Search

• Coal isothermal adsorption/desorption deformation experiments with liquid nitrogen quenching were carried out. • The variation of coal gas adsorption capacity and volumetric strain under liquid nitrogen cold leaching were investigated. • The relationship between coal adsorption capacity and volumetric strain under liquid nitrogen cold leaching was discussed. The research on gas adsorption deformation characteristics of coal under liquid nitrogen cold soaking deserves investigation, as most of the investigation efforts in this field are in a preliminary stage. In this article, the experiments of coal adsorption deformation under different times of liquid nitrogen cold soaking (0, 1, 3, 5, 7 and 9) were carried out. The variation of coal gas adsorption capacity and volumetric strain under different times of liquid nitrogen cold soaking were investigated. Based on thermodynamics, the adsorption strain model of coal was developed, and the relationship between coal adsorption capacity and volumetric strain was discussed. The research results show that: (i) the coal adsorption capacity and volumetric strain both gradually decrease with the increase of the number of liquid nitrogen cold soaking; (ii) the saturated gas adsorption capacity and limit volume strain of coal both show a decreasing trend with the increase of liquid nitrogen cold soaking times; (iii) the volumetric strain of coal under the different times of liquid nitrogen cold soaking first accelerates and then slowly rises with the increase of adsorption capacity. After liquid nitrogen cold soaking, the volumetric strain growth rate of coal gradually decreases; (iv) the coal under different cold soaking times reaches the limit volumetric strain at a pressure (P) that is higher than the pressure (p) required to reach the saturation adsorption capacity, and the values of p and P both show a decreasing trend with the increase of liquid nitrogen cold soaking times; (v) the model results have good predictive effect. [ABSTRACT FROM AUTHOR]

• The maximized entropy term with clear prediction meaning under simplex is introduced to avoid two trivial solutions obtained from primal clustering model on neighbors and pure pursuit for entropy maximization, respectively. • The Laplacian rank constraint with ℓ 0 -norm is developed to dynamically obtain sparse similarity matrix with exact c connected components, which avoids extra discretization process in classical SC. • ℓ 0 -norm constraint assigns fused neighbors for each sample, accelerates the spectral analysis, and assists rank constraint to discover c connected components more accurately. • A novel monotonic function optimization method is proposed to tackle the ℓ 0 -norm constraint with fixed pseudo-label matrix, which elegantly reveals the consistence between graph sparsity and neighbor assignment. Graph-based clustering has been considered as an effective kind of method in unsupervised manner to partition various items into several groups, such as Spectral Clustering (SC). However, there are three species of drawbacks in SC: (1) The effects of clustering is sensitive to the affinity matrix that is fixed by original data. (2) The input affinity matrix is simply based on distance measurement, which lacks of clear physical meaning under probabilistic prediction. (3) Additional discretization procedures still need to be operated. To cope with these issues, we propose a new clustering model, which refers to Entropy Regularization for unsupervised Clustering with Adaptive Neighbors (ERCAN), to dynamically and simultaneously update affinity matrix and clustering results. Firstly, the maximized entropy regularization term is introduced in probability model to avoid trivial similarity distributions. Additionally, we newly introduce the Laplacian rank constraint with ℓ 0 -norm to construct adaptive neighbors for sparsity and strength segmentation ability without extra discretization process. Finally, we present a novel monotonic function optimization method, which reveals the consistence between graph sparsity and neighbor assignment, to address the ℓ 0 -norm constraint in alternative optimization process. Comprehensive experiments show the superiority of our method with promising results. [ABSTRACT FROM AUTHOR]

Detecting humans, faces, and other objects is important for pose estimation, behaviour analysis, and recognition. Most of the existing detection methods exploit sliding-window technique that typically evaluates image patches at uniform grids, with constant pixel strides along horizontal and vertical directions in an image. This approach can lead to excessively redundant computation since target object instances are relatively rare events compared to non-objects of the background. Therefore, most of the computation is unnecessarily wasted on the background. In this paper, to deal with this problem, we propose to scan the image using adaptive instead of fixed (unchanged) strides. That is, a high response of current sliding window generates small strides for the subsequent sliding windows in both horizontal and vertical directions, which means an object instance is likely to exist around. Otherwise, a low response gives large pixel strides and results in sparse sampling on the background. As a result, the areas of potential object instances are densely sampled and the areas of non-objects are sparsely sampled, leading to the reduction of total computation cost without loss of detection accuracy. Experimental results on face detection demonstrate the high efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The analysis of 3D medical images becomes necessary since the 3D imaging techniques have been more and more widely applied in medical applications. This paper introduces a novel segmentation method for extracting objects of interest (OOI) in 3D ultrasound images. In the proposed method, a bilateral filtering model is first applied to a 3D ultrasound volume data set for speckle reduction. We then take advantage of graph theory to construct a 3D graph, and merge sub-graphs into larger one during the segmentation process. Therefore, the proposed method can be called a 3D graph-based segmentation algorithm. After the mergence of sub-graphs, a set of minimum spanning trees each of which corresponds to a 3D sub-region is generated. In terms of segmentation accuracy, the experiments using an ultrasound fetus phantom, a resolution phantom and human fingers demonstrate that the proposed method outperforms the 3D Snake and Fuzzy C means clustering methods, indicating improved performance for potential clinical applications. [ABSTRACT FROM AUTHOR]

Articulated human pose estimation in unconstrained conditions is a great challenge. We propose a deep structure that represents a human body in different granularity from coarse-to-fine for better detecting parts and describing spatial constrains between different parts. Typical approaches for this problem just utilize a single level structure, which is difficult to capture various body appearances and hard to model high-order part dependencies. In this paper, we build a three layer Markov network to model the body structure that separates the whole body to poselets (combined parts) then to parts representing joints. Parts at different levels are connected through a parent–child relationship to represent high-order spatial relationships. Unlike other multi-layer models, our approach explores more reasonable granularity for part detection and sophisticatedly designs part connections to model body configurations more effectively. Moreover, each part in our model contains different types so as to capture a wide range of pose modes. And our model is a tree structure, which can be trained jointly and favors exact inference. Extensive experimental results on two challenging datasets show the performance of our model improving or being on-par with state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

To fill the semantic gap between the predictive power of computational saliency models and human behavior, this paper proposes to predict where people look at using spatial-aware object-level cues. While object-level saliency has been recently suggested by psychophysics experiments and shown effective with a few computational models, the spatial relationship between the objects has not yet been explored in this context. We in this work for the first time explicitly model such spatial relationship, as well as leveraging semantic information of an image to enhance object-level saliency modeling. The core computational module is a graphlet-based (i.e., graphlets are moderate-sized connected subgraphs) deep architecture, which hierarchically learns a saliency map from raw image pixels to object-level graphlets (oGLs) and further to spatial-level graphlets (sGLs). Eye tracking data are also used to leverage human experience in saliency prediction. Experimental results demonstrate that the proposed oGLs and sGLs well capture object-level and spatial-level cues relating to saliency, and the resulting saliency model performs competitively compared with the state-of-the-art. [ABSTRACT FROM PUBLISHER]

In this paper, a new fine-grained image categorization system that improves spatial pyramid matching is developed. In this method, multiple cells are combined into cellets in the proposed categorization model, which are highly responsive to an object's fine categories. The object components are represented by cellets that can connect spatially adjacent cells within the same pyramid level. Here, image categorization can be formulated as the matching between the cellets of corresponding images. Toward an effective matching process, an active learning algorithm that can effectively select a few representative cells for constructing the cellets is adopted. A linear-discriminant-analysis-like scheme is employed to select discriminative cellets. Then, fine-grained image categorization can be conducted with a trained linear support vector machine. Experimental results on three real-world data sets demonstrate that our proposed system outperforms the state of the art. [ABSTRACT FROM PUBLISHER]

This paper presents a fast and robust level set method for image segmentation. To enhance the robustness against noise, we embed a Markov random field (MRF) energy function to the conventional level set energy function. This MRF energy function builds the correlation of a pixel with its neighbors and encourages them to fall into the same region. To obtain a fast implementation of the MRF embedded level set model, we explore algebraic multigrid (AMG) and sparse field method (SFM) to increase the time step and decrease the computation domain, respectively. Both AMG and SFM can be conducted in a parallel fashion, which facilitates the processing of our method for big image databases. By comparing the proposed fast and robust level set method with the standard level set method and its popular variants on noisy synthetic images, synthetic aperture radar (SAR) images, medical images, and natural images, we comprehensively demonstrate the new method is robust against various kinds of noises. In particular, the new level set method can segment an image of size $500 \times 500$ within 3 s on MATLAB R2010b installed in a computer with 3.30-GHz CPU and 4-GB memory. [ABSTRACT FROM AUTHOR]

Realistic action recognition has been one of the most challenging research topics in computer vision. The existing methods are commonly based on non-probabilistic classification, predicting category labels but not providing an estimation of uncertainty. In this paper, we propose a probabilistic framework using Gaussian processes (GPs), which can tackle regression problems with explicit uncertain models, for action recognition. A major challenge for GPs when applied to large-scale realistic data is that a large covariance matrix needs to be inverted during inference. Additionally, from the manifold perspective, the intrinsic structure of the data space is only constrained by a local neighborhood and data relationships with far-distance usually can be ignored. Thus, we design our GPs covariance matrix via the proposed ℓ 1 construction and a local approximation (LA) covariance weight updating method, which are demonstrated to be robust to data noise, automatically sparse and adaptive to the neighborhood. Extensive experiments on four realistic datasets, i.e., UCF YouTube, UCF Sports, Hollywood2 and HMDB51, show the competitive results of ℓ 1 -GPs compared with state-of-the-art methods on action recognition tasks. [ABSTRACT FROM AUTHOR]

Aurora is the typical ionosphere track generated by the interaction of solar wind and magnetosphere, whose modality and variation are significant to the study of space weather activity. A new aurora classification algorithm based on biologically inspired features (BIFs) and discriminative locality alignment (DLA) is proposed in this paper. First, an aurora image is represented by the BIFs, which combines the C1 units from the hierarchical model of object recognition in cortex and the gist features from the saliency map; then, the manifold learning method called DLA is used to obtain the effective sparse representation for auroras based on BIFs; finally, classification results using support vector machine and nearest neighbour with three sets of features: the C1 unit features, the gist features and the BIFs illustrate the effectiveness and robustness of our method on the real aurora image database from Chinese Arctic Yellow River Station. [ABSTRACT FROM PUBLISHER]

A transmission line is one of the most hazardous objects to low altitude flying aircraft. Due to its extremely tiny size and unsalient visual features, transmission line detection (TLD) is a well-recognized problem. In this paper, a novel TLD method is proposed with the assistance of the spatial correlation between pylon and line for TLD. First, a unidirectional spatial mapping is built up to describe the pylon line spatial correlation. Then, the proposed pylon line spatial correlation and other line features are integrated into a Bayesian framework, which is trained in advance and used to estimate the probability of one line segment belonging to a transmission line. Compared with three other line-based TLD methods, the experimental results demonstrate that the proposed method can obtain better detection performance with higher detection rates and much lower false alarm rates. [ABSTRACT FROM AUTHOR]

• In order to implement clustering task, the proposed approach fully utilizes multiple view features to learn a consensus representation. Specifically, it makes the common consensus representation be close to each view initial affinity matrix as much as possible. Moreover, to capture principal components of different views, the nuclear norm is applied to the learned consensus representation. • Considering that each view feature is inclined to explore specific properties, therefore, the proposed method assigns different weight for each view feature in the form of exponential flatten. • An efficient alternative iteration algorithm is exploited to solve the proposed optimization problem. In addition, extensive experiments are conducted on four multi-view data sets without noises and one multi-view data set with"salt and pepper" noises to demonstrate the superiority of proposed SMSC_NN method. Multi-view clustering attracts more and more attention due to the fact that it can utilize the complementary and compatible information from multi-view data sets. In many graph-based multi-view clustering approaches, the graph quality is important since it influences the following clustering performance. Therefore, learning a high quality similarity graph is desired. In this paper, we propose a novel clustering method which is named as Self-weighting Multi-view Spectral Clustering based on Nuclear Norm (SMSC_NN). Specifically, to fully utilize the multiple view features, the common consensus representation is learned. Moreover, to capture the principal components from various view features, the nuclear norm is introduced which can make the view-specific information be well explored. Further, due to the fact that each view feature denotes a sort of specific property, the adaptive weights are assigned instead of equal view weights. In order to verify the effectiveness of the proposed method, four multi-view data sets are used to conduct the clustering experiments. Extensive experimental results demonstrate the superiority of the proposed method comparing with state-of-the-art multi-view clustering approaches. In addition, the proposed approach is experimented on the Cal101-20 data set with "salt and pepper" noises, and experimental results verify that the proposed SMSC_NN method can remain robust to noises. [ABSTRACT FROM AUTHOR]

The article offers brief profiles of editorial board Leman Akoglu, Justin Levandoski, and Carlos Ordonez, who contributed to the writing of the journal.

Abstract: Flying bird detection (FBD) is critical in avoiding bird–aircraft collisions. Most existing approaches rely on motion detection to identify the flying bird, since it is a typical moving object. However, when there exist other moving objects, those methods often fail to distinguish flying birds from those objects due to the insufficiency of feature description. In this paper, we introduce a novel hierarchical feature model exploiting shape and shape dynamics to improve the ability of representing a flying bird, and then apply it to the FBD problem. As the shape of a flying bird is very distinctive in geometric structures and could provide discriminating spatial information, an improved shape context feature descriptor is proposed at the lower level to capture the spatial relations in bird shape. Then the shape descriptor is extended into the spatio-temporal domain and a shape dynamics description is built at the higher level, in which a 4-state Markovian model is adopted and is learned from training sequences. Moreover, to build a mapping from the lower level to the higher level of the hierarchy, a shape similarity index (SSI) based matching mechanism is designed. We apply these two-level features for detecting flying bird for improved safety of aircrafts flying at low-altitude. The experimental results show that the proposed method is effective and outperforms three other existing vision-based FBD approaches. [Copyright &y& Elsevier]

Abstract: Segmentation of medical images is an inevitable image processing step for computer-aided diagnosis. Due to complex acoustic inferences and artifacts, accurate extraction of breast lesions in ultrasound images remains a challenge. Although there have been many segmentation techniques proposed, the performance often varies with different image data, leading to poor adaptability in real applications. Intelligent computing techniques for adaptively learning the boundaries of image objects are preferred. This paper focuses on optimization of a previously documented method called robust graph-based (RGB) segmentation algorithm to extract breast tumors in ultrasound images more adaptively and accurately. A novel technique named as parameter-automatically optimized robust graph-based (PAORGB) image segmentation method is accordingly proposed and performed on breast ultrasound images. A particle swarm optimization algorithm is incorporated with the RGB method to achieve optimal or approximately optimal parameters. Experimental results have shown that the proposed technique can more accurately segment lesions from ultrasound images compared to the RGB and two conventional region-based methods. [Copyright &y& Elsevier]

Vision-based power line detection (PLD) is an important yet challenging problem in low-altitude flight. Different from the traditional PLD methods, which only aim at line information, we propose a novel object-aware PLD method to obtain better detection performance. A new definition of power line is first proposed to present its object-aware properties; and then a cascaded PLD scheme is devised with line detection, region filtration, and object validation based on corresponding image cues in joint color (RGB) and near-infrared (NIR) images. Considering that the primary goal of PLD is to capture all potential information and decrease the false negatives, we first treat the universal line shape in pixel from joint RGB-NIR images as a basic feature to explore general line candidates. To further pick out the accurate regions occupied by power lines, on the one hand we filter the false candidates based on the region-based intensity of special material characteristics in NIR, and on the other hand we validate the power lines according to the color features in RGB. The experiments demonstrate the advantages of our proposed method in three aspects: good detection accuracy, high true detection rate, and low false detection rate. [ABSTRACT FROM AUTHOR]

Abstract: An Al/conductive coating/α-PbO2–CeO2–TiO2/β-PbO2–MnO2–WC–ZrO2 composite electrode material was prepared through electrochemical oxidation co-deposition on an Al/conductive coating/α-PbO2–CeO2–TiO2 substrate. The effects of manganese nitrate concentration on the chemical composition, electrocatalytic activity, and stability of the composite anode material were investigated using energy dispersive X-ray spectroscopy, anode polarization curves, quasi-stationary polarization curves, electrochemical impedance spectroscopy, scanning electron microscopy, and X-ray diffraction. Results revealed that the WC and nano-ZrO2 content in the β-PbO2–MnO2–WC–ZrO2 composite coatings increased with increasing manganese nitrate concentration. Moreover, the highest values of 6.61 wt% and 3.51 wt%, respectively, were achieved at 80 g L−1 manganese nitrate. PbO2 content decreased and MnO2 content increased with the increasing manganese nitrate concentration; both the descending and ascending trends were nonlinear. The Al/conductive coating/α-PbO2–CeO2–TiO2/β-PbO2–MnO2–WC–ZrO2 composite electrode obtained at 80 g L−1 manganese nitrate concentration in plating solution exhibited reduced overpotential for oxygen evolution (0.610 V at 500 A m−2), highest electrocatalytic activity, longest service life (360 h at 40 °C in 150 g L−1 H2SO4 solution at 2 A cm−2), and lowest cell voltage (2.75 V at 500 A m−2). Furthermore, the composite coating obtained with 80 g L−1 manganese nitrate had uniform crystal grains. The deposit formed was flat, dense, and crackless. [Copyright &y& Elsevier]

This paper comprehensively surveys the development of face hallucination (FH), including both face super-resolution and face sketch-photo synthesis techniques. Indeed, these two techniques share the same objective of inferring a target face image (e.g. high-resolution face image, face sketch and face photo) from a corresponding source input (e.g. low-resolution face image, face photo and face sketch). Considering the critical role of image interpretation in modern intelligent systems for authentication, surveillance, law enforcement, security control, and entertainment, FH has attracted growing attention in recent years. Existing FH methods can be grouped into four categories: Bayesian inference approaches, subspace learning approaches, a combination of Bayesian inference and subspace learning approaches, and sparse representation-based approaches. In spite of achieving a certain level of development, FH is limited in its success by complex application conditions such as variant illuminations, poses, or views. This paper provides a holistic understanding and deep insight into FH, and presents a comparative analysis of representative methods and promising future directions. [ABSTRACT FROM AUTHOR]

Abstract: The technique of visual saliency detection supports video surveillance systems by reducing redundant information and highlighting the critical, visually important regions. It follows that information about the image might be of great importance in depicting the visual saliency. However, the majority of existing methods extract contrast-like features without considering the contribution of information content. Based on the hypothesis that information divergence leads to visual saliency, a two-stage framework for saliency detection, namely information divergence model (IDM), is introduced in this paper. The term “information divergence” is used to express the non-uniform distribution of the visual information in an image. The first stage is constructed to extract sparse features by employing independent component analysis (ICA) and difference of Gaussians (DoG) filter. The second stage improves the Bayesian surprise model to compute information divergence across an image. A visual saliency map is finally obtained from the information divergence. Experiments are conducted on nature image databases, psychological patterns and video surveillance sequences. The results show the effectiveness of the proposed method by comparing it with 13 state-of-the-art visual saliency detection methods. [Copyright &y& Elsevier]

With the rapid development of the intelligent video surveillance (IVS), person re-identification, which is a difficult yet unavoidable problem in video surveillance, has received increasing attention in recent years. That is because computer capacity has shown remarkable progress and the task of person re-identification plays a critical role in video surveillance systems. In short, person re-identification aims to find an individual again that has been observed over different cameras. It has been reported that KISS metric learning has obtained the state of the art performance for person re-identification on the VIPeR dataset refid="ref39"/. However, given a small size training set, the estimation to the inverse of a covariance matrix is not stable and thus the resulting performance can be poor. In this paper, we present regularized smoothing KISS metric learning (RS-KISS) by seamlessly integrating smoothing and regularization techniques for robustly estimating covariance matrices. RS-KISS is superior to KISS, because RS-KISS can enlarge the underestimated small eigenvalues and can reduce the overestimated large eigenvalues of the estimated covariance matrix in an effective way. By providing additional data, we can obtain a more robust model by RS-KISS. However, retraining RS-KISS on all the available examples in a straightforward way is time consuming, so we introduce incremental learning to RS-KISS. We thoroughly conduct experiments on the VIPeR dataset and verify that 1) RS-KISS completely beats all available results for person re-identification and 2) incremental RS-KISS performs as well as RS-KISS but reduces the computational cost significantly. [ABSTRACT FROM AUTHOR]

Recovering a large matrix from a small subset of its entries is a challenging problem arising in many real applications, such as image inpainting and recommender systems. Many existing approaches formulate this problem as a general low-rank matrix approximation problem. Since the rank operator is nonconvex and discontinuous, most of the recent theoretical studies use the nuclear norm as a convex relaxation. One major limitation of the existing approaches based on nuclear norm minimization is that all the singular values are simultaneously minimized, and thus the rank may not be well approximated in practice. In this paper, we propose to achieve a better approximation to the rank of matrix by truncated nuclear norm, which is given by the nuclear norm subtracted by the sum of the largest few singular values. In addition, we develop a novel matrix completion algorithm by minimizing the Truncated Nuclear Norm. We further develop three efficient iterative procedures, TNNR-ADMM, TNNR-APGL, and TNNR-ADMMAP, to solve the optimization problem. TNNR-ADMM utilizes the alternating direction method of multipliers (ADMM), while TNNR-AGPL applies the accelerated proximal gradient line search method (APGL) for the final optimization. For TNNR-ADMMAP, we make use of an adaptive penalty according to a novel update rule for ADMM to achieve a faster convergence rate. Our empirical study shows encouraging results of the proposed algorithms in comparison to the state-of-the-art matrix completion algorithms on both synthetic and real visual datasets. [ABSTRACT FROM AUTHOR]

• MXene Ti 3 C 2 Tx SA film was fabricated by the Langmuir-Blodgett method. • Passive Q-switched laser operation at 1064 nm and 1342 nm, respectively, were successfully achieved besed on MXene Ti 3 C 2 Tx SA. MXene is a fast-growing family of 2D materials with unique light–matter interactions. Ti 3 C 2 Tx belongs to the family of MXene that show nonlinear saturable absorption characteristics and has been studied widely. However, translating the excellent performance of MXene flakes into stable thin film saturable absorbers (SA) devices has been a challenging task. Herein, we report the fabrication of a long term stable MXene Ti 3 C 2 Tx film SA deposited on a quartz plate by the Langmuir–Blodgett (LB) method for the first time, and it was used in passive Q-switched solid-state pulsed laser generation at the central wavelengths of 1.06 and 1.34 μm, respectively. LB Ti 3 C 2 Tx SAs exhibits excellent optical properties such as high modulation depth, low loss, and high linear transmittance at mid-infrared wavelengths. By inserting the LB Ti 3 C 2 Tx SAs into two Nd-doped solid-state lasers, short pulses were generated with the pulse duration of 244 ns and 311 ns in the 1.06 and 1.34 μm regimes, respectively. In addition, long-term stability was maintained in constant temperature drying. The results illustrate the potential of the MXene LB Ti 3 C 2 Tx SA films for laser applications, paving new ways for producing large-area, ultra-uniform, low-loss and stable MXene SA by the LB method. [ABSTRACT FROM AUTHOR]

Abstract: Face recognition is one of the biometric identification methods with the highest potential. The existing face recognition algorithms relying on the texture information of face images are affected greatly by the variation of expression, scale and illumination. Whereas the algorithms based on the shape topology weaken the influence of illumination to some extent, but the impact of expression, scale and illumination on face recognition is still unsolved. To this end, we propose a new method for face recognition by integrating texture information with shape information, called biview face recognition algorithm. The texture models are constructed by using subspace learning methods and shape topologies are formed by building graphs for face images. The proposed biview face recognition method is compared with recognition algorithms merely based on texture or shape information. Experimental results of recognizing faces under the variation of illumination, expression and scale demonstrate that the performance of the proposed biview face recognition outperforms texture-based and shape-based algorithms. [Copyright &y& Elsevier]

We propose a novel method to model human actions by explicitly coding motion and structure features that are separately extracted from video sequences. Firstly, the motion template (one feature map) is applied to encode the motion information and image planes (five feature maps) are extracted from the volume of differences of frames to capture the structure information. The Gaussian pyramid and center-surround operations are performed on each of the six obtained feature maps, decomposing each feature map into a set of subband maps. Biologically inspired features are then extracted by successively applying Gabor filtering and max pooling on each subband map. To make a compact representation, discriminative locality alignment is employed to embed the high-dimensional features into a low-dimensional manifold space. In contrast to sparse representations based on detected interest points, which suffer from the loss of structure information, the proposed model takes into account the motion and structure information simultaneously and integrates them in a unified framework; it therefore provides an informative and compact representation of human actions. The proposed method is evaluated on the KTH, the multiview IXMAS, and the challenging UCF sports datasets and outperforms state-of-the-art techniques on action recognition [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing is one of the most important techniques in analyzing hyperspectral images, which decomposes a mixed pixel into a collection of constituent materials weighted by their proportions. Recently, many sparse nonnegative matrix factorization (NMF) algorithms have achieved advanced performance for hyperspectral unmixing because they overcome the difficulty of absence of pure pixels and sufficiently utilize the sparse characteristic of the data. However, most existing sparse NMF algorithms for hyperspectral unmixing only consider the Euclidean structure of the hyperspectral data space. In fact, hyperspectral data are more likely to lie on a low-dimensional submanifold embedded in the high-dimensional ambient space. Thus, it is necessary to consider the intrinsic manifold structure for hyperspectral unmixing. In order to exploit the latent manifold structure of the data during the decomposition, manifold regularization is incorporated into sparsity-constrained NMF for unmixing in this paper. Since the additional manifold regularization term can keep the close link between the original image and the material abundance maps, the proposed approach leads to a more desired unmixing performance. The experimental results on synthetic and real hyperspectral data both illustrate the superiority of the proposed method compared with other state-of-the-art approaches. [ABSTRACT FROM PUBLISHER]

Abstract: Based on the assumption about the sparse representation of natural images and the theory of compressed sensing, very promising results about single-image super-resolution were obtained by an excellent algorithm introduced by Yang et al. [45]. However, their success could not be well explained theoretically. The lack of theoretical insight has hindered the further improvement of the algorithm. In this paper, Yang’s algorithm is revisited in the view of learning theory. According to this point, Yang’s algorithm can be considered as a linear regression method in a special feature space which is named as sparse coding space by us. In fact, it has been shown that Yang’s algorithm is a result of optimal linear estimation in sparse coding space. More importantly, our theoretical analysis suggests that Yang’s algorithm can be improved by using more flexible regression methods than the linear regression method. Following the idea, a novel single-image super-resolution algorithm which is designed based on the framework of L 2-Boosting is proposed in the paper. The experimental results show the effectiveness of the proposed algorithm by comparing with other methods, which verify our theoretical analysis about Yang’s algorithm. [Copyright &y& Elsevier]

Abstract: Most of the existing methods for pedestrian detection work well, only when the following assumption is satisfied: the features extracted from the training dataset and the testing dataset have very similar distributions in the feature space. However, in practice, this assumption does not hold because of the scene complexity and variation. In this paper, a new method is proposed for detecting pedestrians in various scenes based on the transfer learning technique. Our proposed method employs the following two strategies for improving the pedestrian detection performance. First, a new sample screening method based on manifold learning is proposed. The basic idea is to choose samples from the training set, which may be similar to the samples from the unseen scene, and then merge the selected samples into the unseen set. Second, a new classification model based on transfer learning is proposed. The advantage of the classification model is that only a small number of samples need to be used from the unseen scenes. Most of the training samples are still obtained from the training scene, which take up to 90% of the entire training samples. Compared to the traditional pedestrian detection methods, the proposed algorithm can adapt to different scenes for detecting pedestrians. Experiments on two pedestrian detection benchmark datasets, DC and NICTA, showed that the method can obtain better performance as compared to other previous methods. [Copyright &y& Elsevier]

Due to the popularity of social media websites, extensive research efforts have been dedicated to tag-based social image search. Both visual information and tags have been investigated in the research field. However, most existing methods use tags and visual characteristics either separately or sequentially in order to estimate the relevance of images. In this paper, we propose an approach that simultaneously utilizes both visual and textual information to estimate the relevance of user tagged images. The relevance estimation is determined with a hypergraph learning approach. In this method, a social image hypergraph is constructed, where vertices represent images and hyperedges represent visual or textual terms. Learning is achieved with use of a set of pseudo-positive images, where the weights of hyperedges are updated throughout the learning process. In this way, the impact of different tags and visual words can be automatically modulated. Comparative results of the experiments conducted on a dataset including 370+images are presented, which demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: Heterogeneous image transformation (HIT) plays an important role in both law enforcements and digital entertainment. Some available popular transformation methods, like locally linear embedding based, usually generate images with lower definition and blurred details mainly due to two defects: (1) these approaches use a fixed number of nearest neighbors (NN) to model the transformation process, i.e., K-NN-based methods; (2) with overlapping areas averaged, the transformed image is approximately equivalent to be filtered by a low pass filter, which filters the high frequency or detail information. These drawbacks reduce the visual quality and the recognition rate across heterogeneous images. In order to overcome these two disadvantages, a two step framework is constructed based on sparse feature selection (SFS) and support vector regression (SVR). In the proposed model, SFS selects nearest neighbors adaptively based on sparse representation to implement an initial transformation, and subsequently the SVR model is applied to estimate the lost high frequency information or detail information. Finally, by linear superimposing these two parts, the ultimate transformed image is obtained. Extensive experiments on both sketch-photo database and near infrared–visible image database illustrates the effectiveness of the proposed heterogeneous image transformation method. [Copyright &y& Elsevier]

Abstract: Visual saliency detection has been applied in many tasks in the fields of pattern recognition and computer vision, such as image segmentation, object recognition, and image retargeting. However, the accurate detection of saliency remains a challenge. The reasons behind this are that: (1) well-defined mechanism for saliency definition is rarely established; and (2) supporting information for detecting saliency is limited in general. In this paper, a multi-spectrum based saliency detection algorithm is proposed. Instead of only using the conventional RGB information as what existing algorithms do, this work incorporates near-infrared clues into the detection framework. Features of color and texture from both types of image modes are explored simultaneously. When calculating the color contrast, an effective color component analysis method is employed to produce more precise results. With respect to the texture analysis, texton representation is adopted for fast processing. Experiments are done to compare the proposed algorithm with other 11 state-of-the-art algorithms and the results indicate that our algorithm outperforms the others. [Copyright &y& Elsevier]

Abstract: Airborne vehicle tracking system is receiving increasing attention due to its high mobility, low cost and large surveillance scope. However, tracking multiple vehicles simultaneously on airborne platform is a challenging problem, owing to camera vibration, which causes visible frame-to-frame jitter in the airborne videos and uncertain vehicle motion. To address these problems, a new collaborative tracking framework is proposed in this paper. The framework consists of a two-level tracking process to track vehicles as groups. The higher level builds the relevance network and divides target vehicles into different groups, where the relevance is calculated based on the status information of vehicles obtained from the lower level. The proposed group tracking takes into account the relevance between vehicles and reduces the impact of camera vibration. Experimental results demonstrated that the proposed method has better performance in terms of tracking speed and tracking accuracy compared to other existing approaches based on particle filter and stationary grouping. [Copyright &y& Elsevier]

Image super-resolution (SR) reconstruction is essentially an ill-posed problem, so it is important to design an effective prior. For this purpose, we propose a novel image SR method by learning both non-local and local regularization priors from a given low-resolution image. The non-local prior takes advantage of the redundancy of similar patches in natural images, while the local prior assumes that a target pixel can be estimated by a weighted average of its neighbors. Based on the above considerations, we utilize the non-local means filter to learn a non-local prior and the steering kernel regression to learn a local prior. By assembling the two complementary regularization terms, we propose a maximum a posteriori probability framework for SR recovery. Thorough experimental results suggest that the proposed SR method can reconstruct higher quality results both quantitatively and perceptually. [ABSTRACT FROM AUTHOR]

The Nyquist–Shannon sampling theorem is on the reconstruction of a band-limited signal from its uniformly sampled samples. The higher the signal bandwidth gets, the more challenging the uniform sampling may become. To deal with this problem, signal reconstruction from local averages has been studied in the literature. In this paper, we obtain an improved Nyquist–Shannon sampling theorem from general local averages. In practice, the measurement apparatus gives a weighted average over an asymmetrical interval. As a special case, for local averages from symmetrical interval, we show that the sampling rate is much lower than that of a result by Gröchenig. Moreover, we obtain two exact dual frames from local averages, one of which improves a result by Sun and Zhou. At the end of this paper, as an example application of local average sampling, we consider a reconstruction algorithm: the piecewise linear approximations. [ABSTRACT FROM AUTHOR]

Airborne vehicle detection and tracking systems equipped on unmanned aerial vehicles (UAVs) are receiving more and more attention due to their advantages of high mobility, fast deployment and large surveillance scope. However, such systems are difficult to develop because of factors like UAV motion, scene complexity, and especially the partial occlusion of targets. To address these problems, a new framework of multi-motion layer analysis is proposed to detect and track moving vehicles in airborne platform. After motion layers are constructed, they are maintained over time for tracking vehicles. Most importantly, since the vehicle motion layers can be maintained even when the vehicles are only partially observed, the proposed method is robust to partial occlusion. Our experimental results showed that (1) compared with other previous algorithms, our method can achieve better performance in terms of higher detection rate and lower false positive rate; (2) it is more efficient and more robust to partial occlusion; (3) it is able to meet the demand of real time application due to its computational simplicity. [ABSTRACT FROM AUTHOR]

Sketch–photo synthesis plays an important role in sketch-based face photo retrieval and photo-based face sketch retrieval systems. In this paper, we propose an automatic sketch–photo synthesis and retrieval algorithm based on sparse representation. The proposed sketch–photo synthesis method works at patch level and is composed of two steps: sparse neighbor selection (SNS) for an initial estimate of the pseudoimage (pseudosketch or pseudophoto) and sparse-representation-based enhancement (SRE) for further improving the quality of the synthesized image. SNS can find closely related neighbors adaptively and then generate an initial estimate for the pseudoimage. In SRE, a coupled sparse representation model is first constructed to learn the mapping between sketch patches and photo patches, and a patch-derivative-based sparse representation method is subsequently applied to enhance the quality of the synthesized photos and sketches. Finally, four retrieval modes, namely, sketch-based, photo-based, pseudosketch-based, and pseudophoto-based retrieval are proposed, and a retrieval algorithm is developed by using sparse representation. Extensive experimental results illustrate the effectiveness of the proposed face sketch–photo synthesis and retrieval algorithms. [ABSTRACT FROM AUTHOR]

Until now, neighbor-embedding-based (NE) algorithms for super-resolution (SR) have carried out two independent processes to synthesize high-resolution (HR) image patches. In the first process, neighbor search is performed using the Euclidean distance metric, and in the second process, the optimal weights are determined by solving a constrained least squares problem. However, the separate processes are not optimal. In this paper, we propose a sparse neighbor selection scheme for SR reconstruction. We first predetermine a larger number of neighbors as potential candidates and develop an extended Robust-SL0 algorithm to simultaneously find the neighbors and to solve the reconstruction weights. Recognizing that the k-nearest neighbor (k-NN) for reconstruction should have similar local geometric structures based on clustering, we employ a local statistical feature, namely histograms of oriented gradients (HoG) of low-resolution (LR) image patches, to perform such clustering. By conveying local structural information of HoG in the synthesis stage, the k-NN of each LR input patch is adaptively chosen from their associated subset, which significantly improves the speed of synthesizing the HR image while preserving the quality of reconstruction. Experimental results suggest that the proposed method can achieve competitive SR quality compared with other state-of-the-art baselines. [ABSTRACT FROM PUBLISHER]

Recently, much attention has been drawn to the problem of matrix completion, which arises in a number of fields, including computer vision, pattern recognition, sensor network, and recommendation systems. This paper proposes a novel algorithm, named robust alternative minimization (RAM), which is based on the constraint of low rank to complete an unknown matrix. The proposed RAM algorithm can effectively reduce the relative reconstruction error of the recovered matrix. It is numerically easier to minimize the objective function and more stable for large-scale matrix completion compared with other existing methods. It is robust and efficient for low-rank matrix completion, and the convergence of the RAM algorithm is also established. Numerical results showed that both the recovery accuracy and running time of the RAM algorithm are competitive with other reported methods. Moreover, the applications of the RAM algorithm to low-rank image recovery demonstrated that it achieves satisfactory performance. [ABSTRACT FROM AUTHOR]

Human segmentation in photo images is a challenging and important problem that finds numerous applications ranging from album making and photo classification to image retrieval. Previous works on human segmentation usually demand a time-consuming training phase for complex shape-matching processes. In this paper, we propose a straightforward framework to automatically recover human bodies from color photos. Employing a coarse-to-fine strategy, we first detect a coarse torso (CT) using the multicue CT detection algorithm and then extract the accurate region of the upper body. Then, an iterative multiple oblique histogram algorithm is presented to accurately recover the lower body based on human kinematics. The performance of our algorithm is evaluated on our own data set (contains 197 images with human body region ground truth data), VOC 2006, and the 2010 data set. Experimental results demonstrate the merits of the proposed method in segmenting a person with various poses. [ABSTRACT FROM AUTHOR]

In this paper, we study the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. This application has two major requirements: to detect crossing pedestrians as early as possible just as they enter the view of the car-mounted camera and to maintain a false alarm rate as low as possible for practical purposes. Although many current sliding-window-based approaches using various features and classification algorithms have been proposed for image-/video-based pedestrian detection, their performance in terms of accuracy and processing speed falls far short of practical application requirements. To address this problem, we propose a three-level coarse-to-fine video-based framework that detects partially visible pedestrians just as they enter the camera view, with low false alarm rate and high speed. The framework is tested on a new collection of high-resolution videos captured from a moving vehicle and yields a performance better than that of state-of-the-art pedestrian detection while running at a frame rate of 55 fps. [ABSTRACT FROM AUTHOR]