Qingsong Zhu

A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior

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.

Learning based alpha matting using support vector regression

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.

A Novel Recursive Bayesian Learning-Based Method for the Efficient and Accurate Segmentation of Video With Dynamic Background

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.

Targeting Accurate Object Extraction From an Image: A Comprehensive Study of Natural Image Matting

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.

Evaluation of various speckle reduction filters on medical ultrasound images

At present, ultrasound is one of the essential tools for noninvasive medical diagnosis. However, speckle noise is inherent in medical ultrasound images and it is the cause for decreased resolution and contrast-to-noise ratio. Low image quality is an obstacle for effective feature extraction, recognition, analysis, and edge detection; it also affects image interpretation by doctor and the accuracy of computer-assisted diagnostic techniques. Thus, speckle reduction is significant and critical step in pre-processing of ultrasound images. Many speckle reduction techniques have been studied by researchers, but to date there is no comprehensive method that takes all the constraints into consideration. In this paper we discuss seven filters, namely Lee, Frost, Median, Speckle Reduction Anisotropic Diffusion (SRAD), Perona-Maliks Anisotropic Diffusion (PMAD) filter, Speckle Reduction Bilateral Filter (SRBF) and Speckle Reduction filter based on soft thresholding in the Wavelet transform. A comparative study of these filters has been made in terms of preserving the features and edges as well as effectiveness of de-noising.We computed five established evaluation metrics in order to determine which despeckling algorithm is most effective and optimal for real-time implementation. In addition, the experimental results have been demonstrated by filtered images and statistical data table.

An accurate and effective FMM-based approach for freehand 3D ultrasound reconstruction

Abstract Freehand three-dimensional ultrasound imaging is a highly attractive research area because it is capable of volumetric visualization and analysis of tissues and organs. The reconstruction algorithm plays a key role to the construction of three-dimensional ultrasound volume data with higher image quality and faster reconstruction speed. However, a systematic approach to such problem is still missing. A new fast marching method (FMM) for three-dimensional ultrasound volume reconstruction using the tracked and hand-held probe is proposed in this paper. Our reconstruction approach consists of two stages: bin-filling stage and hole-filling stage. Each pixel in the B-scan images is traversed and its intensity value is assigned to its nearest voxel in the bin-filling stage. For the efficient and accurate reconstruction, we present a new hole-filling algorithm based on the fast marching method. Our algorithm advances the interpolation boundary along its normal direction and fills the area closest to known voxel points in first, which ensure that the structural details of image can be preserved. Experimental results on both ultrasonic abdominal phantom and in vivo urinary bladder of human subject and comparisons with some popular algorithms are used to demonstrate its improvement in both reconstruction accuracy and efficiency.

Estimation of Respiration Rate from Three-Dimensional Acceleration Data Based on Body Sensor Network

Respiratory monitoring is widely used in clinical and healthcare practice to detect abnormal cardiopulmonary function during ordinary and routine activities. There are several approaches to estimate respiratory rate, including accelerometer(s) worn on the torso that are capable of sensing the inclination changes due to breathing. In this article, we present an adaptive band-pass filtering method combined with principal component analysis to derive the respiratory rate from three-dimensional acceleration data, using a body sensor network platform previously developed by us. In situ experiments with 12 subjects indicated that our method was capable of offering dynamic respiration rate estimation during various body activities such as sitting, walking, running, and sleeping. The experimental studies also suggested that our frequency spectrum-based method was more robust, resilient to motion artifact, and therefore outperformed those algorithms primarily based on spatial acceleration information.

Single Image Dehazing Using Color Attenuation Prior

In this paper, we propose a simple but powerful prior, color attenuation prior, for haze removal from a single input hazy image. By creating a linear model for modelling the scene depth of the hazy image under this novel prior and learning the parameters of the model by using a supervised learning method, the depth information can be well recovered. With the depth map of the hazy image, we can easily remove haze from a single image. Experimental results show that the proposed approach is highly efficient and it outperforms state-of-the-art haze removal algorithms in terms of the dehazing effect as well.

Sample entropy characteristics of movement for four foot types based on plantar centre of pressure during stance phase.

BackgroundMotion characteristics of CoP (Centre of Pressure, the point of application of the resultant ground reaction force acting on the plate) are useful for foot type characteristics detection. To date, only few studies have investigated the nonlinear characteristics of CoP velocity and acceleration during the stance phase. The aim of this study is to investigate whether CoP regularity is different among four foot types (normal foot, pes valgus, hallux valgus and pes cavus); this might be useful for classification and diagnosis of foot injuries and diseases. To meet this goal, sample entropy, a measure of time-series regularity, was used to quantify the CoP regularity of four foot types.MethodsOne hundred and sixty five subjects that had the same foot type bilaterally (48 subjects with healthy feet, 22 with pes valgus, 47 with hallux valgus, and 48 with pes cavus) were recruited for this study. A Footscan® system was used to collect CoP data when each subject walked at normal and steady speed. The velocity and acceleration in medial-lateral (ML) and anterior-posterior (AP) directions, and resultant velocity and acceleration were derived from CoP. The sample entropy is the negative natural logarithm of the conditional probability that a subseries of length m that matches pointwise within a tolerance r also matches at the next point. This was used to quantify variables of CoP velocity and acceleration of four foot types. The parameters r (the tolerance) and m (the matching length) for sample entropy calculation have been determined by an optimal method.ResultsIt has been found that in order to analyze all CoP parameters of velocity and acceleration during the stance phase of walking gait, for each variable there is a different optimal r value. On the contrary, the value m=4 is optimal for all variables.Sample entropies of both velocity and acceleration in AP direction were highly correlated with their corresponding resultant variables for r>0.91. The sample entropy of the velocity in AP direction was moderately correlated with the one of the acceleration in the same direction (r≥0.673), as well as with the resultant acceleration (r≥0.660). The sample entropy of resultant velocity was moderately correlated with the one of the acceleration in AP direction, as well as with the resultant acceleration (for the both r≥0.689). Moderate correlations were found between variables for the left foot and their corresponding variables for the right foot.Sample entropies of AP velocity, resultant velocity, AP acceleration, and resultant acceleration of the right foot as well as AP velocity and resultant velocity of the left foot were, respectively, significantly different among the four foot types.ConclusionsIt can be concluded that the sample entropy of AP velocity (or the resultant velocity) of the left foot, ML velocity, resultant velocity, ML acceleration and resultant acceleration could serve for evaluation of foot types or selection of appropriate footwear.

A Novel Nonlinear Regression Approach for Efficient and Accurate Image Matting

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.