People Tracking Algorithm for Human Height Mounted Cameras
| Autor: | Vladimir Kononov, Anton Konushin, V. S. Konushin |
|---|---|
| Rok vydání: | 2011 |
| Předmět: | |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783642231223 DAGM-Symposium |
| DOI: | 10.1007/978-3-642-23123-0_17 |
| Popis: | We present a new people tracking method for human height mounted camera, e.g. the one attached near information or advertising stand. We use state-of-the-art particle filter approach and improve it by explicitly modeling of object visibility which makes the method able to cope with difficult object overlapping. We employ our own method based on online-boosting classifiers to resolve occlusions and show that it is well suited for tracking multiple objects. In addition to training an online-classifier which is updated each frame we propose to store object appearance and update it with a certain lag. It helps to correctly handle situations when a person enters the scene while another one leaves it at the same time. We demonstrate the perfomance of our algorithm and advantages of our contributions on our own video dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|