Motivation: Outdoor images often suffer from low contrast and limited visibility due to haze, small particles such as dust, mist, and fumes which deflect light from its original course of propagation. Haze has two effects on the image: it weaken the imgage contrast and also adds an additive component to the image, so-called airlight. Recovering a haze-free image can restore the visibility of the scene and correct the color shift caused by the airlight. Furthermore, dehazing can benefit many computer vision algorithms which usually assume that the input image after radiometric calibration is the scene radiance and will suffer from the biased, low contrast scene radiance. Last but not lease, since haze is dependent on the unknow depth information, scene depth estimation is usually a by-product of dehazing and the depth information can be used for other applications.
example of haze image
example of haze-free image
Research plan: In this project, we will perform single image dehazing and also video dehazing. We will perform single image dehazing using state-of-the-art algorithms including the one proposed by He et al. in  and also method based on non-local haze-lines proposed in . Then we will extend the method for single image dehazing to video dehazing. To perform video dehazing efficiently, we will first use algorithm in  to estimate the airlight. Then we simply use the airlight computed from the first frame for all other frames in the video inputs by assuming that the airlight remains the same for the period when video was taken. After getting the airlight estimation, we will dehaze each frame of the input video. Detailed implementation will be discussed in the future update.Code: