Abstract | ||
---|---|---|
In this work, moving skin and shadow regions are analyzed and detected using adaptive mixture models. Both motion information and clues from skin and shadow properties are used to construct and update the models. The skin and shadow probabilities of each pixel are integrated into the mixture model framework. Furthermore, the adaptive mixtures are updated dynamically with learning rates adjusted by the skin and shadow probabilities. The experimental results have validated the effectiveness of the proposed method. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2499788.2499791 | ICIMCS |
Keywords | Field | DocType |
shadow region analysis,motion information,shadow property,adaptive model,adaptive mixture,shadow region,mixture model framework,shadow probability,adaptive mixture model | Computer vision,Shadow,Pattern recognition,Computer science,Artificial intelligence,Pixel,Region analysis,Mixture model | Conference |
Citations | PageRank | References |
0 | 0.34 | 6 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hsu-Yung Cheng | 1 | 243 | 23.56 |
Chih-Chang Yu | 2 | 32 | 8.93 |