Enhanced Image Dehazing Using Bright and Dark Channel Prior

Visibility degradation caused by haze presents a major challenge for computer vision systems in outdoor environments. This project introduces an enhanced image dehazing method based on Bright and Dark Channel Prior (BDCP), an improvement over traditional dark channel technique. By incorporating both bright and dark channel information, the method more effectively estimates the transmission map and atmospheric light, resulting in clearer and more natural dehazed images. The proposed algorithm refines visual quality through a fusion-based enhancement and edge-preserving filtering. Extensive experiments demonstrate that this approach significantly outperforms conventional methods in terms of contrast restoration and color fidelity, particularly under dense haze conditions.