Loading...
Please wait, while we are loading the content...
A Real-Time System for Abnormal Path Detection
| Content Provider | Semantic Scholar |
|---|---|
| Author | Calderara, Simone Alaimo, Clara Prati, Andrea Cucchiara, Rita |
| Copyright Year | 2009 |
| Abstract | This paper proposes a real-time system capable to extract and model object trajectories from a multi-camera setup with the aim of identifying abnormal paths. The trajectories are modeled as a sequence of positional distributions (2D Gaussians) and clustered in the training phase by exploiting an innovative distance measure based on a global alignment technique and Bhattacharyya distance between Gaussians. An on-line classification procedure is proposed in order to on-the-fly classify new trajectories into either “normal” or “abnormal” (in the sense of rarely seen before, thus unusual and potentially interesting). Experiments on a real scenario will be presented. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://imagelab.ing.unimore.it/Pubblicazioni/pubblicazioni/icdp2009.pdf |
| Alternate Webpage(s) | http://imagelab.ing.unimore.it/files2/icdp2009.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Domain-driven design Experiment Numerous Online and offline Preparation Real-time clock Real-time computing Real-time operating system Real-time transcription |
| Content Type | Text |
| Resource Type | Article |
