Urban Night Image Restoration Algorithm Based on Space Model
Jing Hu, Yuanyuan Liu · 2018
In this paper, we propose a new algorithm to restore non-uniform illumination images at night. Building space model to simulate the night illumination environment, and propose a new detection light source algorithm based on this space model. Adaptive exposure according to the distance between the object and the light source, the illumination intensity of the original image is redistributed to make the whole image illumination uniform, and the aim of restoring the non-uniform illumination image is achieved. At the same time, in order to facilitate subsequent detection and recognition, this paper presents an algorithm to increase the contrast of images. The proposed algorithm is tested in the night non-uniform illumination environment. The experimental results show that the proposed algorithm is superior to the conventional exposure algorithm in image detail restoration.