Abstract | ||
---|---|---|
In this paper, we propose an efficient automatic contrast enhancement algorithm for low lighting video. The algorithm is based on a piecewise stretch on the brightness component extracted with Retinex theory in HSV space to improve the visuality of the image. By dividing the brightness component into dark and bright part, nonlinear transformations with different distribution assumption were performed respectively. All the model parameters were estimated automatically according to the illumination conditions. We use two methods to estimate the brightness. The one is global illumination estimation and the other is local illumination estimation. In comparison with global estimation, a local illumination estimation method is proposed for the further improvement. Experiments show that the algorithm can achieve satisfactory effect for nighttime image or video enhancement by comparing with some state-of-the-art approaches. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/SPAC.2014.6982691 | SPAC |
Keywords | Field | DocType |
image enhancement,video signal processing,hsv space,retinex theory,automatic contrast enhancement algorithm,distribution assumption,global illumination estimation,illumination conditions,local illumination estimation method,low lighting video,nonlinear transformations,piecewise stretch,piecewise-based contrast enhancement framework,video enhancement,contrast enhancement,night video enhancement,nonlinear transformation,retinex,lighting,brightness,real time systems,histograms,estimation | Color constancy,HSL and HSV,Histogram,Computer vision,Nonlinear system,Division (mathematics),Global illumination,Artificial intelligence,Brightness,Piecewise,Mathematics | Conference |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dongsheng Wang | 1 | 9 | 7.35 |
Xin Niu | 2 | 56 | 11.39 |
Yong Dou | 3 | 632 | 89.67 |