Automatic Learning of Background Semantics in Generic Surveilled Scenes

Advanced surveillance systems for behavior recognition in outdoor traffic scenes depend strongly on the particular configuration of the scenario. Scene-independent trajectory 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 semantic regions. State-of-the-art approaches for unsupervised scene labeling exploit trajectory 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 trajectory analysis. Subsequently, a so-called GI-MRF inference process reinforces spatial coherence, and incorporates taxonomy-guided smoothness constraints. Our method achieves automatic and effective labeling of conceptual regio...

• Type: Conference
• Year: 2010
• Where: ECCV
• Authors: Carles Fernández, Jordi Gonzàlez, Xavier Roca
• Keywords: Behavior Analysis, ECCV 2010, Markov Random Field, Scene Learning, Trajectory Analysis