its performance on a newer basketball dataset that features complete world championship basketball matches. In all cases, our approach preserves identity better than state-of-the-art tracking algorithms.

show abstract

“…Tracklets were explored in previous works [4,23,16] mainly for the purpose of connecting them into complete trajectories for better tracking or human action recognition but not for learning semantic regions or clustering trajectories. Our approach does not require first obtaining complete trajectories from tracklets.…”

Section: Related Workmentioning

confidence: 99%