Single image haze removal using dark channel prior

In this paper, we propose a simple but effective image prior - dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of the haze-free outdoor images. It is based on a key observation - most local patches in haze-free outdoor images contain some pixels which have very low intensities in at least one color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high quality haze-free image. Results on a variety of outdoor haze images demonstrate the power of the proposed prior. Moreover, a high quality depth map can also be obtained as a by-product of haze removal.

In this paper, we propose a simple but effective image prior-dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of outdoor haze-free images. It is based on a key observation-most local patches in outdoor haze-free images contain some pixels whose intensity is very low in at least one color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high-quality haze-free image. Results on a variety of hazy images demonstrate the power of the proposed prior. Moreover, a high-quality depth map can also be obtained as a byproduct of haze removal.

Generally computer applications use digital images. Digital image plays a vital role in the analysis and explanation of data, which is in the digital form. Images and videos of outside scenes are generally affected by the bad weather environment such as haze, fog, mist etc. It will result in bad visibility of the scene caused by the lack of quality. This paper exhibits a study about various image defogging techniques to eject the haze from the fog images caught in true world to recuperate a fast and enhanced nature of fog free images. In this paper, we propose a simple but effective the weighted median (WM) filter was first presented as an overview of the standard median filter, where a nonnegative integer weight is assigned to each position in the filter window image .Gaussian and laplacian pyramids are applying Gaussian and laplacian filter in an image in cascade order with different kernel sizes of gaussian and laplacian filter .The dark channel prior is a type of statistics of the haze-free outdoor images. It is based on a key observation - most local patches in haze-free outdoor images contain some pixels which have very low intensities in at least one-color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high-quality haze-free image. Results on a variety of outdoor haze images demonstrate the power of the proposed prior. Moreover, a high-quality depth map can also be obtained as a by-product of haze removal and Calculate the PSNR and MSE of three sample images.

Image degraded by haze is a critical aspect in today's environment while getting a high-quality haze-free image remains an important task in computer vision. In recent year, many works have been done to improve the visibility of image taken under bad weather. Conventional designs use multiple image and/ or single image to deal with haze removal. In this paper, we use a simple but effective prior, a variation of distance (VoD) prior, to estimate the transmission map and remove haze from a single input image. The VoD prior is developed based on the idea that the outdoor visibility of images taken under hazy weather conditions seriously reduced when the distance increases. The thickness of the haze can be estimated effectively and a haze-free image can be recovered by adopting the VoD prior and the new haze imaging model. Our method is stable to image local regions containing objects in different depths. Our experiments showed that the proposed method achieved better results than several state-of-the-art methods, and it can be implemented very quickly. Our method due to its fast speed and the good visual effect is suitable for real-time applications. This work confirms that estimating the transmission map using the distance information instead the color information is a crucial point in image enhancement and especially single image haze removal.

Conventional designs use multiple image or single image to deal with haze removal. The presented paper uses median filer with modified co-efficient (16 adjacent pixel median) and estimate the transmission map and remove haze from a single input image. The median filter prior(co-efficient) is developed based on the idea that the outdoor visibility of images taken under hazy weather conditions seriously reduced when the distance increases. The thickness of the haze can be estimated effectively and a haze-free image can be recovered by adopting the median filter prior and the new haze imaging model. Our method is stable to image local regions containing objects in different depths. Our experiments showed that the proposed method achieved better results than several state-of-the-art methods, and it can be implemented very quickly. Our method due to its fast speed and the good visual effect is suitable for real-time applications. This work confirms that estimating the transmission map using the distance information instead the color information is a crucial point in image enhancement and especially single image haze removal.

A procedure for haze detection and removal from a single image using dark channel and fast bilateral filter has been developed. It involves the analysis of the statistics of the haze images. The dark channel prior with the haze imaging model is used to estimate the parameters of the haze and recover a high quality haze-free image. With the fast bilateral filter, we can acquire the fine transmission estimation and has low computation. Experimental results on variety of hazy images demonstrate the proposed method is simple and powerful.

Haze removal is important for the normal work of computer vision system. However, most of the existing image dehazing methods are aimed at daytime haze images. These methods cannot always work well for night haze images since the spatially non-uniform environmental illumination are present at nighttime scenes that can generate glow. This makes nighttime haze removal from single image is an ill-posed problem with challenges. In this paper, we propose a novel algorithm for single nighttime image haze removal. We first remove the glow effects by decomposing the glow image from the nighttime haze image based on a nighttime haze imaging model which can account for spatially non-uniform environmental illumination and the glow effects in the image. Then, we estimate the atmospheric light by combining multiple patch sizes local atmospheric light using multiscale fusion algorithm. Transmission is estimated by maximizing the objective function which is designed by considering the image contrast and color distortion. Finally, haze is removed using the two estimated parameters. Experimental results show that the proposed algorithm can achieve haze-free results while removing the glow effects.

In this paper, we propose a simple but effective method to remove haze from a single input image. This method is not only prior on dark channel, but also light. Based on dark channel prior (DCP), a new haze removal scheme is proposed by Dr. He in [6] and it is becoming popular because of its dark channel statistics of outdoor haze-free images. Whereas, there are two problems in the scheme proposed in [6]: the cost of computing the transmission map using soft mapping is high and the atmospheric light is over-exposure when a bright area is shown in images. This paper proposes a novel dehazing algorithm with dark channel and light channel where the light channel is a kind of statistics of outdoor hazy images. Moreover, the guided filter is introduced to refine the dark channel and the light channel in this paper. The objective of proposed dehazing algorithm (PDA) is to alleviate or remove these problems found in [6]. To verify the PDA and compare it with the DCP scheme, several examples are given in this paper. The results show that the PDA is about 25 times faster than the DCP since the soft matting is avoided on average, and visual quality in the PDA without over-exposure problem is better than that in the DCP. With these improvements, the proposed method may be applied in video surveillance, intelligent transportation system and remote sensing.

Haze removal or dehazing has been a challenge in the field of image restoration. Recently, He et al.. proposed a single image dehazing scheme based on an interesting statistical prior called the dark channel prior (DCP). By the DCP, two parameters in the haze image model, the atmospheric light and the transmission map, can be estimated easily. Consequently, the DCP scheme has attracted much attention in this field. Note that the DCP scheme relies on the block-based dark channel which is considered as a strong DCP assumption. In this paper, a pixel-based dark channel is introduced through which the atmospheric light and the transmission map are estimated. The pixel-based dark channel is considered as a weak DCP (WDCP) since its statistical property is not as strong as that in the block-based dark channel. With a similar manner in the DCP scheme, the atmospheric light is estimated through the pixel-based dark channel. To make the pixel-based dark channel feasible in the transmission map estimation, an adaptive scaling factor for the initial transmission map is employed and the pixel-based dark channel is applied as the guide image in the transmission map refinement by the guided image filtering. Furthermore, an objective assessment is used to evaluate the proposed WDCP scheme and the compared DCP scheme. Simulation results indicate that the proposed WDCP scheme is more efficient, 24.30 times faster than the DCP scheme on average. Moreover, the proposed WDCP scheme is of better subjective visual quality than the DCP scheme and the employed objective assessment generally agrees with the results in the given examples.

Single image haze removal is an important task in computer vision. However, haze removal is an extremely challenging problem due to its massively ill-posed, which is that at each pixel we must estimate the transmission and the global atmospheric light from a single color measurement. In this paper, we propose a new deep learning-based method for removing haze from single input image. First, we estimate a transmission map via joint estimation of clear image detail and transmission map, which is different from traditional methods only estimating a transmission map for a hazy image. Second, we use a global regularization method to eliminate the halos and artifacts. Experimental results on synthetic dataset and real-world images show our method outperforms the other state-of-the-art methods.

Images captured in haze weather suffer from serious degradation of color and contrast due to incident light scattering and absorption. However, most of the existing methods which are based on depth information could not get satisfactory haze removal effect. In this paper, a simple but effective method is presented - image restoration using improved dark channel prior. The dark channel prior is based on a large number of statistical information. Most local patches in haze-free outdoor image contain some pixels which have very low intensities in at least one color channel. Using this prior with the haze image model, we can recover a high quality haze-free image. Image or video taken in haze day is restored using guided filtering finally. The simulation experiments based on Matlab demonstrate that the method is easy to use and able to improve quality of the images in haze efficiently. Meantime, the method can meet certain practical requirements.

Weighted Guided Image Filtering and Haze Removal in Single Image

Pre-processing for single image dehazing

Single image haze removal is an important task in computer vision. However, haze removal is an extremely challenging problem due to it is massively ill-posed, which is that we need to estimate the transmission and the corresponding haze-free pixel from a single color measurement at each pixel. In this paper, we propose a new deep learning based method for removing haze from single input image. First, we estimate a transmission map via joint estimation of clear image details and transmission map, which is different from traditional methods which only estimating a transmission map for a hazy image. Second, we use a global regularization method to eliminate the halos and artifacts. Experimental results demonstrate that our method outperforms the other state-of-the-art dehazing methods.

Wireless Multimedia Sensor Networks (WMSNs) have been implemented and used in many applications. The camera sensors are usually deployed in the wild to capture the image information and events. Images of outdoor scenes are usually degraded by the turbid medium in the atmosphere (fog, haze etc), which will reduce the accuracy of the sensor system greatly. On the other hand, due to the limited bandwidth in WMSNs, the camera sensor often report with a low frame rate. The traditional fog removal algorithm based on the visual stream can not be applied in the WMSNs directly. In this paper, we propose a simple but effective image prior to remove fog from a single input image. We employ the dark channel prior which is a kind of statistics of the haze-free outdoor images. Using this prior with the haze imaging model, we can directly estimate the thickness of the fog and recover a high quality fog-free image. Experiment results demonstrate the power of the proposed algorithm.