Abstract | ||
---|---|---|
A robust scheme is proposed to generate an anti-ghosting high dynamic range (HDR) image from a set of low dynamic range (LDR) images with different exposure times. Three major contributions of this paper are 1) a bi-directional prediction method; 2) an adaptive threshold for the classification of pixels; 3) Bayes estimator based methods for the on-line updating of predicted values and the synthesis of pixels to fill in the regions of moving objects to preserve their dynamic ranges. The proposed scheme is suitable for both static and dynamic scenes. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICASSP.2010.5495327 | 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING |
Keywords | Field | DocType |
High dynamic range, collaborative image processing, ghosting artifacts, similarity | Computer vision,Dynamic range,Computer science,Signal generator,Image processing,Low dynamic range,Robustness (computer science),Pixel,Artificial intelligence,High dynamic range,Bayes estimator | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Z. Li | 1 | 1578 | 164.19 |
Zijian Zhu | 2 | 99 | 9.24 |
Shoulie Xie | 3 | 177 | 20.80 |
Shiqian Wu | 4 | 1347 | 85.75 |
Susanto Rahardja | 5 | 652 | 102.05 |