Search

Estimating human pose from images is the key to enabling machines to understand human actions. Existing works on human pose estimation mainly focus on designing more resultful deep neural networks to regress the locations of human joints. Although the human pose is obedient to anatomy and shows rich anatomical features, reasoning human body structure by machine in a complex environment is still an open problem. This paper proposes AnatPose which can effectively capture the structural dependency among human body parts by both deep neural network architecture and learning objectives: (1) For the deep neural network architecture, a bidirectional learning paradigm is proposed to learn body-part proportions and dependencies by organizing human body parts as sequential data. This innovation enables the messages to pass in a bidirectional way and makes the human body exchange information about each part deeper during training. (2) For the learning objective, the proposed AnatPose learns a probabilistic representation of multi-scale anatomical features, including keypoint heatmaps, bone heatmaps, and symmetry heatmaps. This innovation enables the multi-scale anatomical features to successfully capture the structural dependency at both low-level joints and high-level associations from the anatomical priors of the human body. Extensive experimental results demonstrate that the proposed AnatPose shows state-of-the-art performance on three challenging datasets. It achieves a PCK@0.2 detection rate of 95.2% on the LSP dataset, a PCKh@0.5 detection rate of 92.9% on the MPII dataset, and an mAP of 76.6% on the Microsoft COCO dataset. Benefiting from its state-of-the-art accuracy, the proposed approach is expected to be widely used in various human pose estimation-driven applications. • AnatPose organizes human body parts as anatomically sequential data. • AnatPose learns the anatomical properties by a bidirectional recurrent neural network. • An anatomically significant objective is designed for optimizing the neural network. • Extensive results show superior performance on human pose estimation. [ABSTRACT FROM AUTHOR]

Human-machine interactive systems show increasing demand for analysing fast moving objects in high-frame-rate videos. Robust foreground detection, which is able to reduce large amount of redundant background data from high-frame-rate video, becomes the essence to achieve ultra-high-speed human-machine interactions. This paper proposes a local spatial propagation based background model generation, a local linear illumination correction based background model update, and a regional central coordinates and edge keypoints constrained foreground region reselection. The three proposals make up a robust and hardware-friendly foreground detection method. Experimental results prove that the proposed hardware-friendly algorithm achieves high accuracy and robustness on various kinds of challenging cases. Meanwhile, the hardware implementation utilizes little hardware resources and achieves realtime processing of high-frame-rate (784 frame/second) video with the delay less than 1 ms/frame in image processing core. In addition, a practical system is implemented by combing a PC, a high-speed camera and a field programmable gate array (FPGA) for realworld applications. This work will significatively promote the development and application of high-speed human machine interaction. A demo of the proposed vision system working at 784 FPS is available at https://wcms.waseda.jp/em/5f84f75136a6. Note to Practitioners—This paper was motivated by the problem of high-frame-rate video contains large amount of redundant background pixels which makes ultra-high-speed human-machine interactions inaccessible. Existing approaches are mainly focused on designing complex background models, but processing speed, which is the most important issue for ultra-high-speed human-machine interactions, has received relatively little attention. This paper suggests a robust and hardware-friendly foreground detection algorithm which has been implemented as a hardware system by using an FPGA, a high-frame-rate camera, and a PC. We show that the hardware implementation utilizes less hardware resources and achieves real-time processing speed of 784 FPS with the delay less than 1 ms/frame in the image processing core. This work is a pioneering attempt of ultra-high-speed foreground detection, which will significatively speed up the wide applications of ultra-high-speed human machine interactions. [ABSTRACT FROM AUTHOR]

Progressive training has unfolded its superiority on a wide range of downstream tasks. However, it may fail in fine-grained recognition (FGR) due to special challenges with high intra-class and low inter-class variances. In this paper, we propose an active self-pace learning method to exploit the full potential of progressive training strategy in FGR. The key innovation of our design is to integrate submodular optimization and self-pace learning into a maximum–minimum optimization framework. The submodular optimization is regarded as a dynamic regularization to select active sample groups in each training round for restricting the search space of self-pace optimization. This can overcome the limitation of traditional self-pace learning that is easily trapped into local minimums when facing challenging samples. Extensive experiments on three public FGR datasets show that the proposed method can win at least 1.5% performance gain in various kinds of network backbones including swin-transformer. • We are the first to exploit the sub–modularity for active sample selection. By our problem formulation, the optimal category subsets can be progressively selected for obtaining steady cumulative gain. • We combine submodular optimization with self-paced learning to generate a collaborated maximum–minimum optimization framework. The constructed framework can achieve smooth and stable progressive learning through using active samples to restrict the search space of self-paced optimization. • The proposed collaborated optimization framework can be deployed on various types of FGR networks. Extensive experiments on three fine-grained recognition datasets can verify the superiority of progressive training, where the averaged recognition gain surpasses 1.5%. [ABSTRACT FROM AUTHOR]

3D human pose estimation plays an important role in various human-machine interactive applications, but how to effectively extract and represent the kinematical features of human body structure in video has always been a challenge. This paper presents some inspiring observations on the human body properties that hold heuristic patterns of human poses: 1) There is distinct temporal coherence in any kind of human pose; 2) there exist evident spatial and temporal correlations among local joints even though the human is doing complex actions. According to the observed patterns, a locally structured feature encoder and a spatial–temporal feature transform are proposed for kinematics-aware feature extraction and enhancement. Unlike existing works directly projecting every bone joint to pose features without distinction, the proposed locally-structured feature encoder maps the local connection property of human body structure to kinematical features which are neural embeddings extracted from both local and global groups of human bone joints. Since the local and global bone-joint groups are pre-defined according to human body kinematics, the kinematical features are able to represent body kinematics. The kinematical features are then transformed by the proposed spatial–temporal feature transform to enhance the spatial and temporal correlations among human bone joints. The overall framework well promotes the representation of human body kinematics for 3D pose estimation. Extensive experimental results on commonly used datasets show that the mean per joint position error (MPJPE) is significantly reduced when compared with state-of-the-art methods under the same experimental condition. The improvement is expected to promote machines to better understand human poses for building superior human-centered automation systems. • Spatial–temporal kinematic-awareness is studied for 3D human pose estimation. • Hybrid-kinematical feature encoder extracts kinematical features of 2D pose. • Spatial–temporal feature transform enhances the spatial and temporal correlations. • The fusion of spatial and temporal features promote the final 3D pose estimation. [ABSTRACT FROM AUTHOR]

The invasive weed algorithm (IWO) is a meta-heuristic algorithm, which is an effective and promising optimiser to address the optimisation problems. In this study, a hybrid algorithm based on the self-adaptive invasive weed algorithm (IWO) and differential evolution algorithm (DE), named SIWODE, is proposed to address the continuous optimisation problems. In the proposed SIWODE, first, the two parameters are adaptively proposed to improve the convergence speed of the algorithm. Second, the crossover and mutation operations are introduced in SIWODE to improve the population diversity and increase the exploration capability during the iterative process. Furthermore, a local perturbation strategy is presented to improve exploitation ability during the late process. The exploration and exploitation ability of the algorithm is effectively balanced by cooperative mechanisms. The experiment results of SIWODE show that the SIWODE has the superior searching quality and stability than other mentioned approaches. [ABSTRACT FROM AUTHOR]

Video-based 3D human pose estimation is an important yet challenging task for many human-involved pattern recognition systems. Existing deep learning-based 3D human pose estimation methods are faced with the problems of lacking large-scale training data and lacking effective solutions to represent the complicated human body structure. To this end, this paper proposes a jo intl y learning framework entitled JoyPose that simultaneously leverages both human pose data augmentation and human pose estimation. In particular, JoyPose consists of an evolutionary data augmentation module and an anatomy-aware global–local pose feature representation module for 3D human pose estimation. The evolution for data augmentation is guided by a reinforcement learning strategy in a probabilistic way according to pose estimation loss. The anatomy-aware global–local pose feature representation module separately captures global features and local features according to anatomical and kinematic patterns observed from pose estimation errors across different human joints. The performance of the final human pose estimation is leveraged by both data augmentation and anatomy-aware global–local feature representation. Extensive experiments on three real-world datasets demonstrate the superiority and robustness against state-of-the-art methods. • JoyPose simultaneously leverages 3D human pose augmentation and pose estimation. • The distributions of crossover and mutation are learned for human pose augmentation. • Pose estimation quality is utilized to guide the distribution updating. • Global and local features are extracted based on the kinematical characters. [ABSTRACT FROM AUTHOR]

Distributed scheduling with assembly machines has been an attractive research field in sustainable supply chains and multi-factory manufacturing systems. This paper investigates a distributed blocking flow shop scheduling problem with an assembly machine (DABFSP) with the total assembly completion time criterion, and proposes an effective discrete monarch butterfly optimization algorithm (EDMBO). First, a constructive heuristic combining the largest processing time rule and the earliest start assembly rule is provided to find a promising sequence. On this basis, an efficient initialization method is introduced to generate an initial population with high quality and diversity. Afterward, a global search procedure is presented, which integrates four kinds of improved operators and expands the solution space in a good direction. Then, according to different problem-specific characteristics, we present four targeted and flexible variable neighborhood search methods based on the critical job and critical factory to exploit the solution space. Finally, statistically significant numerical experiments are carried out with state-of-the-art optimization methods based on 1710 benchmark instances. The experimental results and detailed analysis demonstrate that the EDMBO is superior to preferred algorithms for addressing the DABFSP. [ABSTRACT FROM AUTHOR]

In the field of image stitching, cases with large camera optical center movement and large parallax have been the virgin territory of research. The goal of image stitching is to overcome the parallax and stitch a natural image. We look into this problem in the context of ultra-low altitude flight of a UAV. We model the 3D world in this scenario and quickly estimate orthographic projection by pairs of homography matrices. Our stitching method can achieve precise alignment since it takes parallax well into consideration. The stitching results are natural and the extra time consumed is short. • We propose a Orthographic Projection Estimation method aided by semantic information. • We propose a image stitching method for low-altitude UAV images. • Low-altitude UAV image stitching based on Orthographic Projection Estimation is proved to be necessary. [ABSTRACT FROM AUTHOR]

Blind image quality assessment (BIQA), which aims to estimate the perceptual quality of images without any reference information, is a very important yet challenging task. Although human visual system is sensitive to degradations on both spatial contrast and spatial distribution, most of the existing structural degradation based BIQA models consider only one of them. This study introduces a novel BIQA model by taking into account degradations on both contrast and spatial distribution. First, the authors construct a multi‐threshold local tetra pattern (MTLTrP) instead of local binary pattern to measure the changes on spatial distribution. Second, Weber–Laplacian of Gaussian (WLOG) operator, which responds to intensity contrast in a small spatial neighbourhood, is proposed to extract local contrast features. Finally, the joint statistics of MTLTrP and WLOG are utilised for BIQA model learning. Experimental results on three large benchmark databases demonstrate that the proposed model outperforms state‐of‐the‐art BIQA models, as well as with several well‐known full reference quality assessment methods. [ABSTRACT FROM AUTHOR]

Automatic classification of texture images is an important and challenging task in the applications of image analysis and scene understanding. In this paper, we focus on the problem of the classification of texture images acquired under various rotation and illumination conditions and propose a new local image descriptor which is named local spiking pattern (LSP). Specifically, the proposed LSP uses a 2-dimensional neural network, which is made up of a series of interconnected spiking neurons, to generate binary images by iteration. The binary images are then encoded to generate discriminative feature vectors. In classification phase, we use a nearest neighborhood classifier to achieve supervised classification. Finally, LSP is evaluated by comparison with some state-of-the-art local image descriptors. Experimental results on Outex texture database show that LSP outperforms most of the other local image descriptors in the noiseless case and shows high robustness when texture images are distorted by salt & pepper noise. [ABSTRACT FROM AUTHOR]

As a matter of fact, mammalian visual system do not pay an equivalent attention to different regions in an image, the visual cortex is less sensitive to textures than non-textures. Therefore, to obtain the optimal visual quality and the perfect compression ratio simultaneously in image quantization, textures should be quantized coarsely, and non-textures should be quantized finely. The pulse-coupled neural networks (PCNN) is a model of synchronous pulse bursts in mammalian visual cortex, which has been proved to be extremely effective in image processing because of its biological background. In this work, a mammalian visual characteristics inspired perceptual image quantization strategy is proposed. It employs PCNN to extract textures from original image. Then, pixels in textures are quantized into less gray scale layers than pixels in non-textures. After that, quantized textures and quantized non-textures are consolidated. Experimental results prove validity and efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

Toughening modification of poly(l‐lactide) (PLLA) with rubber particles is often realized at the cost of transparency, mechanical strength, and modulus because high rubber loadings are generally required for toughening. In this work, a promising strategy to simultaneously improve the transparency and stiffness–toughness performance of poly(butyl acrylate)‐poly(methyl methacrylate) (BAMMA) core‐shell rubber nanoparticles toughened PLLA blends by utilizing the stereocomplex (SC) crystallization between PLLA and poly(d‐lactide) (PDLA) is devised. The results reveal that the construction of SC crystallites in PLLA matrix via melt‐mixing PLLA/BAMMA blends with PDLA can prevent BAMMA nanoparticles from aggregation and promote them to form network‐like structure at lower contents. As a result, not only higher toughening efficiency with less rubber contents but also superior transparency is achieved in the PLLA/PDLA/BAMMA blends as compared with the PLLA/BAMMA ones where large aggregated BAMMA clusters are formed. Moreover, the outstanding reinforcement of SC crystallites network for PLLA can impart an enhanced tensile strength and modulus to PLLA/PDLA/BAMMA blends, thus improving the stiffness–toughness performance of PLLA/PDLA/BAMMA blends to a higher degree. This work demonstrates that SC crystallization is a promising solution to solve the contradiction between transparency and mechanical properties and then obtain superior comprehensive performances in rubber toughened PLLA blends. [ABSTRACT FROM AUTHOR]

Background: The aim of this study was to review our experience in managing renal or adrenal tumors with level III or IV inferior vena cava thrombus by using deep hypothermic circulatory arrest (DHCA), and to evaluate survival outcomes.Methods: Between September 2004 and March 2016, we treated 33 patients with renal or adrenal malignancy tumor and thrombus extending into the inferior vena cava. Patients were identified according to radiographic records and operative findings. Clinicopathological and operative characteristics were recorded, and comparisons of clinical and operative characteristics through DHCA were performed. A Cox regression model was used to determine predictors of perioperative mortality.Results: Twenty-one out of 33 patients with level III (n = 15), level IV (n = 5), or level II (n = 1) renal or adrenal tumors were treated surgically through cardiopulmonary bypass (CPB) with DHCA, and 12 patients with level II or III tumors were treated surgically through normothermic CPB. Three complications were observed, and one death occurred perioperatively, owing to multiple organ failure. The overall perioperative mortality was 4.7%. There were significant differences in the clinicopathological characteristics, operative duration, estimated blood loss, transfusions and hospital stay depending on use of DHCA. Multivariate analysis indicated that the operative duration (OR, 3.78; P < 0.001), estimated blood loss (OR, 1.08; P = 0.02), and transfusion (OR, 2.13; P = 0.038) during/after surgery were positively associated with higher mortality and morbidity. DHCA failed to reach statistical significance (P = 0.378).Conclusions: Use of CPB and DHCA to treat renal or adrenal tumors allows for complete tumor resection, especially at the T4 stage. Although it can cause physical damage, this technique does not increase operative risk and is a relatively safe approach. [ABSTRACT FROM AUTHOR]

The acceptance check is a key step to decide whether an overhead transmission line can be put into use. However, for the acceptance check of towers, the manual means is still adopted mostly nowadays, which is dangerous and inefficient. The main challenges for intelligent check technique are the automatic tower segmentation and intelligent requirements of some detection items. Here, based on point clouds from lidars, some intelligent methods are proposed for tower related acceptance check items. The geometric structural changing rules for towers are found and analyzed to identify and segment towers from the scene point cloud automatically. A model‐constrained method is proposed for fine filtering of towers. With point cloud registration strategies, the tilt angle of a tower is calculated intelligently and the defect detection of a tower is conducted successfully. Experiments show that the results of the proposed methods are accurate, efficient and automatic, which have potential for real applications. [ABSTRACT FROM AUTHOR]

Combined with human visual characteristics, this paper proposes an adaptive image quantization method using pulse coupled neural networks (PCNN). It is acknowledged that PCNN satisfies human visual characteristics which can be used to quantize images. We have been trying to obtain the optimal image quantized with minimum amount of data for a long time and finally discover that the proposed algorithm comes up to the expected standard. First, the gray scale image is imported into PCNN and then the parameters of PCNN are set automatically. Secondly, the image is quantized by the hand of proposed algorithm. The experimental results of the gray natural images from the standard image library prove the validity and efficiency of our proposed quantization method. [ABSTRACT FROM AUTHOR]

As multipath is one of the dominating error sources for high accuracy Global Navigation Satellite System (GNSS) applications, multipath mitigation approaches are employed to minimize this hazardous error in receivers. Binary offset carriermodulation (BOC), as a modernized signal structure, is adopted to achieve significant enhancement. However, because of its multi-peak autocorrelation function, conventional multipath mitigation techniques for binary phase shift keying (BPSK) signal would not be optimal. Currently, non-parametric and parametric approaches have been studied specifically aiming at multipath mitigation for BOC signals. Non-parametric techniques, such as Code Correlation ReferenceWaveforms (CCRW), usually have good feasibility with simple structures, but suffer from low universal applicability for different BOC signals. Parametric approaches can thoroughly eliminate multipath error by estimating multipath parameters. The problems with this category are at the high computation complexity and vulnerability to the noise. To tackle the problem, we present a practical parametric multipath estimation method in the frequency domain for BOC signals. The received signal is transferred to the frequency domain to separate out the multipath channel transfer function for multipath parameter estimation. During this process, we take the operations of segmentation and averaging to reduce both noise effect and computational load. The performance of the proposed method is evaluated and compared with the previous work in three scenarios. Results indicate that the proposed averaging-Fast Fourier Transform (averaging-FFT) method achieves good robustness in severe multipath environments with lower computational load for both low-order and high-order BOC signals. [ABSTRACT FROM AUTHOR]

Exploring an optimal combination of features from high-dimensional text vectors is an essential step for classification on Scientific and Technical Service (STS) resources. However, existing metaheuristic feature selection methods exhibit deteriorated performance and increased computational costs when dealing with high-dimensional datasets. Based on these issues, a novel Enhanced Binary Black Hole (EBBH) algorithm is investigated to improve the performance of mining the optimal subset of high-dimensional attributes in STS resources text. In the proposed EBBH, all operators employ a novel binary encoding framework to reduce the number of features, which provides a more efficient way to search the solution space. As a pre-processing step, prime feature attention assigns different selection weights based on the variable importance ranking from random forests, ensuring a high-quality initial population is generated. Moreover, we incorporate an adaptive enhancement strategy to maintain the balance between exploitation and exploration in the search process. The proposed EBBH is assessed on eight high-dimensional benchmark datasets and subsequently demonstrated successful application to five STS resource datasets. Comparative experiments with 12 state-of-the-art algorithms for high-dimensional problems revealed the superiority of EBBH in terms of fitness, classification accuracy, and selected features. [ABSTRACT FROM AUTHOR]

Abstract: Background: As drug-eluting stent (DES) has almost overcome the disadvantage of frequent restenosis, off-pump coronary artery bypass grafting (OPCAB) has been introduced to avoid complications of cardiopulmonary bypass. However, which approach may promise better outcomes for patients with coronary artery disease remains controversial. Methods: Three databases were searched. The outcomes of interest were major adverse cardiac and cerebrovascular events (MACCE), all-cause death, target vessel revascularization (TVR), repeat revascularization (RRV), myocardial infarction (MI), and cerebrovascular events (CVE). The relative risk (RR) was calculated as the summary statistic. Results: 11,452 patients from 22 studies were included, of which 4949 patients underwent OPCAB and 6503 patients received DES. The cumulative rates of MACCE (RR [95% CI]=0.43 [0.34, 0.54], P <0.00001), all-cause death (RR [95% CI]=0.56 [0.33, 0.96], P =0.03), TVR (RR [95% CI]=0.33 [0.21, 0.53], P <0.00001), RRV (RR [95% CI]=0.22 [0.11, 0.42], P <0.00001) and MI (RR [95% CI]=0.13 [0.05, 0.29], P <0.00001) at 3years were all lower in OPCAB group. The incidences of in-hospital death (RR [95% CI]=1.31 [0.81, 2.13], P =0.27) and MI (RR [95% CI]=1.03 [0.60, 1.78], P =0.92) were not different between groups, but the rate of in-hospital CVE was lower (RR [95% CI]=2.6355 [1.0033, 6.9228], P =0.05) in DES group. Conclusions: OPCAB presents better long-term outcomes of MACCE, all-cause mortality, TVR, RRV and MI but uncertain outcome of postoperative CVE without influencing the incidences of in-hospital death and MI. [Copyright &y& Elsevier]