Breaking the Chain: Liberation from the Temporal Markov Assumption for Tracking Human Poses

Ryan Tokola, Wongun Choi, Silvio Savarese; The IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2424-2431

Abstract


We present an approach to multi-target tracking that has expressive potential beyond the capabilities of chainshaped hidden Markov models, yet has significantly reduced complexity. Our framework, which we call tracking-byselection, is similar to tracking-by-detection in that it separates the tasks of detection and tracking, but it shifts temporal reasoning from the tracking stage to the detection stage. The core feature of tracking-by-selection is that it reasons about path hypotheses that traverse the entire video instead of a chain of single-frame object hypotheses. A traditional chain-shaped tracking-by-detection model is only able to promote consistency between one frame and the next. In tracking-by-selection, path hypotheses exist across time, and encouraging long-term temporal consistency is as simple as rewarding path hypotheses with consistent image features. One additional advantage of tracking-by-selection is that it results in a dramatically simplified model that can be solved exactly. We adapt an existing tracking-by-detection model to the tracking-by-selection framework, and show improved performance on a challenging dataset (introduced in [18]).

Related Material


[pdf]
[bibtex]
@InProceedings{Tokola_2013_ICCV,
author = {Tokola, Ryan and Choi, Wongun and Savarese, Silvio},
title = {Breaking the Chain: Liberation from the Temporal Markov Assumption for Tracking Human Poses},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}