Abandoned object detection via subspace learning
| Autor: | A. Koksal Hocaoglu, Hasan Huseyin Sonmez |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Initialization 020206 networking & telecommunications 0102 computer and information sciences 02 engineering and technology 01 natural sciences Object detection 010201 computation theory & mathematics Robustness (computer science) Video tracking 0202 electrical engineering electronic engineering information engineering Computer vision Artificial intelligence business Subspace topology Sparse matrix |
| Zdroj: | SIU |
| DOI: | 10.1109/siu.2016.7495761 |
| Popis: | In this study, a novel video surveillance algorithm is developed for detection of abandoned objects in public scenes. Two different foreground model is used to detect moving and temporarily static objects. A subspace learning method, called GoDec, is used to detect foreground objects. By using GoDec algorithm, shape and contour of foreground objects are obtained more precisely than the traditional methods. Algorithm is tested on different public datasets and on a new dataset prepared in various environments by GTU, Gebze Technical University. According to test results, proposed method gives better results especially for background initialization and occlusion problems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|