Name
Abstract | ||
|---|---|---|
Videos captured in car often suffer from dust on the wind screen glass. The dust particles on wind screen decrease the video quality and make them blur. Removing dust and restoring high quality dust-free video is a challenging task in the field of video stream processing. In this paper, we propose an improved iterative optimization pipeline to remove dust from the videos. Our method employs boundary constraint to keep transmission map in a reasonable range and use spatial constraint on the transmission map to avoid introduction of significant halo artifacts into the resultant video. With optimized transmission map as an initial condition, our method can separate dust layer and background layer from input video frames and keeps the background frames being color faithful with fine details. Test results demonstrate that our proposed method can recover dust-free videos from the dust contaminated input videos and keep the resultant video color faithful. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ICEBE.2017.57 | 2017 IEEE 14th International Conference on e-Business Engineering (ICEBE) |
Keywords | Field | DocType |
dust removal,spatial constraint,wind screen glass,dust particles,wind screen decrease,video quality,restoring high quality dust-free video,video stream processing,background layer,input video frames,dust-free videos,input videos,resultant video color faithful,car video capture | Computer vision,Dust particles,Computer science,Initial value problem,Artificial intelligence,Halo,Stream processing,Video quality | Conference |
ISBN | Citations | PageRank |
978-1-5386-1413-6 | 0 | 0.34 |
References | Authors | |
14 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Biao Xiong | 1 | 7 | 2.17 |
| ZhiYong Huang | 2 | 0 | 1.01 |
| ShuangMei Peng | 3 | 0 | 0.34 |
| Xiang Fei | 4 | 40 | 8.94 |
| Nazaraf Shah | 5 | 175 | 27.55 |