Abstract: In underground coal mine environments, factors such as suspended coal dust and artificial light sources often lead to low brightness or uneven illumination in surveillance video images, resulting in severe image degradation. Existing underground image enhancement methods are not ideal and may cause issues like overexposure at near light points and distortion at far light points. To address this, we propose an image enhancement method for non-uniform illumination in underground coal mines based on the glow model and SRLLIE algorithm. This method consists of three main parts: using the glow model for exposure reduction, generating illumination and reflectance maps with the SRLLIE algorithm, and optimizing the illumination map to obtain the enhanced image using the Retinex model.First, the glow model is applied to remove the influence of glare in the image, avoiding overexposure and resulting in a low-illumination image without glare. Based on this, the objective function of the low-illumination enhancement SRLLIE algorithm is improved, and the alternating direction method of multipliers (ADMM) is used for iterative solving to obtain the illumination and reflectance maps that suppress overexposure while preserving structural details and removing low-light noise. Then, the illumination map is optimized using an S-shaped gamma correction function, further suppressing overexposed areas and enhancing the brightness of low-illumination regions. Finally, according to the Retinex theory, the optimized illumination map is multiplied by the denoised reflectance map to obtain the final enhanced image.To verify the effectiveness of the proposed algorithm, comparison experiments with relevant methods are conducted. The experimental results show that the proposed algorithm outperforms others in overall image quality, significantly enhancing image contrast, effectively solving the problem of uneven illumination in underground coal mine images, and improving the clarity of surveillance images. This provides valuable decision support for coal mine safety production and the construction of intelligent mines.