Separation of video clips into foreground and background components is a useful and important technique, making recognition, classification, and scene analysis more efficient. In this paper, we ...propose a motion-assisted matrix restoration (MAMR) model for foreground-background separation in video clips. In the proposed MAMR model, the backgrounds across frames are modeled by a low-rank matrix, while the foreground objects are modeled by a sparse matrix. To facilitate efficient foreground-background separation, a dense motion field is estimated for each frame, and mapped into a weighting matrix which indicates the likelihood that each pixel belongs to the background. Anchor frames are selected in the dense motion estimation to overcome the difficulty of detecting slowly moving objects and camouflages. In addition, we extend our model to a robust MAMR model against noise for practical applications. Evaluations on challenging datasets demonstrate that our method outperforms many other state-of-the-art methods, and is versatile for a wide range of surveillance videos.
Most matrix reconstruction methods assume that missing entries randomly distribute in the incomplete matrix, and the low-rank prior or its variants are used to well pose the problem. However, in ...practical applications, missing entries are structurally rather than randomly distributed, and cannot be handled by the rank minimization prior individually. To remedy this, this paper introduces new matrix reconstruction models using double priors on the latent matrix, named Reweighted Low-rank and Sparsity Priors (ReLaSP). In the proposed ReLaSP models, the matrix is regularized by a low-rank prior to exploit the inter-column and inter-row correlations, and its columns (rows) are regularized by a sparsity prior under a dictionary to exploit intra-column (-row) correlations. Both the low-rank and sparse priors are reweighted on the fly to promote low-rankness and sparsity, respectively. Numerical algorithms to solve our ReLaSP models are derived via the alternating direction method under the augmented Lagrangian multiplier framework. Results on synthetic data, image restoration tasks, and seismic data interpolation show that the proposed ReLaSP models are quite effective in recovering matrices degraded by highly structural missing and various types of noise, complementing the classic matrix reconstruction models that handle random missing only.
Methane, the main component of natural gas, is one of the primary sources of energy extensively employed worldwide. However, the utilization of natural gas is limited by reserves and geographical ...availability. Thus, a thermochemical method of converting biomass to methane is appealing, especially gasification. Important factors affecting methane production are discussed in the review including operating parameters, catalysts of methanation and gas conditioning effects. Low temperature and high pressure are beneficial to promote methanation reaction. Ni-based catalysts are widely used as methanation catalysts, but suffer from deactivation problems due to carbon deposition, sintering and poisoning. The methods of gas conditioning include using water gas shift reaction and adding hydrogen from electrolysis. In addition, environmental and economic views are discussed. Other thermochemical process including hydrothermal gasification, fast pyrolysis and direct methanation at low temperature are also introduced briefly. Based on the above discussion, potential research directions for optimizing methane production are proposed.
This paper presents an in-depth study and analysis of Chinese painting image classification by a multitask joint sparse representation algorithm for texture feature extraction of Chinese painting ...images and proposes a method to extract texture features directly for the original images. It simplifies the process of image grayscale conversion and preserves the information contained in the original Chinese painting images to the greatest extent. The algorithm uses the ideas of multicolor domain analysis and multiscale analysis, combined with the traditional grayscale coeval matrix to extract texture features. Experiments show that the multiscale grayscale cooccurrence matrix algorithm outperforms the traditional grayscale cooccurrence matrix algorithm and the color grayscale cooccurrence matrix algorithm. The discriminative ability of multiple features for target recognition is integrated by multitask learning, thus improving the robustness and generalization ability of the algorithm; meanwhile, the recognition accuracy is improved by using a two-level multitask learning mode to exclude the interference of a large number of irrelevant dictionary atoms. The experimental results show that the algorithm has higher recognition accuracy and better robustness than the existing sparse representation SAR target recognition algorithm. Configuration recognition experiments are conducted on different configurations of target data, and the experimental results show that the algorithm achieves better configuration recognition accuracy than existing algorithms.
Retinal vessel segmentation and centerline extraction are crucial steps in building a computer-aided diagnosis system on retinal images. Previous works treat them as two isolated tasks, while ...ignoring their tight association. In this paper, we propose a deep semantics and multi-scaled cross-task aggregation network that takes advantage of the association to jointly improve their performances. Our network is featured by two sub-networks. The forepart is a deep semantics aggregation sub-network that aggregates strong semantic information to produce more powerful features for both tasks, and the tail is a multi-scaled cross-task aggregation sub-network that explores complementary information to refine the results. We evaluate the proposed method on three public databases, which are DRIVE, STARE and CHASE_DB1. Experimental results show that our method can not only simultaneously extract retinal vessels and their centerlines but also achieve the state-of-the-art performances on both tasks.
The present study examined the patterns of sex behaviors before and during COVID-19, and identified the factors associated with condomless anal intercourse during COVID-19 from individual, ...interpersonal, and contextual level among men who have sex with men (MSM) in Hong Kong.
A cross-sectional study was conducted among MSM in Hong Kong. A total of 463 MSM completed a cross-sectional telephone survey between March 2021 and January 2022.
Among all participants, the mean number of regular sex partners, non-regular sex partners, and casual sex partners during the COVID-19 period were 1.24, 2.09, and 0.08 respectively. Among those who had sex with regular, non-regular, and casual sex partner during the COVID-19 period, respectively 52.4%, 31.8% and 46.7% reported condomless anal intercourse. Compared to the pre-COVID-19 period, participants reported significantly fewer number of regular and non-regular sex partners during the COVID-19 period. However, a higher level of condomless anal intercourse with all types of sex partners during the COVID-19 period was also observed. Adjusted for significant socio-demographic variables, results from logistic regression analyses revealed that perceived severity of COVID-19 (aOR = 0.72, 95% CI = 0.58, 0.88), COVID-19 risk reduction behaviors in general (aOR = 0.68, 95% CI = 0.48, 0.96), COVID-19 risk reduction behaviors during sex encounters (aOR = 0.45, 95% CI = 0.30, 0.66), condom negotiation (aOR = 0.61, 95% CI = 0.44, 0.86), and collective efficacy (aOR = 0.79, 95% CI = 0.64, 0.98) were protective factors of condomless anal intercourse with any type of sex partners during the COVID-19 period.
The COVID-19 control measures have caused a dramatic impact on the sexual behavior of MSM in Hong Kong. Interventions that promote condom use during the COVID-19 pandemic are still needed and such interventions could emphasize prevention of both COVID-19 and HIV.
Objective: This paper explores the relationship between alcohol consumption and psychological health outcome in an economically underdeveloped area of China. Methods: We conducted convenience ...sampling and recruited 439 participants at alcohol-related risk as identified by Alcohol Use Disorder Identification Test. Well-being and mental health were the primary outcomes. We employed multiple regression analysis to determine the correlation between alcohol consumption and health outcome. Results: Participants with higher scores for alcohol dependence were more likely to obtain higher scores for stress (0.11 95% CI: 0.03, 0.19), anxiety (0.15 95% CI: 0.07, 0.23) and depression (0.11 95% CI: 0.03, 0.19). Similarly, increasing scores for harmful alcohol use items were associated with higher scores for anxiety (0.08 95% CI: 0.01,0.16) and stress (0.08 95% CI: 0.01,0.15) and lower scores for positiveness (0.07 95% CI: -0.14, -0.01). Participants with stable incomes and the ethnic minority reported more favorable psychological outcomes or fewer negative emotions. Conversely, individuals who drank passively were more prone to experiencing lower positive and higher negative psychological effects. Conclusions: Higher scores on measures of alcohol dependence and harmful alcohol use indicate elevated psychological risks. Socioeconomic status, ethnicity, and drinking motivations modified the associations.
With the rapid advancement of deep learning and computer vision, these technologies are becoming increasingly vital in areas like virtual reality, medical diagnosis, and sports training. Existing ...methods for real-time 3D human body pose keypoint detection and quality assessment face significant challenges such as insufficient detection accuracy, low computational efficiency, and high data quality requirements. To address these challenges, we propose an innovative solution, GAN-BodyPose. This approach integrates 3D convolutional neural networks, self-attention mechanisms, and generative adversarial networks to deliver efficient and accurate detection and assessment in real time. The GAN-BodyPose framework combines 3D-CNN and self-attention for effective feature extraction and keypoint detection, enhanced further by generative adversarial networks for superior data quality and accuracy. Our extensive evaluations using a large-scale 3D human body pose dataset demonstrated that GAN-BodyPose outperforms traditional methods, showing improvements in processing speed (15% faster), accuracy in terms of Mean Per Joint Position Error (reduced by approximately 2.2%), and an Area Under the Curve (AUC) score increased by approximately 9.5% compared to HR-Net and other datasets. Additionally, it achieves lower Floating-Point Operations (FLOPs) by about 9.3%, indicating more efficient computational performance. These advancements underline the potential of our approach to significantly enhance user experiences in virtual reality, motion capture, and other real-time applications. The successful application of GAN-BodyPose promises greater efficiency and precision in fields ranging from game development to medical diagnostics, and robust support for human-computer interaction and gesture recognition. This research represents a substantial contribution to deep learning applications in robot control, decision-making, and broadens the research foundation in these domains.
•Introduced 3D-CNN for efficient feature extraction, improving keypoint detection in real-time scenarios.•Added self-attention mechanism to enhance understanding of relationships within 3D human body pose data.•Integrated GANs to enhance data quality and accuracy, generating realistic 3D human body pose data.
•Operational design domain for AVs at freeway entrance terminals is quantified.•Sensor detecting range and angle are mathematically derived for flat and 5% grades.•Taper and parallel merging types ...have minor differences in required range/angle.•Max. detecting range (185.0 m) and angle (179.9 degrees) are feasible for most AVs.•Min. acceleration lane length suggested for humans may not be available for AVs.
The safe operation of automated vehicles (AVs) is now on the research agenda, with attention to the AV’s operational design domain (ODD), which defines the conditions in which its driving automation system is designed to function. Due to the limited sight line on freeway entrance terminals, crashes involving AVs continue to occur during the merging operation. Considering that detecting range and detecting angle are critical parameters for the AV sensor’s sight triangle and may differ from human driver requirements, it is urgent to provide initial ODD results to improve the AV’s detection capabilities at entrance terminals. Based on sight triangle requirements, this study took a mathematical approach to quantify the relationships among AV sensor capabilities, design speed, and geometric design indicators separately for flat grades and 5 % grades. Required stopping sight distance (SSD) for the merging AV and travelled distance of the through-lane vehicle were calculated based on vehicle kinematics, common sensor capabilities, and Green Book parameter values. Using the law of cosines, the required detecting range and the detecting angle for AV sensors were calculated at various ramp and through-lane design speed combinations as the ODD constraint indicators. Two types of entrance terminals, the taper and the parallel, were considered in this study. Results show: 1) the maximum required detecting range and angle for AV sensors reached 185.0 m and 179.9 degrees, respectively; 2) the required detecting range and angle have only minor differences between the taper and parallel types; 3) the minimum acceleration lane length suggested for human drivers may not be available for AVs. These results provide two major contributions to safe operation of AVs: 1) for roadway design, the results provide general design references for acceleration lane length, merging angle, and sight-distance guarantee at freeway entrance terminals; and 2) for ODD management, results provide theoretical support for governments and traffic management departments to regulate AVs at these terminals, in some cases limiting the AV to manual driving or lower speed limits.
•A dual-branch depth estimation network architecture that separately captures low-level and high-level feature representations.•A refinement module is proposed to fuse different levels of features ...from both the branches and obtain the final high-quality depth map.•A nonlocal spatial attention module is proposed to explicitly exploit the nonlocal correlation in spatial domain.
Existing monocular depth estimation methods are unsatisfactory due to the inaccurate inference of depth details and the loss of spatial information. In this paper, we present a novel detail-preserving network (DPNet), i.e., a dual-branch network architecture that fully addresses the above problems and facilitates the depth map inference. Specifically, in contextual branch (CB), we propose an effective and efficient nonlocal spatial attention module by introducing non-local filtering strategy to explicitly exploit the pixel relationship in spatial domain, which can bring significant promotion on depth details inference. Meanwhile, we design a spatial branch (SB) to preserve the spatial information and generate high-resolution features from input color image. A refinement module (RM) is then proposed to fuse the heterogeneous features from both spatial and contextual branches to obtain a high quality depth map. Experimental results show that the proposed method outperforms SOTA methods on benchmark RGB-D datasets.
PDF
