Abstract

Advanced surveillance systems for behavior recognition in outdoor traffic scenes depend strongly on the particular configuration of the scenario. Scene-independent tra jectory analysis techniques sta- tistically infer semantics in locations where motion occurs, and such inferences are typically limited to abnormality. Thus, it is interesting to design contributions that automatically categorize more specific se- mantic regions. State-of-the-art approaches for unsupervised scene la- beling exploit tra jectory data to segment areas like sources, sinks, or waiting zones. Our method, in addition, incorporates scene-independent knowledge to assign more meaningful labels like crosswalks, sidewalks, or parking spaces. First, a spatiotemporal scene model is obtained from tra jectory analysis. Subsequently, a so-called GI-MRF inference process reinforces spatial coherence, and incorporates taxonomy-guided smooth- ness constraints. Our method achieves automatic and effective labeling of conceptual regions in urban scenarios, and is robust to tracking errors. Experimental validation on 5 surveillance databases has been conducted to assess the generality and accuracy of the segmentations. The resulting scene models are used for model-based behavior analysis.