检索结果-内蒙古大学图书馆

Evaluating Local Geometric Feature Representations for 3D Rigid data Matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Jiaqi Quan, Siwen Wang, Peng Zhang, Yanning National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Poly-technical University Xi’an710129 China School of Electronic and Control Engineering Chang’An University Xi’an710064 China

—Local geometric descriptors remain an essential component for 3D rigid data matching and fusion. The devise of a rotational invariant local geometric descriptor usually consists of two steps: local reference frame (LRF) construction and feature representation. Existing evaluation efforts have mainly been paid on the LRF or the overall descriptor, yet the quantitative comparison of feature representations remains unexplored. This paper fills this gap by comprehensively evaluating nine state-of-the-art local geometric feature representations. Our evaluation is on the ground that ground-truth LRFs are leveraged such that the ranking of tested feature representations are more convincing as opposed to existing studies. The experiments are deployed on six standard datasets with various application scenarios (shape retrieval, point cloud registration, and object recognition) and data modalities (LiDAR, Kinect, and Space Time) as well as perturbations including Gaussian noise, shot noise, data decimation, clutter, occlusion, and limited overlap. The evaluated terms cover the major concerns for a feature representation, e.g., distinctiveness, robustness, compactness, and efficiency. The outcomes present interesting findings that may shed new light on this community and provide complementary perspectives to existing evaluations on the topic of local geometric feature description. A summary of evaluated methods regarding their peculiarities is also presented to guide real-world applications and new descriptor crafting. Copyright © 2019, The Authors. All rights reserved.

关键词： Shot noise

Fundamental diagram and stability analysis of mixed traffic considering heterogeneous car-following behaviors and platoon factors

学校读者我要写书评

暂无评论

Intelligent Transportation Infrastructure 2024年第3期3卷

作者： Sun, Zhanbo Yan, Qiruo Liu, Yafei Fu, Zhijian Yang, Lei School of Transportation and Logistics Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory for Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China

With the advancement of connected automated vehicles (CAVs), it is anticipated that mixed traffic environments, where human-driven vehicles (HVs) coexist with CAVs, will become prevalent in the future. The study aims to investigate the impact of heterogeneous car-following behaviors of HVs (e.g. aggressive, normal, and mild driving styles) and platoon factors of CAVs (i.e. platoon intensity and maximum platoon size) on the fundamental diagram and stability of mixed traffic. Firstly, a Markov chain approach is employed to describe the probability distributions of different leader-follower combinations, enabling us to construct a comprehensive mixed traffic model. Subsequently, a general modeling framework based on the mixed traffic model is established to examine the effects of heterogeneous car-following behaviors and platoon factors on the fundamental diagram and stability of mixed traffic. The results from numerical experiments reveal several findings: 1. an increase in the proportion of aggressive driving style enhances both the capacity and stability of mixed traffic;2. larger platoon intensity and maximum platoon size contribute to improved capacity, particularly in scenarios where a large fraction of HVs exhibit aggressive driving behavior;3. platoon intensity has a positive impact on traffic flow stability, while larger maximum platoon size leads to reduced stability;and 4. increasing CAV penetration without considering platoon intensity may lead to reduced stability compared to scenarios with a substantial proportion of aggressive drivers. © 2024 The Author(s).

关键词： connected automated vehicles fundamental diagram heterogeneous car-following behavior Markov chain mixed traffic traffic stability

Learning High-Resolution and Efficient Non-local Features for Brain Glioma Segmentation in MR Images 23rd

学校读者我要写书评

暂无评论

Learning High-Resolution and Efficient Non-local Features fo...

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Jia, Haozhe Xia, Yong Cai, Weidong Huang, Heng Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xian710072 China School of Computer Science University of Sydney SydneyNSW2006 Australia Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA15261 United States JD Finance America Corporation Mountain ViewCA94043 United States

ISBN: (纸本)9783030597184

Brain glioma segmentation using multi-parametric magnetic resonance (MR) imaging has significant clinical value. Although 3D convolutional neural networks (CNNs) have become increasingly prevalent in delivering this segmentation task, these models still suffer from an insufficient ability to high-resolution feature representation for small and irregular regions, limited local receptive fields, and poor long-range dependencies. In this paper, we propose a 3D High-resolution and Non-local Feature Network (HNF-Net) for brain glioma segmentation using multi-parametric MR imaging. We construct HNF-Net based mainly on the parallel multi-scale fusion (PMF) module, which helps produce strong high-resolution feature representation and aggregate multi-scale contextual information. We also introduce the expectation-maximization attention (EMA) module to HNF-Net, aiming to capture the long-range dependent contextual information and reduce the feature redundancy in a lightweight fashion. We evaluated our HNF-Net on the BraTS 2019 Challenge dataset against eight top-ranking methods listed on the challenge leaderboard. Our results suggest that the proposed HNF-Net achieves improved overall performance over these methods, and our ablation study demonstrates the effectiveness of the PMF module and EMA module. © 2020, Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

A performance evaluation of correspondence grouping methods for 3D rigid data matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Jiaqi Xian, Ke Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710129 China National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent years, their advantages and shortcomings remain unclear regarding different applications and perturbations. To fill this gap, this paper gives a comprehensive evaluation of nine state-of-the-art 3D correspondence grouping methods. A good correspondence grouping algorithm is expected to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall as well as facilitating accurate transformation estimation. Toward this rule, we deploy experiments on three benchmarks with different application contexts including shape retrieval, 3D object recognition, and point cloud registration together with various perturbations such as noise, point density variation, clutter, occlusion, partial overlap, different scales of initial correspondences, and different combinations of keypoint detectors and descriptors. The rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation. Based on the outcomes, we give a summary of the traits, merits, and demerits of evaluated approaches and indicate some potential future research directions. Copyright © 2019, The Authors. All rights reserved.

关键词： Benchmarking

Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Peng Liu, Jing He, Xiangteng Peng, Yuxin Wang, Peng Zhang, Yanning The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Poly-technical University China The Guangzhou Institute of Technology Xidian University China The Wangxuan Institute of Computer Technology Peking University China

Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies, which can be roughly interpreted as the binary or multiple event classification. However, such a setup that builds relationships between complicated anomalous events and single labels, e.g., "vandalism", is superficial, since single labels are deficient to characterize anomalous events. In reality, users tend to search a specific video rather than a series of approximate videos. Therefore, retrieving anomalous events using detailed descriptions is practical and positive but few researches focus on this. In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e.g., language descriptions and synchronous audios. Unlike the current video retrieval where videos are assumed to be temporally well-trimmed with short duration, VAR is devised to retrieve long untrimmed videos which may be partially relevant to the given query. To achieve this, we present two large-scale VAR benchmarks and design a model called Anomaly-Led Alignment Network (ALAN) for VAR. In ALAN, we propose an anomaly-led sampling to focus on key segments in long untrimmed videos. Then, we introduce an efficient pretext task to enhance semantic associations between video-text fine-grained representations. Besides, we leverage two complementary alignments to further match cross-modal contents. Experimental results on two benchmarks reveal the challenges of VAR task and also demonstrate the advantages of our tailored method. Captions are publicly released at https://***/Roc-Ng/VAR. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Prediction of fatal adverse prognosis in patients with fever-related diseases based on machine learning:a retrospective study

学校读者我要写书评

暂无评论

Chinese Medical Journal 2020年第5期133卷 583-589页

作者： Chun-Hong Zhao Hui-Tao Wu He-Bin Che Ya-Nan Song Yu-Zhuo Zhao Kai-Yuan Li Hong-Ju Xiao Yong-Zhi Zhai Xin Liu Hong-Xi Lu Tan-Shi Li Medical School of Chinese People’s Liberation Army Beijing 100853China Department of Emergency The First Medical Center of Chinese People’s Liberation Army General HospitalBeijing 100853China National Engineering Laboratory for Medical Big Data Application Technology The First Medical Center to Chinese People’s Liberation Army General HospitalBeijing 100853China

Background:Fever is the most common chief complaint of emergency *** identification of patients at an increasing risk of death may avert adverse *** aim of this study was to establish an early prediction model of fatal adverse prognosis of fever patients by extracting key indicators using big data ***:A retrospective study of patients’data was conducted using the Emergency Rescue database of Chinese People’s Liberation Army General *** were divided into the fatal adverse prognosis group and the good prognosis *** commonly used clinical indicators were *** feature elimination method was used to determine the optimal number of the included *** the training model,logistic regression,random forest,adaboost,and bagging were *** also collected the emergency room data from December 2018 to December 2019 with the same inclusion and exclusion *** performance of the model was evaluated by accuracy,F1-score,precision,sensitivity,and the areas under receiver operator characteristic curves(ROC-AUC).Results:The accuracy of logistic regression,decision tree,adaboost and bagging was 0.951,0.928,0.924,and 0.924,F1-scores were 0.938,0.933,0.930,and 0.930,the precision was 0.943,0.938,0.937,and 0.937,ROC-AUC were 0.808,0.738,0.736,and 0.885,***-AUC of ten-fold cross-validation in logistic and bagging models were 0.80 and 0.87,*** top six coefficients and odds ratio(OR)values of the variables in the logistic regression were cardiac troponin T(CTnT)(coefficient=0.346,OR=1.413),temperature(T)(coefficient=0.235,OR=1.265),respiratory rate(RR)(coefficient=–0.206,OR=0.814),serum kalium(K)(coefficient=0.137,OR=1.146),pulse oxygen saturation(SPO2)(coefficient=–0.101,OR=0.904),and albumin(ALB)(coefficient=–0.043,OR=0.958).The weights of the top six variables in the bagging model were:CTnT,RR,lactate dehydrogenase,serum amylase,heart rate,and systolic blood ***

关键词： Fever Infection Machine learning Prognosis

High-Resolution Traffic Flow Prediction Model Based on Deep Learning

学校读者我要写书评

暂无评论

Journal of Computer Science Research 2019年第1期1卷 1-9页

作者： Zhihong Yao Yibing Wang School of Transportation and Logistics Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong UniversityChengduSichuan610031China TOPS Laboratory Department of Civil and Environmental EngineeringUniversity of Wisconsin-Madison1415 Engineering DriveMadisonWI 53706USA Department of Architecture Engineering Yantai Vocational CollegeYantaiShandong264670China

The time resolution of the existing traffic flow prediction model is too big to be applied to adaptive signal timing *** on the view of the platoon dispersion model,the relationship between vehicle arrival at the downstream intersection and vehicle departure from the upstream intersection was ***,a high-resolution traffic flow prediction model based on deep learning was *** departure flow rate from the upstream and the arrival flow rate at the downstream intersection was taking as the input and output in the proposed model,***,the parameters of the proposed model were trained by the field data,and the proposed model was implemented to forecast the arrival flow rate of the downstream *** show that the proposed model can better capture the fluctuant traffic flow and reduced MAE,MRE,and RMSE by 9.53%,39.92%,and 3.56%,respectively,compared with traditional models and algorithms,such as Robertson's model and artificial neural ***,the proposed model can be applied for realtime adaptive signal timing optimization.

关键词： Traffic flow predicition Deep learning Time resolution Platoon dispersion Signal timing optimization Real time

Real-Time Chaotic Video Encryption Based on Multi-Threaded Parallel Confusion and Diffusion

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Jiang, Dong Yuan, Zhen Li, Wen-Xin Wang, Hai-Tao Lu, Liang-Liang School of Internet Anhui University Hefei230039 China National Engineering Research Center of Agro-Ecological Big Data Analysis and Application Anhui University Hefei230601 China Key Laboratory of Optoelectronic Technology of Jiangsu Province Nanjing Normal University Nanjing210023 China National Laboratory of Solid State Microstructures Nanjing University Nanjing210093 China Hefei National Laboratory Hefei230088 China

Due to the strong correlation among adjacent pixels, image encryption schemes typically perform multiple rounds of confusion and diffusion to protect images against various attacks, which is time-consuming and cannot meet the real-time requirements for video encryption. Existing works, therefore, realize video encryption by simplifying encryption process or selectively encrypting specific pixels, resulting in lower security compared to image encryption. This paper proposes a real-time chaotic video encryption strategy based on parallel computing. It splits video frame into sub-frames, creates a set of threads to concurrently perform confusion and diffusion operations on corresponding sub-frames, and efficiently outputs encrypted frames. To assess its performance, two cryptosystems are implemented using different chaotic systems. Encryption speed evaluation demonstrates a significant acceleration in byte generation, confusion, and diffusion phases, enabling real-time encryption on different X86 platforms. The average encryption time is less than 42ms, despite performing five rounds of confusion and diffusion operations on each frame. Statistical and security analysis prove that the deployed cryptosystems exhibit exceptional statistical properties and provide resistance to different attacks. Moreover, our method is adopted to implement a multi-user, real-time mobile video communication system using embedded systems, validating the feasibility of the proposed strategy for various application scenarios. © 2023, The Authors. All rights reserved.

关键词： Cryptography

Channel Estimation and Signal Detection for NLOS Ultraviolet Scattering Communication with Space Division Multiple Access

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Yubo Pan, Yuchen Gong, Chen Liu, Beiyuan Xu, Zhengyuan Key Laboratory of Wireless-Optical Communications Chinese Academy of Sciences University of Science and Technology of China Anhui Hefei230027 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Shaanxi Xi’an710072 China

We design a receiver assembling several photomultipliers (PMTs) as an array to increase the field of view (FOV) of the receiver and adapt to multiuser situation over None-line-of-sight (NLOS) ultraviolet (UV) channels. Channel estimation and signal detection have been investigated according to the space division characteristics of the structure. Firstly, we adopt the balanced structure on the pilot matrix, analyze the channel estimation mean square error (MSE), and optimize the structure parameters. Then, with the estimated parameters, an analytical threshold detection rule is proposed as a preliminary work of multiuser detection. The detection rule can be optimized by analyzing the separability of two users based on the Gaussian approximation of Poisson weighted sum. To assess the effect of imperfect estimation, the sensitivity analysis of channel estimation error on two-user signal detection is performed. Moreover, we propose a successive elimination method for on-off keying (OOK) modulated multiuser symbol detection based on the previous threshold detection rule. A closed-form upper bound on the detection error rate is calculated, which turns out to be a good approximation of that of multiuser maximum-likelihood (ML) detection. The proposed successive elimination method is twenty times faster than the ML detection with negligible detection error rate degradation. Copyright © 2023, The Authors. All rights reserved.

关键词： Channel estimation