Clarity method of fog and dust image in fully mechanized mining face

Abstract

At present, the abnormal state of equipment and surrounding rocks in the fully mechanized mining face is mainly detected by visual methods. However, the vision sensor works in a low-light environment and it is affected by factors such as water fog and dust, which lead to blurred images. The defogging algorithm of image based on boundary constraint and context regularization has a good effect on image restoration in the daily environment, but the recovery quality is poor in low illumination environment. Therefore, a method based on boundary constraint and nonlinear context regularization is proposed. The model of fog and dust image is established, and the transmittance function is roughly estimated by boundary constraint method. Then, the nonlinear context regularization method based on logarithmic transformation is used to estimate and optimize the scene transmission model to improve the brightness of the image, and the low illumination fog and dust image is restored by the optimized transmittance function. The logarithmic transformation multiple is selected according to the peak value of image brightness. In order to highlight the effectiveness of our method, the widely used and improved Dark Channel Prior or other methods are used for comparison. The experiment results indicate that our method can effectively remove fog and dust and improve the brightness of the image of the fully mechanized face. It is of great significance to ensure safe production and safety of workers and equipment in coal mine.