Haze removal Methods: A Comprehensive Review

Haze removal is useful in computational photography and computer vision applications. Single image haze removal is still a challenge for real-time embedded systems. In general, dark channel prior approach can effectively remove haze from a single image. However, the halo effect is the major problem of dehazing. In this study, adaptive filtering, which is easy for VLSI design, is introduced to refine the transmission map and improve the result of haze removal. A hardware architecture for our haze removal method is proposed to achieve the real-time requirement. A specific hardware component is designed to compute lengths of the paths and adaptive structuring element (ASE). The hardware architecture for haze removal is implemented in 180 nm CMOS technology and occupies 5.46 mm 2 with 143 K bit on-chip memory. The design can operate at 177MHz and support for HD (1280×720) 192 frame/s. Experiment results show that the hardware implementation is suitable in embedded system for real-time HD applications.

Computer vision applications in outdoor environment are mainly affected by factors such as pollution, clouds, shadow, haze, fog. Herein, an algorithm for real-time haze detection and removal in image has been implemented. For this purpose, the Dark Channel Prior technique is used which is efficient method for haze removal and also contains information about the level of haze in the image. Initially, visibility index of image frame is estimated to determine whether image is hazy or not using haze detection model. Thereafter, hazy images are processed with haze removal model to enhance the image visibility. The haze removal model uses guided filter to accelerate the process. Non-hazy images do not require to process with haze removal model. The algorithm has been tested for four datasets, i.e., non-hazy, slightly hazy, medium hazy, and heavily hazy. The proposed algorithm is performing well and also able to tackle the halo effects at some extent.

Millions of digital images are captured by imaging devices on a daily basis. The way imaging devices operate follows an integral process from which the information of the original scene needs to be estimated. The estimation is done by inverting the integral process of the imaging device with the use of optimization techniques. This linear inverse problem, the inversion of the integral acquisition process, is at the heart of several image processing applications such as denoising, deblurring, inpainting, and super-resolution. We describe in detail the use of linear inverse problems in these applications. We review and compare several state-of-the-art optimization algorithms that invert this integral process. Linear inverse problems are usually very difficult to solve. Therefore, additional prior assumptions need to be introduced to successfully estimate the output signal. Several priors have been suggested in the research literature, with the Total Variation (TV) being one of the most prominent. In this thesis, we review another prior, the l0 pseudo-norm over the gradient domain. This prior allows full control over how many non-zero gradients are retained to approximate prominent structures of the image. We show the superiority of the l0 gradient prior over the TV prior in recovering genuinely piece-wise constant signals. The l0 gradient prior has shown to produce state-of-the-art results in edge-preserving image smoothing. Moreover, this general prior can be applied to several other applications, such as edge extraction, clip-art JPEG artifact removal, non-photorealistic image rendering, detail magnification, and tone mapping. We review and evaluate several state-of-the-art algorithms that solve the optimization problem based on the l0 gradient prior. Subsequently we apply the l0 gradient prior to two applications where we show superior results as compared to the current state-of-the-art. The first application is that of single-image reflection removal. Existing solutions to this problem have shown limited success because of the highly ill-posed nature of the problem. We show that the standard l0 gradient prior with a modified data-fidelity term based on the Laplacian operator is able to sufficiently remove unwanted reflections from images in many realistic scenarios. We conduct extensive experiments and show that our method outperforms the state-of-the-art. In the second application of haze removal from visible-NIR image pairs we propose a novel optimization framework, where the prior term penalizes the number of non-zero gradients of the difference between the output and the NIR image. Due to the longer wavelengths of NIR, an image taken in the NIR spectrum suffers significantly less from haze artifacts. Using this prior term, we are able to transfer details from the haze-free NIR image to the final result. We show that our formulation provides state-of-the-art results compared to haze removal methods that use a single image and also to those that are based on visible-NIR image pairs.

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.

Haze is a common phenomenon often produced during bad weather that obscure scenes, reduces visibility, and degrades colors. Haze removal poses a serious challenge because of the difficulty to develop an exact mathematical model when a single hazy image is given as the input. In this paper, we propose a single image haze removal method to highlight the edges. A edge-aware constraint weighting scheme based on first-order derivative from Gradient domain Guided Image filter is adopted in this algorithm which helps to preserve the edges better. In this dehazing algorithm, simplified dark channel of the haze image can be separated as base layer and detail layer by applying a filter, i.e., weighted guided image filter. The transmission map is obtained from the base layer and thereby it is utilized to restore haze-free image. Result analysis show that the proposed algorithm preserves and highlights the edges without any color distortion. Experimental results are performed on natural haze images, aerial images, and under water images. In qualitative analysis, edge map shows the better performance of the proposed method. Quantitative Analysis have been carried out which demonstrates the better performance of the proposed algorithm when compared with the existing method.

Haze significantly degrades the visibility for ship navigation and traffic monitoring in China's inland waterways. In this study, the authors propose a novel haze-removal method based on sky segmentation and dark channel prior to restore images. Sky segmentation is accomplished by using robust image matting and region growth algorithms. Then, the average image intensity of the sky region is chosen as the atmospheric light value to address the defect of dark channel prior. Experimental results show that their method can restore inland waterway images effectively; restored images are more natural and smoother than those obtained by the state-of-the-art haze removal algorithms.

Haze removal is useful in computational photography and computer vision applications. Although many haze removal algorithms have been proposed, their computational efficiency requires improvement. A real-time haze removal method is presented in this paper. The method is based on the concept of a dark channel prior. To enhance the haze removal performance, an approximate method to estimate the atmospheric light and transmission is employed. For embedded system applications, a hardware architecture to perform real-time haze removal is proposed. The hardware can achieve 116 MHz on Stratix FPGA. The simulation results indicate that the hardware is highly efficient and performs well. It obtains good image recovery results and satisfies the real-time requirement even for large images.

In this paper, we propose an accurate single image haze removal method that divides hazed images into regions in advance, where haze removal processing is difficult, and applies it to the estimation of ambient light. In addition, we propose a method of iterative haze removal for further improving image accuracy. The conventional method has a problem that the amount of haze is estimated larger than the actual amount in the regions where the distance between the photographic spot and subject is long, and causes that ambient light cannot be estimated accurately. The regions which are difficult to be processed mainly white and sky regions. If those regions are processed in the same way as the other regions, bad effects are observed such as the image becomes darker or its color changes too much. In the proposed method, the regions which are difficult to estimate the amount of haze are divided into multiple regions by extracting pixels similar to the feature pixels, and then ambient light is determined from the regions where haze removal processing is easy. The proposed method can easily extract the appropriate color of haze for any given image.

A constrained total variation model for single image dehazing

In a recent study, it was shown that, with adversarial training of an attentive generative network, it is possible to convert a raindrop degraded image into a relatively clean one. However, in real world, raindrop appearance is not only formed by individual raindrops, but also by the distant raindrops accumulation and the atmospheric veiling, namely haze. Current methods are limited in extracting accurate features from a raindrop degraded image with background scene, the blurred raindrop regions, and the haze. In this paper, we propose a new model for an image corrupted by the raindrops and the haze, and introduce an integrated multi-task algorithm to address the joint raindrop and haze removal (JRHR) problem by combining an improved estimate of the atmospheric light, a modified transmission map, a generative adversarial network (GAN) and an optimized visual attention network. The proposed algorithm can extract more accurate features for both sky and non-sky regions. Experimental evaluation has been conducted to show that the proposed algorithm significantly outperforms state-of-the-art algorithms on both synthetic and real-world images in terms of both qualitative and quantitative measures.

In poorly lit environmental conditions, the camera does not capture clear images. There are many enhancement processes for low light images, considering all those factors, it is inferred that the main problem that arises even after the enhancement process is the noise. Haze removal method is taken for the enhancement of the image after performing various studies on the various processes. Guided, Median, Gaussian and Weiner filters are deployed for removing the noise which is enhanced during the process in the low light image set. The performance analysis of the filters is carried out to measure the rate of enhancement with metrics such as SNR, PSNR and SSIM. The experimental results here show the performance of various filters taken into consideration and found that guided filter, median filter and wiener filter showed good enhanced results.

Haze removal or dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years. Despite this growing interest, the scientific community is still lacking a reference dataset to evaluate objectively and quantitatively the performance of proposed dehazing methods. The few datasets that are currently considered, both for assessment and training of learning-based dehazing techniques, exclusively rely on synthetic hazy images. To address this limitation, we introduce the first outdoor scenes database (named O-HAZE) composed of pairs of real hazy and corresponding haze-free images. In practice, hazy images have been captured in presence of real haze, generated by professional haze machines, and O-HAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. To illustrate its usefulness, O-HAZE is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000. This reveals the limitations of current techniques, and questions some of their underlying assumptions.

Rain removal from a single image is a challenge which has been studied for a long time. In this paper, a novel convolutional neural network based on wavelet and dark channel is proposed. On one hand, we think that rain streaks correspond to high frequency component of the image. Therefore, haar wavelet transform is a good choice to separate the rain streaks and background to some extent. More specifically, the LL subband of a rain image is more inclined to express the background information, while HL, LH subband tend to represent the rain streaks and the edges respectively. On the other hand, the accumulation of rain streaks from long distance makes the rain image look like haze veil. We extract dark channel of rain image as a feature map in network. By increasing this mapping between the dark channel of input and output images, we achieve haze removal in an indirect way. All of the parameters are optimized by back-propagation. Experiments on both synthetic and realworld datasets reveal that our method outperforms other state-of-the-art methods from a qualitative and quantitative perspective.

Haze usually limits the visibility and reduces the contrast of outdoor images. The removal of haze in a single image has always been a challenging problem. Recently, many methods have been proposed to effectively remove haze in harsh conditions. However, these methods fail to balance the dehazing effect and time consumption. This paper proposes a method based on HSV colour space to restore the visibility of uniform scattering medium. It can prevent the atmospheric light and transmission from being miscalculated. This method uses the brightness component of haze image to estimate the global atmospheric light, which reduces the influence of luminescent objects on atmospheric light estimation. Then, this paper deduces the estimation model of the saturation of scene radiance based on the atmospheric scattering model. In the meantime, according to the advantages and problems of the model, the fast estimation of the transmission is realized by using the stretching function. Finally, this paper solves the parameters in the model by iterative method. Since this method can estimate different media transmission for each pixel, better results can be obtained. The simulation results show that the algorithm is superior to the existing algorithms in terms of dehazing effect and time consumption.

Images of outdoor scenes show poor visibility in presence of haze. This results in poor performance of many outdoor images progressing systems. In this paper, we present a fast haze removal method using a single color or gray level image. Based on the analyses of physical-based model, we estimate airlight and atmospheric light utilizing the simple average filter. Our method is very simple and efficient and achieves real-time computation. Experiments demonstrate that our results achieve as good visibility as a few state-of-art algorithms'.