A Single Image Dehazing Method Based on Adaptive Gamma Correction
Nguyen Minh Hong, Nguyen Chi Thanh · 2019 6th NAFOSTED Conference on Information and Computer Science (NICS) · 2019
Image dehazing is an important task in control systems of autonomous vehicles. It is necessary to increase accuracy and performance of road obstacles recognition. In this paper, we propose a single image dehazing method based on adaptive gamma correction (DAGC). The DAGC method processes haze on the Value band of the HSV color space by using the Gamma-correction with estimating the adaptive parameter based on the weighting cumulative density function. Otherwise, it also improves the Saturation band. In the experiments, we tested the DAGC method on the dehazing dataset of TAU and compare with other similar dehazing methods. The results showed that, the proposed method outperformed other methods.