Scene Radiance Research Articles

Transmission Estimation by Complex Assumption with Occlusion Handling

Transmission estimation is a critical step in single-image dehazing. The estimate of each pixel describes the portion of the scene radiance that is degraded by hazing and finally reaches the image sensor. Transmission estimation is an underconstrained problem, and, thus, various assumptions, priors, and models are employed to make it solvable. However, most of the previous methods did not consider the different assumptions simultaneously, which, therefore, did not correctly reflect the previous assumptions in the final result. This paper focuses on this problem and proposes a method using an energy function that clearly defines the optimal transmission map and combines the assumptions from three aspects: fidelity, smoothness, and occlusion handling, simultaneously. Fidelity is measured by a novel principle derived from the dark channel prior, smoothness is described by the assumption of piecewise smoothening, and occlusion handling is achieved based on a new proposed feature. The transmissions are estimated by searching for the optimal solution of the function that can retain all the employed assumptions simultaneously. The proposed method is evaluated on the synthetic images of two datasets and various natural images. The results show that there is remarkable fidelity and smoothness in the transmission and that a good performance is exhibited for haze removal.

Performance evaluation of various desmogging techniques for single smoggy images

The worsening air pollution is producing serious smog problems in the world. The high concentration of aerosol, that attenuates the scene radiance and adds undesired scattering illumination into the actual illumination values, has a serious effect on the visibility of the images. Therefore, images captured under smoggy environments suffer from poor visibility. Because, the smog particles attenuate the illumination reflected by the targets and add undesired scattering light. Therefore, imaging under smoggy environments affect the performance of many machine vision systems such as intelligent transportation system, remote sensing imaging, aerial imaging, etc. From the literature, it has been observed that majority of existing researchers have either focused on foggy or hazy images only.

An Efficient Image Haze Removal Algorithm based on New Accurate Depth and Light Estimation Algorithm

Single image Dehazing has become a challenging task for a variety of image processing and computer applications. Many attempts have been devised to recover faded colors and improve image contrast. Such methods, however, do not achieve maximum restoration, as images are often subject to color distortion. This paper proposes an efficient single image Dehazing algorithm that offers satisfactory scene radiance restoration. The proposed method stands on the estimation of two key indices; image blur and atmospheric light that can be employed in the Image Formation Model (IFM) to recover scene radiance of the hazy image. More clearly, we propose an efficient depth estimation method using image blur. Most existing algorithms implement atmospheric light as a constant which often leads to inaccurate estimations, we propose a new algorithm “A-Estimate” based on blur and energy to estimate the atmospheric light accurately, an adaptive transmission map also has been proposed. Experimental results on real and synthesized hazy images demonstrate an improved performance in the proposed method when compared to existing state-of-the-art methods.

A Unified Variational Model for Single Image Dehazing

Haze is a common weather phenomenon, which hinders many outdoor computer vision applications such as outdoor surveillance, navigation control, vehicle driving, and so on. In this paper, a simple but effective unified variational model for single image dehazing is presented based on the total variation regularization. From the perspective of the relationship between image dehazing and Retinex, the dehazing problem can be formulated as the minimization of a variational Retinex model. The proposed variational model incorporates two ${\ell _{1}}$ -norm regularization terms to constrain the scene transmission and the inverted scene radiance respectively, which can be better applied into image dehazing field. Different from the conventional two-step framework, our proposed model can simultaneously obtain the accurate transmission map and the recovered scene radiance by integrating the transmission estimation stage and the image recovery stage into the unified variational model. The entire optimization of the proposed unified variational model can be solved by an alternating direction minimization scheme. The experiments on various simulated and real-world hazy images indicate that the proposed algorithm can yield considerably promising results comparative to several state-of-the-art dehazing and enhancement techniques.

Single image haze removal with approximate radiance darkness prior

In this paper, we propose a novel and effective method for removing haze based on a single image, which firstly computes the dark channel of the estimated radiance image by decomposing the dark channel of the haze input image, and the method then estimates the transmission map of the input image. Finally, the scene radiance image is restored by the classical atmospheric scattering model. Experimental results show that the proposed method outperforms He et al.’s method in terms of haze removal.

Single Image Dehazing Using Haze-Lines

Haze often limits visibility and reduces contrast in outdoor images. The degradation varies spatially since it depends on the objects' distances from the camera. This dependency is expressed in the transmission coefficients, which control the attenuation. Restoring the scene radiance from a single image is a highly ill-posed problem, and thus requires using an image prior. Contrary to methods that use patch-based image priors, we propose an algorithm based on a non-local prior. The algorithm relies on the assumption that colors of a haze-free image are well approximated by a few hundred distinct colors, which form tight clusters in RGB space. Our key observation is that pixels in a given cluster are often non-local, i.e., spread over the entire image plane and located at different distances from the camera. In the presence of haze these varying distances translate to different transmission coefficients. Therefore, each color cluster in the clear image becomes a line in RGB space, that we term a haze-line. Using these haze-lines, our algorithm recovers the atmospheric light, the distance map and the haze-free image. The algorithm has linear complexity, requires no training, and performs well on a wide variety of images compared to other state-of-the-art methods.

Single Image Dehazing Based on the Physical Model and MSRCR Algorithm

To address the hazy weather image degradation problem, we propose a single image dehazing method based on a physical model and the brightness components of the image by using a multi-scale retinex with color restoration algorithm. The overall dehazing process involves three components, including the atmospheric light value calculation, transmission map estimation, and recovery of the hazy image scene radiance. Our contribution is that we propose a novel algorithm to dehaze a single image by calculating the atmospheric light value and computing the transmission map while considering the dynamic range of the image. Experimental results show that our algorithm can effectively improve the image quality degraded by foggy weather and retain sufficient image details.

Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond.

Single-image dehazing is an important low-level vision task with many applications. Early studies have investigated different kinds of visual priors to address this problem. However, they may fail when their assumptions are not valid on specific images. Recent deep networks also achieve a relatively good performance in this task. But unfortunately, due to the disappreciation of rich physical rules in hazes, a large amount of data are required for their training. More importantly, they may still fail when there exist completely different haze distributions in testing images. By considering the collaborations of these two perspectives, this paper designs a novel residual architecture to aggregate both prior (i.e., domain knowledge) and data (i.e., haze distribution) information to propagate transmissions for scene radiance estimation. We further present a variational energy-based perspective to investigate the intrinsic propagation behavior of our aggregated deep model. In this way, we actually bridge the gap between prior-driven models and data-driven networks and leverage advantages but avoid limitations of previous dehazing approaches. A lightweight learning framework is proposed to train our propagation network. Finally, by introducing a task-aware image separation formulation with a flexible optimization scheme, we extend the proposed model for more challenging vision tasks, such as underwater image enhancement and single-image rain removal. Experiments on both synthetic and real-world images demonstrate the effectiveness and efficiency of the proposed framework.

Single Image Dehazing With Depth-aware Non-local Total Variation Regularization.

Single image dehazing can benefit many computer vision applications hence has attracted much more attention in recent years. However, it still remains a challenging task due to its double uncertainty of scene transmission and scene radiance. The existing image dehazing methods usually impair edges in the estimated transmission which leads to halo effects in the dehazing results. Besides, most existing methods suffer from noise and artifacts amplification in dense haze region after dehazing. To address these challenges, we propose a transmission adaptive regularized image recovery method for high quality single image dehazing. An initial transmission map is first obtained by a boundary constraint on the haze model. Then it is refined by applying a non-local total variation (NLTV) regularization to keep depth structures while smoothing excessive details. Noticing that the artifacts amplification effect depends on scene transmission, a transmission adaptive regularized recovery method based on NLTV is proposed to simultaneously suppress visual artifacts and preserve image details in the final dehazing result. An efficient alternating optimization algorithm is also proposed to solve the regularization model. Thorough experimental results demonstrate that the proposed method can effectively suppress visual artifacts for degraded hazy images, and yields high-quality results comparative to the state-of-the-art dehazing methods both quantitatively and qualitatively.

Single-shot underwater image restoration: A visual quality-aware method based on light propagation model

In this paper, we present a novel method to restore the visual quality of images from scenes immersed in participating media, in particular water. Our method builds upon existing physics-based model and estimates the scene radiance by removing the medium interference on light propagation. Our approach requires a single image as input and, by combining a physics-based model for light propagation and a set of quality metrics, reduces the artifacts and degradation imposed by the attenuation, forward scattering, and backscattering effects. We show that the resulting images produced by our technique from underwater images are amenable to be directly used as input to algorithms which do not assume disturbances from the media. Our experiments demonstrate that, as far as visual image quality is concerned, our methodology outperforms both traditional image based restoration approaches and the state-of-the-art methods. Our approach brings advantages regarding descriptor distinctiveness which enables the use of underwater images in legacy non-participating media algorithms such as keypoint detection and description.

Saliency‐based dark channel prior model for single image haze removal

Images degraded by haze usually have low contrast and fide colours, and thus have bad effects on applications such as object tracking, face recognition, and intelligent surveillance. So the purpose of dehazing is to recover the image contrast without colour distortion. The dark channel prior (DCP) is widely used in the field of haze removal because of its simplicity and effectiveness. However, when faced with bright white objects, DCP overestimates the haze from its true value and thus causes colour distortion. In this study, the authors propose a dehazing model combining saliency detection with DCP to obtain recovered images with little colour distortion. There are three main contributions. First, they introduce a novel saliency detection method, focusing on superpixel intensity contrast, to extract bright white objects in the hazy image. Those objects are not used to estimate the atmospheric light and transmission in the dark channel image. Second, a self-adaptive upper bound is set for the scene radiance to prevent some regions being too bright. Third, they propose a quantitative indicator, colour variance distance, to evaluate the colour restoration. Experimental results show that their proposed model generates less colour distortion and has better comprehensive performance than competing models.

Towards Perceptual Image Dehazing by Physics-Based Disentanglement and Adversarial Training

Single image dehazing is a challenging under-constrained problem because of the ambiguities of unknown scene radiance and transmission. Previous methods solve this problem using various hand-designed priors or by supervised training on synthetic hazy image pairs. In practice, however, the predefined priors are easily violated and the paired image data is unavailable for supervised training. In this work, we propose Disentangled Dehazing Network, an end-to-end model that generates realistic haze-free images using only unpaired supervision. Our approach alleviates the paired training constraint by introducing a physical-model based disentanglement and reconstruction mechanism. A multi-scale adversarial training is employed to generate perceptually haze-free images. Experimental results on synthetic datasets demonstrate our superior performance compared with the state-of-the-art methods in terms of PSNR, SSIM and CIEDE2000. Through training on purely natural haze-free and hazy images from our collected HazyCity dataset, our model can generate more perceptually appealing dehazing results.

Color Attenuation Prior (CAP) for Single Image Dehazing

Single image haze removal has been a challenging problem due to its ill-posed nature. In this paper, we have used a simple but powerful color attenuation prior for haze removal from a single input hazy image. By creating a linear model for modeling the scene depth of the hazy image under this novel prior and learning the parameters of the model with a supervised learning method, the depth information can be well recovered. With the depth map of the hazy image, we can easily estimate the transmission and restore the scene radiance via the atmospheric scattering model, and thus effectively remove the haze from a single image. Experimental results show that the proposed approach outperforms state-of-the-art haze removal algorithms in terms of both efficiency and the dehazing effect.

Optimizing Image Acquisition Systems for Autonomous Driving

Task requirements for image acquisition systems vary substantially between applications: requirements for consumer photography may be irrelevant - or may even interfere - with requirements for automotive, medical and other applications. The remarkable capabilities of the imaging industry to create lens and sensor designs for specific applications has been demonstrated in the mobile computing market. We might expect that the industry can further innovate if we specify the requirements for other markets. This paper explains an approach to developing image system designs that meet the task requirements for autonomous vehicle applications. It is impractical to build a large number of image acquisition systems and evaluate each of them with real driving data; therefore, we assembled a simulation environment to provide guidance at an early stage. The open-source and freely available software (isetcam, iset3d, and isetauto) uses ray tracing to compute quantitatively how scene radiance propagates through a multi-element lens to form the sensor irradiance. The software then transforms the irradiance into the sensor pixel responses, accounting for a large number of sensor parameters. This enables the user to apply different types of image processing pipelines to generate images that are used to train and test convolutional networks used in autonomous driving. We use the simulation environment to assess performance for different cameras and networks.

Haze Removal Using Color Attenuation Prior With Varying Scattering Coefficients

This paper deals with removal of haze using color attenuation prior. It will helps for dehazing single image. For dehazing linear model is used. It is based on atmospheric scattering model. In this technique saturation and brightness values of an image is considered. It is less time consuming algorithm and also it has greater dehazing effects. Also varying scattering coefficient is used for dehazing purpose. With the depth map of the hazy image, we can smoothly surmise the transmission and give back the scene radiance via the atmospheric scattering model, and thus effectively remove the haze from a single image. It can implement very easily.

Modeling thermal emissive bands radiometric calibration impact with application to AVHRR

AbstractA novel analytical model of the calibration error impact on the Earth radiance measurement from thermal emissive bands of sensors is developed. The goal is to assess the impact of calibration errors, to evaluate those errors and to perform correction. This model is applied in the correction of bias in Advanced Very High Resolution Radiometer (AVHRR) channels 4 and 5 observed from the intercomparison with Infrared Atmospheric Sounding Interferometer measurements. A two‐step regression is used to separate the effects of calibration radiance errors from calibration coefficient errors. In the first step, the calibration radiance error, primarily due to internal calibration target (ICT) imperfections and temperature measurement error, is evaluated using the bias from selected Earth scenes with brightness temperatures close to the ICT temperature. The effects from the ICT imperfections and temperature measurement errors are analyzed collectively. The resulting estimation of the calibration radiance error is 0.30% for channel 4 and 0.33% for channel 5. After correcting the Earth scene radiance for these effects, the errors in the offset and nonlinear coefficient of instrument response are evaluated through the second step of the regression. A weighting function is used to account for the nonuniformity in the data distribution over the Earth radiance range. After the evaluation of the errors, removal of their effects can be achieved either through corrections of the calibration coefficients or correction of the measured radiance. The results are useful for the improvement of the AVHRR IR channel calibration algorithm. This model and two‐step regression approach can also be applied to other similar broadband thermal infrared radiometric sensors.

Single Image Dehazing Based on Combining Dark Channel Prior and Scene Radiance Constraint

Images captured in foggy or hazy weather conditions often suffer from poor visibility. The dark channel prior method has well solved the single image dehazing problem in nature, but it is invalid when the scene objects are inherently similar to the atmospheric light and no shadow is cast on them. We propose an efficient regularization method by adding a scene radiance constraint and combing the dark channel prior to remove hazes from a single input image. The experiments show that this improved algorithm can deal with various levels of foggy weather conditions, as well as greatly enhance the image's visibility and details. In addition, the recovered haze-free image has little or no halo artifacts.

High-speed video haze removal algorithm for embedded systems

In this paper, we implemented a video haze removal system that runs in real time and can be integrated in a vehicle dashboard to assist drivers. We used a heterogeneous TI TMS320DM6446 platform to distribute the algorithmic tasks among ARM, DSP, and VICP cores. Our processing algorithm uses the dark channel prior and has been applied to video. It has two algorithmic components which are the operation on multi-scale resolution and a new reconstruction formula for recovering the scene radiance to save computational time without sacrificing quality. We achieved eight frames per second at 720 × 480 video frame resolution.

Single Image Haze Removal Algorithm using Color Attenuation Prior and Multi-Scale Fusion

This paper compares the Fast Single Image Haze Removal (FSIHR) using Color Attenuation Prior (CAP) and MultiScale Fusion (MSF) methods. Single image haze removal has been a challenging problem due to its ill-posed environment. FSIHR works as simple but powerful color attenuation earlier, for removal of haze from a single input hazy image. MSF method is a fusion-based approach that results from two original hazy image inputs by applying a white balance and a contrast enhancing process. To merge the information of the derived inputs successfully, to maintain the regions with good visibility, it filters their important features by computing three measures (weight maps): luminance (Y), chromaticity (C), and saliency (S). The other FSIHR using CAP creates a linear model for modeling the picture depth of the hazy image with a supervised learning method; the depth information can be well recovered. With the depth map of the hazy image, the transmission and the scene radiance restoration via the atmospheric scattering model, and thus efficiently remove the haze from a single image. While the MSF method is faster than existing single image dehazing strategies and yields precise results.

Single image dehazing via multi‐scale gradient domain contrast enhancement

Outdoor images captured under bad weathers often suffer from low visibility. In this study, a novel method is presented to improve the visibility of a single input hazy image. On the basis of the observation that degradation of a hazy image occurs both in contrast and colour, the authors method aims at compensating the contrast and colour of the image, respectively. To achieve this, they propose a multi-scale gradient domain contrast enhancement approach that handles the different residual images rather than the entire image, and correct the attenuation of colour according to the estimated transmission. Since there is no need to recover the scene radiance by the degradation model, their method depends less on the accuracy of transmission and does not require the estimation of atmospheric light. Experiments on a variety types of hazy images show that their method yields accurate results with fine details and vivid colour, even better than other state-of-the-art dehazing methods.