Abstract
In this paper, we propose a new algorithm to detect and extract natural snow from video. We detect the snow particle from images or videos by a series of filters, and each of these filters can recognize the features of snow efficiently. We label snow in videos and extract the alpha value of the snow particles by alpha matting. Our method can be applied to many fields such as background reconstruction. Experimental results show that our method is effective.
| Original language | English |
|---|---|
| Pages (from-to) | 1124-1130 |
| Number of pages | 7 |
| Journal | Information Processing Letters |
| Volume | 110 |
| Issue number | 24 |
| DOIs | |
| State | Published - 30 Nov 2010 |
| Externally published | Yes |
Keywords
- Alpha matting
- Design of algorithm
- Snow
- Video