Low Illumination Image Enhancement Algorithm Based on Illumination Equalization and Edge Detail Enhancement

In order to ensure the safe and efficient operation of the railway, the railway foreign object intrusion monitoring system has become the main way to obtain information. Due to the low visibility of the images collected at night in the low illumination environment, the loss of detail information is serious, which seriously reduces the accuracy of video intelligent recognition. To solve these problems, this paper proposes an image enhancement algorithm based on illumination equalization and edge detail enhancement. Firstly, the S component and V component of the image in the color space HSV are stretched, and the adaptive bilateral filter function is used as the center surrounding function to extract the light component of the low illumination image. Then, the two-dimensional gamma function is used to correct the image brightness to obtain the illumination balanced image; Then the four direction Sobel operator is used to extract the edge details of the image, and the image depicting the edge details is obtained; Finally, the enhanced image is obtained by multi weight feature pyramid image fusion. The method proposed in this paper is tested by selecting the video images in the low illumination environment at night in the railway integrated monitoring system. The experimental results show that the method proposed in this paper is superior to other classical algorithms in terms of SSIM, PSNR, NIQE evaluation indicators. The algorithm in this paper can effectively improve the brightness and clarity of low illumination images at night, while making the enhanced image contain more image edge details.