An effective and robust single-image dehazing method based on gamma correction and adaptive Gaussian notch filtering

• Published in: The Journal of supercomputing Vol. 80; no. 7; pp. 9253 - 9276
• Main Authors: Kumari, Apurva, Sahoo, Subhendu Kumar
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2024; Springer Nature B.V
• Subjects: Advanced driver assistance systems; Compilers; Computer Science; Computer vision; Crashes; Ill posed problems; Interpreters; Light; Methods; Neural networks; Noise measurement; Notch filters; Performance evaluation; Performance measurement; Processor Architectures; Programming Languages; Signal to noise ratio; Traffic accidents; Visibility; Vision systems; Weather; Transmission depth; Gaussian notch filtering; Outdoor vision; Gamma correction
• ISSN: 0920-8542; 1573-0484
• DOI: 10.1007/s11227-023-05805-z

The weather has a detrimental effect on outdoor vision systems and raises the probability of traffic crashes and road accidents. The scattering of atmospheric particles degrades outdoor images captured in poor weather conditions such as haze and fog. The reduced visibility has a significant impact on driving assistance systems designed for automatic vehicles. As a result, clear visibility is critical for outdoor computer vision systems. Image dehazing is one of the ill-posed problems because evaluating transmission depth is challenging. It is essential to estimate transmission depth with the greatest degree of accuracy. In order to estimate or optimize the transmission depth, this paper employs the adaptive Gaussian notch filter and the concept of gamma correction to recover the final scene radiance. The results of the experiments are assessed and compared both quantitatively and qualitatively with state-of-the-art techniques. The experimental results demonstrate that the proposed indicators ensure high consistency in qualitative and quantitative evaluation using six performance metrics: two blind assessment indicators (e, r), contrast gain ( C gain ) , visual contrast measure (VCM), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and probability.