Real-time image /video haze removal algorithm with color restoration
Diao Yangji · Journal of Computer Applications · 2014
To overcome the defects of the existing algorithms, such as the poor real-time performance, bad effect in sky area and dark dehazed image, a real-time image haze removal algorithm was proposed. Firstly, dark channel prior was used to estimate the rough transmission map. Secondly, the method of optimized guided filtering was used to refine the down-sampled rough transmission map, which can real-time process higher resolution image. Thirdly, refined transmission map was upsampled and corrected to obtain the final transmission map, which can overcome the defect of bad effect in sky area. Finally,the clear image was got by adaptive brightness adjustment with color restoration. The complexity of the algorithm is only a linear function of the number of input image pixels, which brings a very fast implementation. For the image which resolution is600 × 400, the processing time is 80 ms. Comparison experiments with other three kind of methods were given, including single image haze removal method using dark channel based on the guided filtering, fast visibility restoration method using the median filter and MSRCR( Multi-Scale Retinex with Color Restoration). The experimental results show that the proposed method not only can significantly improve the contrast and color of haze image with strong robustness, but also the quality and the efficiency is superior to the comparison algorithms.