Abstract | ||
---|---|---|
The detection and localization of anomalous behaviors in crowded scenes is considered, and a joint detector of temporal and spatial anomalies is proposed. The proposed detector is based on a video representation that accounts for both appearance and dynamics, using a set of mixture of dynamic textures models. These models are used to implement 1) a center-surround discriminant saliency detector that produces spatial saliency scores, and 2) a model of normal behavior that is learned from training data and produces temporal saliency scores. Spatial and temporal anomaly maps are then defined at multiple spatial scales, by considering the scores of these operators at progressively larger regions of support. The multiscale scores act as potentials of a conditional random field that guarantees global consistency of the anomaly judgments. A data set of densely crowded pedestrian walkways is introduced and used to evaluate the proposed anomaly detector. Experiments on this and other data sets show that the latter achieves state-of-the-art anomaly detection results. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TPAMI.2013.111 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
anomalous behavior detection,temporal saliency scores,temporal anomaly,pedestrians,crowded pedestrian walkways,anomalous behavior localization,image representation,spatial saliency score,video analysis,dynamic textures models,temporal anomaly maps,dynamic texture,normal behavior model,state-of-the-art anomaly detection result,surveillance,center-surround discriminant saliency detector,anomaly detection,multiple spatial scale,anomaly judgment global consistency,crowded scene,crowded scenes,proposed anomaly detector,conditional random field,object detection,anomaly judgment,video representation,temporal anomaly map,proposed detector,joint detector,image texture,center-surround saliency,spatial saliency scores,spatial anomaly maps,training data,video surveillance,spatial anomaly,occupational safety,ergonomics,suicide prevention,injury prevention,human factors | Conditional random field,Computer vision,Anomaly detection,Object detection,Data set,Pattern recognition,Computer science,Image texture,Salience (neuroscience),Artificial intelligence,Operator (computer programming),Detector | Journal |
Volume | Issue | ISSN |
36 | 1 | 1939-3539 |
Citations | PageRank | References |
172 | 3.29 | 32 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weixin Li | 1 | 637 | 20.78 |
Vijay Mahadevan | 2 | 1063 | 35.39 |
Nuno Vasconcelos | 3 | 5410 | 273.99 |