Multi-Pose Multi-Target Tracking for Activity Understanding
Abstract
We evaluate the performance of a widely used tracking- by-detection and data association multi-target tracking pipeline applied to an activity-rich video dataset. In contrast to traditional work on multi-target pedestrian tracking where people are largely assumed to be upright, we use an activity-rich dataset that includes a wide range of body poses derived from actions such as picking up an object, riding a bike, digging with a shovel, and sitting down. For each step of the tracking pipeline, we identify key limitations and offer practical modifications that enable robust multi-target tracking over a range of activities. We show that the use of multiple posture-specific detectors and an appearance-based data association post-processing step can generate non-fragmented trajectories essential for holistic activity understanding.
This research was sponsored by the Army Research Laboratory and was accomplished under Cooperative Agree- ment Number W911NF-10-2-0061.
BibTeX
@workshop{Izadinia-2013-7653,author = {Hamid Izadinia and Varun Ramakrishna and Kris M. Kitani and Daniel Huber},
title = {Multi-Pose Multi-Target Tracking for Activity Understanding},
booktitle = {Proceedings of IEEE Workshop on the Applications of Computer Vision (WACV '13)},
year = {2013},
month = {January},
pages = {385 - 390},
keywords = {Multi-Target Tracking, Activity Recognition},
}