Enhancement of Mine Images Based on HSV Color Space

This study focuses on enhancing the quality of video images in coal mines under challenging conditions such as dust and low illumination. Existing algorithms often suffer from poor generalization and low accuracy. To address these limitations, we propose an unsupervised image enhancement method based on the HSV color space transformation, incorporating the Retinex theory into the luminance component (V channel). A disturbance technique is employed to perturb the luminance, and a reflectance estimation network based on U-Net is designed to ensure consistency between the original reflectance and the disturbed reflectance within the same scene. Additionally, residual multiscale and attention mechanism modules are introduced to improve accuracy while reducing the network's parameter count. The saturation component (S channel) is adaptively adjusted based on the correlation coefficient. The final enhanced image is obtained by recombining the original hue (H channel), luminance, and saturation before converting to the RGB color space. Importantly, our algorithm does not require training on normal light images. The experimental results indicate that our algorithm outperforms other state-of-the-art algorithms in terms of objective quality metrics, namely Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Additionally, our algorithm exhibits superior performance in subjective visual analysis compared to the comparative algorithms, demonstrating its efficacy in improving the visual quality of low-light images in mining environments.