Fast single-image dehazing using linear transformation

Haze can turn a colored image into a white-and-gray one, causing a loss of image detail and a reduction in contrast. Haze also disturbs many applications, including direct target observations and indirect recognition, tracking, and measurements. Image dehazing can remove haze from images, increase the scene visibility, and improve the overall visual effect. However, most existing dehazing methods, which require a large number of computations and complex steps, cannot meet the requirements of a real-time application. In this paper, a fast single-image dehazing algorithm is proposed. Using the proposed haze imaging model, we estimate the atmospheric light using an infinite sky region and close white region, calculate the transmission map using a linear transformation, and recover a haze-free image. We also demonstrate its good performance by conducting experiments on various hazy images. The proposed algorithm can be efficiently implemented in O(N) time and has a faster speed than most previous dehazing methods. In addition, the method takes no more than 40 ms to process an image of one-million pixels on a PC with a 3.1 GHz Intel Xeon processor.