Single image haze removal has been a challenging problem due to its ill-posed nature. In this paper, we propose 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.

With the development of digital multimedia technologies, image matting has gained increasing interests from both academic and industrial communities. The purpose of image matting is to precisely extract the foreground objects with arbitrary shapes from an image or a video frame for further editing. It is generally known that image matting is inherently an ill-posed problem because we need to output three images out of only one input image. In this paper, we provide a comprehensive survey of the existing image matting algorithms and evaluate their performance. In addition to the blue screen matting, we systematically divide all existing natural image matting methods into four categories: 1) color sampling-based; 2) propagation-based; 3) combination of sampling-based and propagation-based; and 4) learning-based approaches. Sampling-based methods assume that the foreground and background colors of an unknown pixel can be explicitly estimated by examining nearby pixels. Propagation-based methods are instead based on the assumption that foreground and background colors are locally smooth. Learning-based methods treat the matting process as a supervised or semisupervised learning problem. Via the learning process, users can construct a linear or nonlinear model between the alpha mattes and the image colors using a training set to estimate the alpha matte of an unknown pixel without any assumption about the characteristics of the testing image. With three benchmark data sets, the various matting algorithms are evaluated and compared using several metrics to demonstrate the strengths and weaknesses of each method both quantitatively and qualitatively. Finally, we conclude this paper by outlining the research trends and suggesting a number of promising directions for future development.

Bad weather (eg., fog and haze) significantly degrades the quality of outdoor images taken by camera, leading to the fact that most automatic systems, which strongly depends on the definition of the input images, fail to work normally. Thus, the improvement of the dehazing technology is highly desired. To overcome the disadvantages of traditional dark channel priorbased algorithm, we propose a more efficient dehazing algorithm combining dark channel prior and mean shift segmentation. Firstly, we take the operation of white balance on the input haze image to reduce the negative influence of color cast. Secondly, we use the mean shift segmentation algorithm to separate the sky regions from the foreground in the transmission map, which is obtained with the dark channel prior-based approach. Thirdly, we enhance the brightness of the sky regions in the transmission map independently and use guided image filtering to smooth the map. Finally, we restore the image with the re-refined transmission map. The experimental results demonstrate that the proposed approach is better able to handle the sky regions and solve the problem of color cast compared with the typical dehazing algorithms.

Identifying moving objects in a video sequence is a fundamental and critical task in video surveillance, traffic monitoring, and gesture recognition in human-machine interface. In this paper, we present a novel recursive Kernel Density Estimation based background modeling method. First, local maximum in the density functions is recursively approximated using a mean shift method. Second, components and parameters in the mixture Gaussian distributions can be selected adaptively via a proposed thresholding mechanism, and finally converge to a stable background distribution model. In the scene segmentation, foreground is firstly separated by simple background subtraction approach. And then a local texture correlation operator is introduced to fill the vacancies and remove the fractional false foreground regions so as to obtain a better video segmentation quality. Experiments conducted on synthetic and video data demonstrate the superior performance of the proposed algorithms.

The task of interactive image segmentation has attracted a significant attention in recent years. The ultimate goal is to extract an object with as few user interactions as possible. In this paper, we present SUPERCUT, a novel interactive algorithm for foreground object extraction and segmentation in images. In the algorithm, the mean shift algorithm with a boundary confidence prior is introduced to efficiently pre-segment the original image into super-pixels with precise boundary. Secondly, a Bayes decision theory is introduced to model and cluster the super-pixels so as to obtain an initial effective classification of super-pixels. To achieve a more accurate object segmentation result, a boundary refinement using Interactive rectangle box with GMM learning is adopted. Experimental results on a benchmark data set show that the proposed framework is highly effective and can accurately segment a wide variety of natural images with ease.

Extraction of thin elongated objects from natural images is an important task in many computer vision applications such as image segmentation, object detection. Extensive approaches attempt to solve this issue with region features or prior knowledge, causing local minimum or short cut path. In this paper, we propose a semi-automatic method for the extraction of thin elongated objects. Given the input image, we manually label some foreground/background pixels as training samples. We use Guassian mixture model (GMM) to model background and extract object. We compute fuzzy affinity based on G-MM and take the framework of fuzzy connectedness (FC) to obtain fuzzy connected component. To obtain better result, we use adaptive components for GMM. Qualitative and quantitative comparisons show that our method outperforms many classical algorithms in terms of accuracy.

Current image matting approaches are often implemented based upon color samples under various local assumptions. In this letter, a novel image matting algorithm is investigated by treating the alpha matting as a regression problem. Specifically, we learn spatially-varying relations between pixel features and alpha values using support vector regression. Via the learning-based approach, limitations caused by local image assumptions can be greatly relieved. In addition, the computed confidence terms in learning phase can be conveniently integrated with other matting approaches for the matting accuracy improvement. Qualitative and quantitative evaluations are implemented with a public matting benchmark. And the results are compared with some recent matting algorithms to show its advantages in both efficiency and accuracy.

Alpha matting refers to the problem of estimating the opacity mask of the foreground in an image. Many recent algorithms solve it with color samples or some local assumptions, causing artifacts when they fail to collect appropriate samples or the assumptions do not hold. In this paper, we treat alpha matting as a supervised learning problem and propose a new matting approach. Given the input image and a trimap (labeling some foreground/background pixels), we segment the unlabeled region into pieces and learn the relations between pixel features and alpha values for these pieces. We use support vector regression (SVR) in the learning process. To obtain better learning results, we design a training samples selection method and use adaptive parameters for SVR. Qualitative and quantitative evaluations on a matting benchmark show that our approach outperforms many recent algorithms in terms of accuracy.

Segmentation of video with dynamic background is an important research topic in image analysis and computer vision domains. In this paper, we present a novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. In the algorithm, each frame pixel is represented as the layered normal distributions which correspond to different background contents in the scene. The layers are associated with a confident term and only the layers satisfy the given confidence which will be updated via the recursive Bayesian estimation. This makes learning of background motion trajectories more accurate and efficient. To improve the segmentation quality, the coarse foreground is obtained via simple background subtraction first. Then, a local texture correlation operator is introduced to fill the vacancies and remove the fractional false foreground regions. Extensive experiments on a variety of public video datasets and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both segmentation accuracy and efficiency.

Modeling background and segmenting moving objects are significant techniques for video segmentation and other video processing applications. Many different methods about background modeling and video extraction have been proposed over the recent years. In this paper, we present a novel recursive Kernel Density Estimation based video segmentation method. In the algorithm, local maximum in the density functions is approximated recursively via a mean shift method firstly. Via a proposed thresholding scheme, components and parameters in the mixture Gaussian distributions can be selected adaptively, and finally converge to a relative stable background distribution mode. In the segmentation, foreground is firstly separated by simple background subtraction method. And then, the Bayes classifier is introduced to eliminate the misclassifications points to improve the segmentation quality. Experiments on four typical video clips are used to compare with some previous methods.