Search

Achieving high visibility and high signal-to-noise ratio (SNR) from a single-shot image captured in low-light environments is an under-constrained problem. To cope with this issue, the intrinsic relationship between the image domain and the radiance domain is first established based on the human visual model, the atmospheric scattering model, and the camera imaging model, and the ideal exposure is derived. Using the illumination-reflection-noise prior, a new convex optimization by employed gradient constraint and the Krisch operator is then presented to estimate the noise-reduced illumination and reflection components. A high SNR image in the optimal exposure is generated in radiance domain, which is finally inversely mapped to obtain a high SNR image in image domain. Experimental results in subjective and objective tests show that the proposed algorithm has a high SNR and pleasant perception in comparison with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The formation of vortex rings in the left ventricular (LV) blood flow is a mechanism for optimized blood transport from the mitral valve inlet to aortic valve outlet, and the vorticity is an important measure of a well-functioning LV. However, due to lack of quantitative methods, the process of defining the boundary of a vortex in the LV and identifying the dominant vortex components has not been studied previously. The Lagrangian-averaged vorticity deviation (LAVD) can enable us to compute the trajectory integral of the normed difference of the vorticity from its spatial mean. Therefore, in this work, we have employed LAVD to identify the Lagrangian vortices and Eulerian vortices for measuring the vortex volume and vorticity in the LV blood flow. We found that during the LV ejection period, the positive (counterclockwise) and negative (clockwise) vorticity of patients are consistently stronger than those of the healthy groups, and the counterclockwise vortex volume of healthy groups (0.84+0.26 ml) is greater than that of patients (0.55+0.28 ml) during the pre-ejection period. Then, during the middle ejection phase, the counterclockwise vortex ring volume of patients (1.89+0.36 ml) exceeds that of healthy groups (1.38+0.43 ml). Finally, during the end-ejection period, the counterclockwise vortex ring volume of healthy subjects (0.61+0.17 ml) is the same as that of patients (0.60+0.19 ml). The results presented in this paper can provide new insights into the blood flow patterns within the LV. It can accurately indicate the role of vortices and vorticity values in intra-LV flow, and portray how cardiomyopathy (and its distorted contractile mechanism) can affect intra-LV flow patterns and mitigate adequate LV outflow. [ABSTRACT FROM AUTHOR]

This paper presents a gamma self‐correction method via chord distribution coding to eliminate the system's gamma effect. For this purpose, the prior gamma‐Gaussian characteristic value, which is extracted by chord distribution Gaussian fitting of the preset gamma's wrapped phase, is used to map the projector's gamma. Experimental results demonstrate that the proposed method has competitive accuracy and feasibility for fringe acquisition and gamma calculation. Thus, this method can be used for online gamma self‐correction in continuous three‐dimensional measurement. [ABSTRACT FROM AUTHOR]

Defocus blur detection aims to identify out-of-focus regions in a single image. Although defocus blur detection has attracted more and more attention in recent years, it still faces some challenges. In particular, the in-focus regions with low contrast are easily misidentified as out-of-focus regions. To address this problem, a perception-guided defocus blur detection method is proposed to estimate defocus blur amounts at edge locations from a single image based on the singular value decomposition (SVD) features. Inspired by the fact that blurring the clear region produces significant changes in SVD domain as compared with re-blurring the blurred one, new SVD features are extracted based on re-blurred singular value difference (RESVD) of the corresponding local gradient patches. Then, perceptual weight based on Just Noticeable Blur (JNB) is introduced to guide the sparse blur map estimation obtained with the SVD features. Finally, the full defocus blur map is constructed from the sparse defocus blur map by the Matting Laplace algorithm. Visual evaluations are conducted on the CUHK, DUT and CTCUG datasets, employing mean absolute error (MAE) and F β -measure as quantitative evaluation metrics. The experimental results demonstrate that the proposed defocus blur detection method is superior to 13 state-of-the-art methods. On the DUT dataset, the proposed method yields a high F β -measure (0.802) with a low MAE (0.081) compared to other methods (F β ≤ 0.799 , MAE ≥ 0.099). On the CUHK and CTCUG datasets, our method achieves the best balance between F β -measure and MAE. Furthermore, our method results in better visual effects than other methods regarding realism and quality. • SVD features distinguish focus via re-blurred singular value difference. • Perceptual weights modulate the sparse blur map obtained with SVD features. • Additional edge points are introduced to obtain a better full blur map. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive Weber-face method is presented to deal with varying lighting and extract illumination-insensitive representation for face recognition. A novel pixel-wise adaptive gamma transformation, which has been proved mathematically, is proposed to achieve a local uniform-illumination assumption in Weber-face. Next, the local binary patterns are extracted from the Weber-face images, and then further alleviate the effect of varying illumination. Experiments demonstrate that the proposed method achieves the high recognition rates of 99.55% and 96.63% on extended Yale B and CMU-PIE databases respectively, which outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

• The curved LCD is first applied to the PMD, which increases the measurable curvature than the planar LCD. • A calibration method is proposed for the system based on the 3D fiducials on the curved LCD rather than the 2D fiducials on the planar one. • Different from the traditional stereo-PMD in which only areas that has common FOV with phase information of two cameras can be reconstructed, the proposed stereo-PMD reconstruction and registration algorithm can reconstruct the surface in FOV of each camera, respectively, and then register together. • The reconstructed error of RMS is less than 100 nm for the concave mirror of ROC 1000 mm. Phase measuring deflectometry (PMD) technique is widely used to measure the specular surface. However, the Current PMD methods are generally based on the planar LCD for the measurement, which limits the measurable curvature of the surface under test (SUT). To increase the measurable range of curvature, this paper proposes a novel PMD method by using a curved LCD monitor. A calibration method based on the cylindrical coordinate system is introduced for the proposed system calibration. To extend the measurable range further, the curved LCD is applied in stereoscopic PMD. The partial surface of SUT in the field of view (FOV) of each camera and curved LCD are reconstructed with iterative algorithm respectively, the calibration parameters as well as the seed point are used for point cloud registration. Simulations show the advantage of a curved LCD over a planar one and the feasibility of the proposed method. The actual performance is demonstrated in the experiments for specular optics and a phone touchscreen. [ABSTRACT FROM AUTHOR]

• Develop a robust technique for cardiac flow analysis and automated vortex ring identification. • Propose a Lagrangian Averaged Vorticity Deviation (LAVD) inspired architecture to address cardiac vortex ring identification. • Implement the optical flow as interpolator to solve the problem of low temporal resolution in phase-contrast magnetic resonance imaging (PC-MRI) for improving the accuracy of LAVD. • Describe quantitatively the evolution of Euler vortices and Lagrangian vortices within the right atrium (RA). • Consider the Hough transform-based ellipse detection for automated vortex identification. To present and validate a method for automated identification of the Lagrangian vortices and Eulerian vortices for analyzing flow within the right atrium (RA), from phase contrast magnetic resonance imaging (PC-MRI) data. Our proposed algorithm characterizes the trajectory integral associated with vorticity deviation and the spatial mean of vortex rings, for the Lagrangian averaged vorticity deviation (LAVD) based identification and tracking of vortex rings within the heart chamber. For this purpose, the optical flow concept was adopted to interpolate the time frames between larger discrete frames, to minimize the error caused by constructing a continuous velocity field for the integral process of LAVD. Then the Hough transform was used to automatically extract the vortex regions of interest. The computed flow data within the RA of the participants' hearts was then used to validate the performance of our proposed method. In the paper, illustrations are provided for derived evolution of Euler vortices and Lagrangian vortices of a healthy subject. The visualization results have shown that our proposed method can accurately identify the Euler vortices and Lagrangian vortices, in the context of measuring the vorticity and vortex volume of the vortices within the RA chamber. Then the employment of Hough transform-based automated vortex extraction has improved the robustness and scalability of the LAVD in identifying cardiac vortices. The analytical results have demonstrated that the introduction of the Horn-Schunck optical flow can more accurately synthesize the intermediate PC-MRI to construct a continuous velocity field, compared with other interpolation methods. A novel analytical framework has been developed to accurately identify the flow vortices in the RA chamber based on Horn-Schunck optical flow and Hough transform. From the obtained analytical study results, the development and changes of dominant vortices within this cardiac chamber during the cardiac cycle can be acquired. This can provide to cardiologists a deeper understanding of the hemodynamics within the heart chambers. [ABSTRACT FROM AUTHOR]

Feature detection is the basis of many computer vision applications. However, the existing feature detectors have poor illumination robustness for various reasons. FAST is a very effective detection method, and is currently widely used for real-time feature detection. The threshold function in the traditional FAST method is a linear function and is unable to deal with the issue of illumination robustness. This paper proposes an illumination-robust feature detection method, the core is an adaptive threshold FAST. The proposed method constructs a threshold function based on neighborhood standard deviation, which successfully solves the problem that the traditional FAST has poor illumination robustness. In addition, a new image preprocessing method consisting of homomorphic filtering and histogram equalization is introduced to the front-end of the proposed method in order to improve the quality of the input image. Compared with state-of-the-art methods, the repeatibility rate of proposed method has been increased several times in the underexposure matching experiment, and the number of repeated features has been increased by dozens of times. Meanwhile, the number of repeated features increased by more than a third on average in the overexposed experiment. The experimental results strongly prove that the proposed method has significant advantages in terms of repeatibility rate, number of repeated features and detection stability evaluation indices. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a criterion for objective defocus blur measurement is theoretically derived from one image. The essential idea is to estimate the point spread function (PSF) from the line spread function (LSF), whereas the LSF is constructed from edge information. It is proven that an edge point corresponds to the local maximal gradient in a blurred image, and therefore edges can be extracted from blurred images by conventional edge detectors. To achieve high accuracy, local Radon transform is implemented and a number of LSFs are extracted from each edge. The experimental results on a variety of synthetic and real blurred images validate the proposed method. The algorithm can be implemented for image quality evaluation in vision-based applications as no reference images are needed. [Copyright &y& Elsevier]

Abstract: It has been found that facial thermograms vary with ambient temperature, as well as other internal and external conditions, and result in severe decline in the facial recognition rate. To tackle this problem, a skin heat transfer (SHT) model based on thermal physiology is derived in this paper. The proposed model converts the facial thermograms into blood-perfusion data, which is revealed to reduce the within-class scatter of face images. The advantage of the derived blood-perfusion data over the raw thermograms for recognition is analyzed by the normalized reverse cumulative histogram. It is shown that blood-perfusion data are more consistent in representing facial features. The experiments conducted on both same-session and time-lapse data have further demonstrated that (1) the blood-perfusion data are less sensitive to ambient temperature, physiological and psychological conditions if the human bodies are in the steady state; (2) for time-lapse data, the performance with the blood-perfusion data is nearly identical to that of the same-session data, while the recognition rate with the temperature data dramatically decreases in this case. The major contributions of this work are the well-grounded infrared data preprocessing and the corresponding face recognition system. [Copyright &y& Elsevier]

Abstract: This paper studies the problem of determining facial orientation without correspondences in distortion-related infrared images. To improve estimation accuracy and reduce sensitivity to noise and unavoidable error, a simple and robust method based on the single linkage clustering is proposed to simultaneously detect inlier set and estimate orientation angle under contaminated data. An iterative strategy is adopted to avoid random choice of link distance in the single linkage clustering. The experimental results indicate that the proposed method is substantially superior to the moment method. This method can also be extended to detect arbitrary objects with mirror symmetrical or nearly symmetrical property. [Copyright &y& Elsevier]

In this paper, a novel learning algorithm for dynamic fuzzy neural networks based on extended radial basis function neural networks, which are functionally equivalent to Takagi–Sugeno–Kang fuzzy systems, is proposed. The algorithm comprises 4 parts: (1) criteria of rules generation; (2) allocation of premise parameters; (3) determination of consequent parameters and (4) pruning technology. The salient characteristics of the approach are: (1) a hierarchical on-line self-organizing learning paradigm is employed so that not only parameters can be adjusted, but also the determination of structure can be self-adaptive without partitioning the input space a priori; (2) fast learning speed can be achieved so that the system can be implemented in real time. Simulation studies and comprehensive comparisons with some other learning algorithms demonstrate that the proposed algorithm is superior in terms of simplicity of structure, learning efficiency and performance. [ABSTRACT FROM AUTHOR]

Proposes an architecture of dynamic fuzzy neural networks (D-FNN) implementing Takagi-Sugeno-Kang (TSK) fuzzy systems based on extended radial basis function (RBF) neural networks. Architecture of the D-FNN; Description of a learning algorithm for the D-FNN.

Calibration is a critical step for the phase measuring deflectometry system. Existing calibration methods are mainly optimizing the calibration parameters with respect to the 2D re-projection error criterion. However, such a procedure cannot reduce metric errors in the practical application. Therefore, an accurate and practical calibration method is proposed. In which, conventional calibration means is first applied for the primary calibration. Then, a precise square planar mirror is used for the optimization of system calibration parameters. All the intrinsic and extrinsic parameters are considered as a global multi-objective optimization problem. Three metric error criteria are introduced to evaluate the 3D reconstruction accuracy of the reference mirror. Compared with classical calibration means, which apply the parameter optimization in 2D image space to minimize the re-projection errors, the proposed optimization approach is executed in 3D space directly. An experiment and comparison are conducted to verify that the proposed optimal calibration approach can effectively reduce the system deviation and to improve the system measurement accuracy. [ABSTRACT FROM AUTHOR]

Estimating the Direction of Arrival (DOA) is a basic and crucial problem in array signal processing. The existing DOA methods fail to obtain reliable and accurate results when noise and reverberation occur in real applications. In this paper, an accurate and robust estimation method for estimating the DOA of sources signal is proposed. Incorporating the Estimating Signal Parameters via Rotational Invariance Techniques (ESPRIT) algorithm with the RANdom SAmple Consensus (RANSAC) algorithm gives rise to the RAN-ESPRIT method, which removes outliers automatically in noise-corrupted environments. In this work, a uniform circular array (UCA) is converted into a virtual uniform linear array (ULA) to begin with. Then, the covariance matrix of the received signals of the virtual linear array is reconstructed, and the ESPRIT algorithm is deployed to estimate initial DOA of the source signal. Finally, the modified RANSAC method with automatically selected thresholds is used to fit the source signal to obtain accurate DOA. The proposed method can remove the unreliable DOA feature data and leads to more accuracy of DOA estimation of source signals in reverberation environments. Experimental results demonstrate that the proposed method is more robust and efficient compared to the traditional methods (i.e., ESPRIT, TLS-ESPRIT). [ABSTRACT FROM AUTHOR]

It is challenging to convert a hazy color image into a gray-scale image because the color contrast field of a hazy image is distorted. In this paper, a novel decolorization algorithm is proposed to transfer a hazy image into a distortion-recovered gray-scale image. To recover the color contrast field, the relationship between the restored color contrast and its distorted input is presented in CIELab color space. Based on this restoration, a nonlinear optimization problem is formulated to construct the resultant gray-scale image. A new differentiable approximation solution is introduced to solve this problem with an extension of the Huber loss function. Experimental results show that the proposed algorithm effectively preserves the global luminance consistency while represents the original color contrast in gray-scales, which is very close to the corresponding ground truth gray-scale one. [ABSTRACT FROM AUTHOR]

It is very challenging to accurately detect smoke from images because of large variances of smoke colour, textures, shapes and occlusions. To improve performance, the authors combine dual threshold AdaBoost with staircase searching technique to propose and implement an image smoke detection method. First, extended Haar‐like features and statistical features are efficiently extracted from integral images from both intensity and saturation components of RGB images. Then, a dual threshold AdaBoost algorithm with a staircase searching technique is proposed to classify the features of smoke for smoke detection. The staircase searching technique aims at keeping consistency of training and classifying as far as possible. Finally, dynamic analysis is proposed to further validate the existence of smoke. Experimental results demonstrate that the proposed system has a good robustness in terms of early smoke detection and low false alarm rate, and it can detect smoke from videos with size of 320 × 240 in real time. [ABSTRACT FROM AUTHOR]

RRT* (Rapidly-exploring Random Tree Star), as a variant of RRT (Rapidly-exploring Random Tree), is widely used to solve path planning problems because of its asymptotic optimality. However, the algorithm is inefficient due to the high initial path cost and the slow convergence rate. In this paper, we propose a More Quickly-RRT* (MQ-RRT*) path planning algorithm based on optimized sampling points to solve the problems. A sparse sampling mechanism is proposed in MQ-RRT* to improve the global search efficiency by reducing repetitive sampling. To make the random tree oriented when expanding, a dynamic goal-biased strategy is proposed, which can reduce the sampling time. Like Q-RRT* (Quick-RRT*), MQ-RRT* expands the set of possible parent nodes in the ChooseParent and Rewire phases, which reduces the path cost. On this basis, a method for creating a new parent node close to the obstacle is proposed. The creation process can be divided into two steps: Remove-tips and CreateNodes , which further reduces the cost of path generation and makes the path smoother by using the triangle inequality principle. Finally, numerical simulations are used to compare the proposed algorithm with RRT*, Q-RRT*, GuILD (Guided Incremental Local Densification), and F-RRT* (Fast-RRT*), which verifies that the proposed algorithm has certain advantages in path cost, convergence rate, and path smoothness. [ABSTRACT FROM AUTHOR]

Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free images with high PSNR and SSIM values for synthetic hazy images but with low contrast, and even some remaining haze for real-world hazy images. In this paper, a novel single image dehazing algorithm is introduced by combining model-based and data-driven approaches. Both transmission map and atmospheric light are first estimated by the model-based methods, and then refined by dual-scale generative adversarial networks (GANs) based approaches. The resultant algorithm forms a neural augmentation which converges very fast while the corresponding data-driven approach might not converge. Haze-free images are restored by using the estimated transmission map and atmospheric light as well as the Koschmieder’s law. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images. [ABSTRACT FROM AUTHOR]

Audio–Visual Segmentation (AVS) aims to extract the sounding objects from a video. The current learning-based AVS methods are often supervised, which rely on specific task data annotations and expensive model training. Recognizing that the video background captured by a static camera is represented as a low-rank matrix, we introduce the non-convex robust principal component analysis into AVS task in this paper. This approach is unsupervised and only relies on input data patterns. Specifically, the proposed method decomposes each modality into the sum of two parts: the low-rank part that represents the background audio and visual information, and the sparse part that represents the foreground information. Furthermore, CUR decomposition is employed at each iteration to reduce the computational complexity in optimization. The experimental results also show that the proposed AVS outperforms the supervised methods on AVS-Bench Single-Source datasets. • Firstly introduces non-convex RPCA for Audio–Visual Segmentation. • Applies CUR decomposition to reduce computational complexity. • The task of unsupervised Audio–Visual Segmentation. • Demonstrates efficiency and effectiveness results on the AVS dataset. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we prove that the principal component analysis (PCA) and the linear discriminant analysis (LDA) can be directly implemented in the discrete cosine transform (DCT) domain and the results are exactly the same as the one obtained from the spatial domain. In some applications, compressed images are desirable to reduce the storage requirement. For images compressed using the DCT, e.g., in JPEG or MPEG standard, the PCA and LDA can be directly implemented in the DCT domain such that the inverse DCT transform can be skipped and the dimensionality of the original data can be initially reduced to cut down computational cost. [Copyright &y& Elsevier]

A small ISO and a small exposure time are usually used to capture an image in back- or low-light condition which results in an image with negligible motion blur and small noise but looks dark. In this paper, a single image brightening algorithm is introduced to brighten such an image. The proposed algorithm includes a unique hybrid learning framework to generate two virtual images with large exposure times. The virtual images are first generated via intensity mapping functions (IMFs) which are computed using camera response functions (CRFs) and this is a model-driven approach. Both the virtual images are then enhanced by using a data-driven approach, i.e. a residual convolutional neural network to approach the ground truth images. The model-driven approach and the data-driven one compensate each other in the proposed hybrid learning framework. The final brightened image is obtained by fusing the original image and two virtual images via a multi-scale exposure fusion algorithm with properly defined weights. Experimental results show that the proposed brightening algorithm outperforms existing algorithms in terms of MEF-SSIM metric. [ABSTRACT FROM AUTHOR]

Feature point detection is the basis of computer vision, and the detection methods with geometric invariance and illumination invariance are the key and difficult problem in the field of feature detection. This paper proposes an illumination-invariant feature point detection method based on neighborhood information. The method can be summarized into two steps. Firstly, the feature points are divided into eight types according to the number of connected neighbors. Secondly, each type of feature points is classified again according to the position distribution of neighboring pixels. The theoretical deduction proves that the proposed method has lower computational complexity than other methods. The experimental results indicate that, when the photometric variation of the two images is very large, the feature-based detection methods are usually inferior, while the learning-based detection methods performs better. However, our method performs better than the learning-based detection method in terms of the number of feature points, the number of matching points, and the repeatability rate stability. The experimental results demonstrate that the proposed method has the best illumination robustness among state-of-the-art feature detection methods. [ABSTRACT FROM AUTHOR]

Capturing high-quality images via mobile devices in low-light or backlighting conditions is very challenging. In this paper, a new, single image brightening algorithm is proposed to enhance an image captured in low-light conditions. Two virtual images with larger exposure times are generated to increase brightness and enhance fine details of the underexposed regions. In order to reduce the brightness change, the virtual images are generated via intensity mapping functions (IMFs) which are computed using available camera response functions (CRFs). To avoid possible color distortion in the virtual image due to one-to-many mapping, a least square minimization problem is formulated to determine brightening factors for all pixels in the underexposed regions. In addition, an edge-preserving smoothing technique is adopted to avoid noise in the underexposed regions from being amplified in the virtual images. The final brightened image is obtained by fusing the original image and two virtual images via a gradient domain guided image filtering (GGIF) based multiscale exposure fusion (MEF) with properly defined weights for all the images. Experimental results show that the relative brightness and color are preserved better by the proposed algorithm. The details in bright regions are also preserved well in the final image. The proposed algorithm is expected to be useful for computational photography on smart phones. [ABSTRACT FROM AUTHOR]

It is challenging to remove rain-streaks from a single image because the rain-streaks are spatially varying. Although data-driven rain removal methods have reported promising performance recently, there are still some defects, such as data dependency and insufficient interpretation. A single image deraining algorithm that combines model-based and data-driven approaches is introduced. First, high-frequency information extracted by an improved weighted guided image filter (iWGIF) is used to learn the rain-streaks to avoid interference from other information through the input image. Then, the input and the learned rain streaks are transferred adaptively from the image domain to the feature domain to learn useful features for high quality image deraining. Finally, networks with multi-scale attention mechanisms are used to restore high-quality images from the latent features. Experiments show that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both qualitative and quantitative measures. [ABSTRACT FROM AUTHOR]

In this paper, the filtering problem for a class of switched positive systems with dwell time is investigated. A novel weighted-average technique is proposed for filter design such that the final estimate of the unmeasurable outputs of the considered system is more accurate than that of traditional approaches. The main contributions of this paper are summarized as follows: By exploiting the positivity and characteristics of switched positive systems with dwell time, a candidate linear copositive Lyapunov function, which is both quasi-time-dependent and mode-dependent, is presented to establish the closed-loop stability of the considered systems. Upon the established closed-loop stability, less conservative bounded positive filters (both upper-bound and lower-bound filter) with ℓ1 disturbance attenuation performance are designed for the considered system. By introducing a proper weight, a weighted-average approach, which is more general than the bounded filter design method, is proposed for filter design. The worst ℓ1 disturbance attenuation performance of the novel developed filter is evaluated. Both the bounded filters and the weighted-average filter are designed by solving standard linear programming problems. A numerical example illustrates the effectiveness of the proposed approach. Copyright © 2017 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

• We proposed a novel AdaptiveWeighted Guided Image Filtering algorithm which outperforms the existing guided filters to preserve accurate edges. • We designed four special cases of the adaptive adjustment algorithm to remove the noise while enhancing depth details. • We proposed a new strategy based on AWGIF algorithm for depth enhancement in Shape-From-Focus. • Our proposed method are applied to the emerging AR/VR on hand-held devices in real-time. Existing shape from focus (SFF) techniques cannot preserve depth edges and fine structural details from a sequence of multi-focus images. Moreover, noise in the sequence affects the accuracy of the depth map. In this paper, a novel depth enhancement algorithm for the SFF based on an adaptive weighted guided image filtering (AWGIF) is proposed to address the above issues. The AWGIF is applied to decompose an initial depth map estimated by the traditional SFF into base and detail layers. In order to preserve the edges accurately in the refined depth map, the guidance image is constructed from the sequence, and the coefficient of the AWGIF is utilized to suppress the noise while enhancing the fine depth details. Experiments on real and synthetic objects demonstrate the superiority of our algorithm in terms of anti-noise, and the ability to preserve depth edges and fine structural details w.r.t. existing methods. [ABSTRACT FROM AUTHOR]

It is known that local filtering-based edge-preserving smoothing techniques suffer from halo artifacts. In this paper, a weighted guided image filter (WGIF) is introduced by incorporating an edge-aware weighting into an existing guided image filter (GIF) to address the problem. The WGIF inherits advantages of both global and local smoothing filters in the sense that: 1) the complexity of the WGIF is $O(N)$ for an image with $N$ pixels, which is same as the GIF and 2) the WGIF can avoid halo artifacts like the existing global smoothing filters. The WGIF is applied for single image detail enhancement, single image haze removal, and fusion of differently exposed images. Experimental results show that the resultant algorithms produce images with better visual quality and at the same time halo artifacts can be reduced/avoided from appearing in the final images with negligible increment on running times. [ABSTRACT FROM AUTHOR]

• U-Net with Gaussian blur and channel weight is developed for segmenting the left atrium in MRI. • Left atrium is reconstructed into a dynamical 3D model for diagnosis of left atrial enlargement(LAE). • State-of-the-arts left atrial segmentation methods such as U-Net, SegNet, and FCN-8 were compared. • Potential clinical applications in accurately evaluating LAE patients. Left atrial enlargement (LAE) is an anatomical variation of the left atrium and the result of the long-term increase of left atrial pressure. Most of the increase in stress or volume is due to potential cardiovascular disease. Studies have shown that LAE can independently predict the development of clinically significant cardiovascular disease and heart failure. If the left atrial volume is accurately measured, it will be an essential indicator of human health and an essential means for doctors to find patients' potential diseases. We can analyze the dynamic changes in the left atrial structure and analyze left atrial dilation. However, manual segmentation was inefficient and error-prone before the 3D reconstruction of the left atrium. In order to solve this problem, a convolution neural network (CNN) method based on cardiac magnetic resonance image (MRI) is proposed to automatically segment the left atrial region. In this paper, we have proposed and developed a novel U-Net with Gaussian blur and channel weight neural network (GCW-UNet) to automatically segment the left atrial region in the MRI of a patient with LAE. After Gaussian blur, different resolutions of the MRI are obtained. High-resolution MRI clearly shows the detailed features of the left atrium, while low-resolution MRI clearly shows the overall outline of the left atrium, which can solve the problem of more minor MRI features. Adaptive channel weights can enhance the atrial segmentation capability of the network. Compared with the state-of-the-art left atrial segmentation methods, our CNN-based technique results in the segmentation of the left atrium being closer to the manual segmentation by an experienced radiologist. On the test datasets, the mean Dice similarity coefficient reaches 93.57%. Firstly, MRI has a small number of imaging artifacts, which results in low segmentation accuracy. Our method successfully solves the problem. Secondly, due to the high similarity between the background (the area outside the left atrium) and the foreground (the left atrium) in MRI, traditional neural networks misclassify the background as the foreground. Our GCW-Unit can address the imbalanced number of pixels between the foreground and background. Finally, after segmenting the left atrium in the MRI by GCW-Unit, we reconstructed the left atrium to model a three-dimensional heart of a patient suffering from LAE. Based on the different time frames of one heartbeat, we could present the dynamics of the left atrial structure during a cardiac cycle. This can better assist in the evaluation of LAE in heart patients. [ABSTRACT FROM AUTHOR]

Highlights: [•] We propose a method to detect visually salient objects in computer rendered images. [•] We calculates saliency by measuring object-level contrast. [•] Both color and color distribution is considered in contrast computation. [•] A new suppression operator is designed. [ABSTRACT FROM AUTHOR]

It is very challenging to synthesize a high dynamic range (HDR) image from multiple differently exposed low dynamic range images when there are moving objects in the images. This is due to the fact that the moving objects will cause ghosting artifacts to appear in the synthesized HDR image. To prevent such artifacts, a patching algorithm is required to correct motion regions such that all the moving objects are synchronized in the differently exposed images. In this paper, a new optimization problem is formulated to correct the motion regions of the multiple differently exposed images by considering both spatial and temporal consistencies. The resultant scheme is a hybrid patching scheme composed of a correction method which is an intensity mapping function at pixel level, and a hole-filling method that uses block-level template matching. The proposed patching scheme is not only robust to large intensity changes in these input images, but also at regions that are over-or under-exposed. Experimental results show that the proposed method is able to prevent ghosting artifacts from appearing in the final synthesized HDR image. [ABSTRACT FROM AUTHOR]

Pose estimation is a particularly important link in the task of robotic bin-picking. Its purpose is to obtain the 6D pose (3D position and 3D posture) of the target object. In real bin-picking scenarios, noise, overlap, and occlusion affect accuracy of pose estimation and lead to failure in robot grasping. In this paper, a new point-pair feature (PPF) descriptor is proposed, in which curvature information of point-pairs is introduced to strengthen feature description, and improves the point cloud matching rate. The proposed method also introduces an effective point cloud preprocessing, which extracts candidate targets in complex scenarios, and, thus, improves the overall computational efficiency. By combining with the curvature distribution, a weighted voting scheme is presented to further improve the accuracy of pose estimation. The experimental results performed on public data set and real scenarios show that the accuracy of the proposed method is much higher than that of the existing PPF method, and it is more efficient than the PPF method. The proposed method can be used for robotic bin-picking in real industrial scenarios. [ABSTRACT FROM AUTHOR]

Inspired by the observation that rougher surfaces yield blurrier reflective images, a novel roughness estimation method via line blur functions (LBF) of edges reflected from such surfaces is proposed in this paper. We first reveal that the point blur function (PBF) is determined by the surface roughness base on the point blur mechanism, and mathematically analyze that the LBF can be derived from its correspondent PBF in the perpendicular direction of edges. Then, the variance of Gaussian curve which fits the LBF is mapped to the surface roughness measured by the stylus profilometry. This mapped linear function is finally applied to measure the roughness of test samples. The experimental results show that when roughness is under 0.29 μ m, the proposed method is comparable to or even higher than the stylus method in accuracy, and has advantages of convenience, high efficiency and non-contact. • Roughness of surfaces with weak textures is estimated from reflective images. • The PBF and the LBF are defined to evaluate the blur degree of reflective images. • The LBF can be derived from the correspondent PBF. • The surface roughness is formulated in terms of the LBF. [ABSTRACT FROM AUTHOR]

• Develop robust segmentation techniques to segment left ventricle (LV) from ultrasound images. • Use machine learning (ML) techniques such as active contour (AC) and convolutional neural network (CNN) for segmentation. • Perform comparative analysis in terms of the ventricular area (VA), the ventricular maximum diameter (VMXD), the ventricular minimum diameter (VMID) and the ventricular long axis angle (AVLA). • Compare automatic and visual approaches using the Dice similarity coefficient, Jaccard indices and Hausdorff distance to estimate the agreement of LV segmented. • Prove the underlying techniques of LV segmentation is useful and practical. In cardiology, ultrasound is often used to diagnose heart disease associated with myocardial infarction. This study aims to develop robust segmentation techniques for segmenting the left ventricle (LV) in ultrasound images to check myocardium movement during heartbeat. The proposed technique utilizes machine learning (ML) techniques such as the active contour (AC) and convolutional neural networks (CNNs) for segmentation. Medical experts determine the consistency between the proposed ML approach, which is a state-of-the-art deep learning method, and the manual segmentation approach. These methods are compared in terms of performance indicators such as the ventricular area (VA), ventricular maximum diameter (VMXD), ventricular minimum diameter (VMID), and ventricular long axis angle (AVLA) measurements. Furthermore, the Dice similarity coefficient, Jaccard index, and Hausdorff distance are measured to estimate the agreement of the LV segmented results between the automatic and visual approaches. The obtained results indicate that the proposed techniques for LV segmentation are useful and practical. There is no significant difference between the use of AC and CNN in image segmentation; however, the AC method could obtain comparable accuracy as the CNN method using less training data and less run-time. [ABSTRACT FROM AUTHOR]

Geometric model fitting is a fundamental issue in computer vision, and the fitting accuracy is affected by outliers. In order to eliminate the impact of the outliers, the inlier threshold or scale estimator is usually adopted. However, a single inlier threshold cannot satisfy multiple models in the data, and scale estimators with a certain noise distribution model work poorly in geometric model fitting. It can be observed that the residuals of outliers are big for all true models in the data, which makes the consensus of the outliers. Based on this observation, we propose a preference analysis method based on residual histograms to study the outlier consensus for outlier detection in this paper. We have found that the outlier consensus makes the outliers gather away from the inliers on the designed residual histogram preference space, which is quite convenient to separate outliers from inliers through linkage clustering. After the outliers are detected and removed, a linkage clustering with permutation preference is introduced to segment the inliers. In addition, in order to make the linkage clustering process stable and robust, an alternative sampling and clustering framework is proposed in both the outlier detection and inlier segmentation processes. The experimental results also show that the outlier detection scheme based on residual histogram preference can detect most of the outliers in the data sets, and the fitting results are better than most of the state-of-the-art methods in geometric multi-model fitting. [ABSTRACT FROM AUTHOR]

The poor operating conditions of fluid lubrication equipment during the start-up process are due to the resistance of the high-viscosity lubricating liquid. Moreover, the excessive reduction in fluid viscosity due to the elevated temperature resulting from power consumption during prolonged operation is not conducive to the generation of dynamic pressure. In this study, we examine the effect of energy accumulation and boundary slip on the laminar flow of a liquid between a pair of rotating plates. The experiments are conducted using a rotary rheometer, with polymethyl methacrylate (PMMA) as the thermal insulation material and polytetrafluoroethylene (PTFE) as the slip drag reduction material, and a three-dimensional simulation model is established. This model is derived by combining the energy equation including the slip length and the heat conduction equation. Thus, the temperature changes over time are predicted by this model, and the model accuracy is verified by experiments. The results reveal the following points: 1) boundary slips function as a drag reduction mechanism for short-time continuous operation; 2) under prolonged operation, the slip reduces the extent of the oil viscosity decrease and clear control of the elevated temperature by the boundary slip is observed. [ABSTRACT FROM AUTHOR]