Proceedings Article | 4 May 2012
David Miller, Aditya Natraj, Ryler Hockenbury, Katherine Dunn, Michael Sheffler, Kevin Sullivan
KEYWORDS: Roads, Video, Automatic tracking, Optical tracking, Inspection, Machine learning, Cameras, Visualization, Data modeling, Ranging
We describe a comprehensive system for learning to identify suspicious vehicle tracks from wide-area motion
(WAMI) video. First, since the road network for the scene of interest is assumed unknown, agglomerative
hierarchical clustering is applied to all spatial vehicle measurements, resulting in spatial cells that largely capture
individual road segments. Next, for each track, both at the cell (speed, acceleration, azimuth) and track (range,
total distance, duration) levels, extreme value feature statistics are both computed and aggregated, to form
summary (p-value based) anomaly statistics for each track. Here, to fairly evaluate tracks that travel across
different numbers of spatial cells, for each cell-level feature type, a single (most extreme) statistic is chosen, over
all cells traveled. Finally, a novel active learning paradigm, applied to a (logistic regression) track classifier, is
invoked to learn to distinguish suspicious from merely anomalous tracks, starting from anomaly-ranked track
prioritization, with ground-truth labeling by a human operator. This system has been applied to WAMI video
data (ARGUS), with the tracks automatically extracted by a system developed in-house at Toyon Research
Corporation. Our system gives promising preliminary results in highly ranking as suspicious aerial vehicles,
dismounts, and traffic violators, and in learning which features are most indicative of suspicious tracks.
