检索结果-内蒙古大学图书馆

Traffic Sign Detection With Event Cameras and DCNN 25

学校读者我要写书评

暂无评论

Traffic Sign Detection With Event Cameras and DCNN

25th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2022

作者： Wzorek, Piotr Kryjak, Tomasz Embedded Vision Systems Group Agh University of Science and Technology Computer Vision Laboratory Department of Automatic Control and Robotics Kraków Poland Silesian University of Technology Department of Digital Systems Gliwice Poland

ISBN: (数字)9788362065424

ISBN: (纸本)9788362065424

In recent years, event cameras (DVS - Dynamic Vision Sensors) have been used in vision systems as an alternative or supplement to traditional cameras. They are characterised by high dynamic range, high temporal resolution, low latency, and reliable performance in limited lighting conditions - parameters that are particularly important in the context of advanced driver assistance systems (ADAS) and self-driving cars. In this work, we test whether these rather novel sensors can be applied to the popular task of traffic sign detection. To this end, we analyse different representations of the event data: event frame, event frequency, and the exponentially decaying time surface, and apply video frame reconstruction using a deep neural network called FireNet. We use the deep convolutional neural network YOLOv4 as a detector. For particular representations, we obtain a detection accuracy in the range of 86.9-88.9% mAP@0.5. The use of a fusion of the considered representations allows us to obtain a detector with higher accuracy of 89.9% mAP@0.5. In comparison, the detector for the frames reconstructed with FireNet is characterised by an accuracy of 72.67% mAP@0.5. The results obtained illustrate the potential of event cameras in automotive applications, either as standalone sensors or in close cooperation with typical frame-based cameras. © 2022 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Cameras

Nonlocal Intrinsic Fracture Energy of Polymerlike Networks

学校读者我要写书评

暂无评论

Physical Review Letters 2023年第22期131卷 228102-228102页

作者： Bolei Deng Shu Wang Chase Hartquist Xuanhe Zhao Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA

Connecting polymer network fracture to molecular-level chain scission remains a quandary. While the Lake-Thomas model predicts the intrinsic fracture energy of a polymer network is the energy to rupture a layer of chains, it underestimates recent experiments by ∼1–2 orders of magnitude. Here we show that the intrinsic fracture energy of polymerlike networks stems from nonlocal energy dissipation by relaxing chains far from the crack tip using experiments and simulations of 2D and 3D networks with varying defects, dispersity, topologies, and length scales. Our findings not only provide physical insights into polymer network fracture but offer design principles for tough architected materials.

关键词： Fracture Mechanical metamaterials Polymer networks

Object Identification and Localization of Visual Explanation for Weapon Detection

学校读者我要写书评

暂无评论

Object Identification and Localization of Visual Explanation...

2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Hnoohom, Narit Chotivatunyu, Pitchaya Yuenyong, Sumeth Wongpatikaseree, Konlakorn Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakorn Pathom Thailand Mahidol University Faculty of Engineering Department of Computer Engineering Nakorn Pathom Thailand University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

Weapon detection is a difficult task that requires accurate identification of weapon objects in images. The object localization approach is mostly used because it combines a gradient with a convolutional layer to create a map of key locations on the image. This paper presents an Eigen-CAM method to localize and detect objects in an image for a Faster Region-based Convolutional Neural Network (Faster R-CNN) residual neural network (ResNet 50) model, giving a visual explanation. The Internet Movie Firearms Database (IMFDB) was used to train a deep learning model with the Faster R-CNN ResNet 50 model of the pre-trained PyTorch framework. Experimental results indicated that the Faster R-CNN ResNet 50 model achieved the highest mAP of 0.497 with 0.5 IoU. The Eigen-CAM method performed effectively for visual image representation. © 2022 IEEE.

关键词： Convolutional neural networks

Meta-ZSDETR: Zero-shot DETR with Meta-learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Lu Zhang, Chenbo Zhao, Jiajia Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory China Department of Computer Science & Technology Tongji University China

Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with background. In this paper, we present the first method that combines DETR and meta-learning to perform zero-shot object detection, named Meta-ZSDETR, where model training is formalized as an individual episode based meta-learning task. Different from Faster R-CNN based methods that firstly generate class-agnostic proposals, and then classify them with visual-semantic alignment module, Meta-ZSDETR directly predict class-specific boxes with class-specific queries and further filter them with the predicted accuracy from classification head. The model is optimized with meta-contrastive learning, which contains a regression head to generate the coordinates of class-specific boxes, a classification head to predict the accuracy of generated boxes, and a contrastive head that utilizes the proposed contrastive-reconstruction loss to further separate different classes in visual space. We conduct extensive experiments on two benchmark datasets MS COCO and PASCAL VOC. Experimental results show that our method outperforms the existing ZSD methods by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

FACOS: Enabling Privacy Protection Through Fine-Grained Access Control with On-chain and Off-chain System

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Chao Hou, Cankun Jiang, Tianyu Ning, Jianting Qiao, Hui Wu, Yusen Fujian Provincial Key Laboratory of Data Intensive Computing the Key Laboratory of Intelligent Computing and Information Processing Fujian China The School of Computer Science and Technology Xidian University Shaanxi Xi’an710071 China The Department of Computer Science University of Miami MiamiFL33146 United States College of Computer and Cyber Security Fujian Normal University Fuzhou350007 China The Faculty of Data Science City University of Macau China

Data-driven landscape across finance, government, and healthcare, the continuous generation of information demands robust solutions for secure storage, efficient dissemination, and fine-grained access control. Blockchain technology emerges as a significant tool, offering decentralized storage while upholding the tenets of data security and accessibility. However, on-chain and off-chain strategies are still confronted with issues such as untrusted off-chain data storage, absence of data ownership, limited access control policy for clients, and a deficiency in data privacy and auditability. To solve these challenges, we propose a permissioned blockchain-based privacy-preserving fine-grained access control on-chain and off-chain system, namely FACOS. We applied three fine-grained access control solutions and comprehensively analyzed them in different aspects, which provides an intuitive perspective for system designers and clients to choose the appropriate access control method for their systems. Compared to similar work that only stores encrypted data in centralized or non-fault-tolerant IPFS systems, we enhanced off-chain data storage security and robustness by utilizing a highly efficient and secure asynchronous Byzantine fault tolerance (BFT) protocol in the off-chain environment. As each of the clients needs to be verified and authorized before accessing the data, we involved the Trusted Execution Environment (TEE)-based solution to verify the credentials of clients. Additionally, our evaluation results demonstrated that our system1 offers better scalability and practicality than other state-of-the-art designs. We deployed our system on Alibaba Cloud and Tencent Cloud and conducted multiple evaluations. The results indicate that it takes about 2.79 seconds for a client to execute the protocol for uploading and about 0.96 seconds for downloading. Compared to other decentralized systems, our system exhibits efficient latency for both download and upload operations.

关键词： Access control

An Inexact Bregman Proximal Difference-of-Convex Algorithm with Two Types of Relative Stopping Criteria

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Lei Hu, Jingjing Toh, Kim-Chuan School of Computer Science and Engineering Guangdong Province Key Laboratory of Computational Science Sun Yat-Sen University China School of Computer Science and Engineering Sun Yat-Sen University China Department of Mathematics Institute of Operations Research and Analytics National University of Singapore Singapore119076 Singapore

In this paper, we consider a class of difference-of-convex (DC) optimization problems, where the global Lipschitz gradient continuity assumption on the smooth part of the objective function is not required. Such problems are prevalent in many contemporary applications such as compressed sensing, statistical regression, and machine learning, and can be solved by a general Bregman proximal DC algorithm (BPDCA). However, the existing BPDCA is developed based on the stringent requirement that the involved subproblems must be solved exactly, which is often impractical and limits the applicability of the BPDCA. To facilitate the practical implementations and wider applications of the BPDCA, we develop an inexact Bregman proximal difference-of-convex algorithm (iBPDCA) by incorporating two types of relative-type stopping criteria for solving the subproblems. The proposed inexact framework has considerable flexibility to encompass many existing exact and inexact methods, and can accommodate different types of errors that may occur when solving the subproblem. This enables the potential application of our inexact framework across different DC decompositions to facilitate the design of a more efficient DCA scheme in practice. The global subsequential convergence and the global sequential convergence of our iBPDCA are established under suitable conditions including the Kurdyka- Lojasiewicz property. Some numerical experiments on the 1-2regularized least squares problem and the constrained 1-2sparse optimization problem are conducted to show the superior performance of our iBPDCA in comparison to existing algorithms. These results also empirically verify the necessity of developing different types of stopping criteria to facilitate the efficient computation of the subproblem in each iteration of our iBPDCA. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

Open-Ended Coaxial Probe Based Chloride Concentration Prediction in Water Using Machine Learning Algorithms 7

学校读者我要写书评

暂无评论

Open-Ended Coaxial Probe Based Chloride Concentration Predic...

7th International Youth Conference on Radio Electronics, Electrical and Power Engineering, REEPE 2025

作者： Hanima Kannan, C.H. Venugopal, Veena Gupta, Deepa Mathur, Parul Kurup, Dhanesh G. Mathur, Priyanka Amrita School of Engineering Amrita Vishwa Vidyapeetham Rf and Wireless Systems Laboratory Department of Electronics and Communication Engineering Bengaluru India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Physical Science Bengaluru India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India School of Engineering and Applied Science Benette University UP Greater Noida India

ISBN: (纸本)9798331531836

Monitoring chloride levels in water is essential for environmental health, industrial processes, and safe drinking water, as both high and low concentrations can cause harm for living being. This paper presents a novel approach to detecting chloride concentrations using Open-Ended Coaxial Probe (OECP) sensing combined with machine learning algorithms. OECP sensing offers real-time, non-destructive, and precise monitoring, enabling early detection of contaminants. Scattering parameter (S11) data across a broad frequency range was collected with varying chloride concentrations in controlled laboratory experiments. Thirteen machine learning algorithms were trained to predict chloride concentrations, with different datasets for training and testing to ensure robustness. Among these, CatBoost demonstrated the best performance. After fine tuning and cross-validation, the CatBoost model achieved a test Mean Square Error (MSE) of 0.00627 and Coefficient of Determination (R2) of 0.9936, showcasing its accuracy for applications in water monitoring, corrosion prevention, and safeguarding public health. © 2025 IEEE.

关键词： Mean square error

Hypergraph based Understanding for Document Semantic Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Qiwei Li, Zuchao Wang, Ping Ai, Haojun Zhao, Hai School of Computer Science Wuhan University China School of Information Management Wuhan University China School of Cyber Science and Engineering Wuhan University China Key Laboratory of Archival Intelligent Development and Service NAAC China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relationship between text nodes and the relation between text content. The existing document understanding models mainly focus on entity categories while ignoring the extraction of entity boundaries. We build a novel hypergraph attention document semantic entity recognition framework, HGA, which uses hypergraph attention to focus on entity boundaries and entity categories at the same time. It can conduct a more detailed analysis of the document text representation analyzed by the upstream model and achieves a better performance of semantic information. We apply this method on the basis of GraphLayoutLM to construct a new semantic entity recognition model HGALayoutLM. Our experiment results on FUNSD, CORD, XFUND and SROIE show that our method can effectively improve the performance of semantic entity recognition tasks based on the original model. The results of HGALayoutLM on FUNSD and XFUND reach the new state-of-the-art results. © 2024, CC BY.

关键词： Semantics

学校读者我要写书评

暂无评论

Physical Review Letters 2023年第21期130卷 210601-210601页

作者： Ya-Dong Wu Yan Zhu Ge Bai Yuexuan Wang Giulio Chiribella Department of Computer Science QICI Quantum Information and Computation Initiative The University of Hong Kong Pokfulam Road Hong Kong Centre for Quantum Technologies National University of Singapore Block S15 3 Science Drive 2 117543 Singapore Department of Computer Science AI Technology Laboratory The University of Hong Kong Pokfulam Road Hong Kong College of Computer Science and Technology Zhejiang University Zhejiang Province 310058 China Department of Computer Science Parks Road Oxford OX1 3QD United Kingdom Perimeter Institute for Theoretical Physics Waterloo Ontario N2L 2Y5 Canada

The task of testing whether two uncharacterized quantum devices behave in the same way is crucial for benchmarking near-term quantum computers and quantum simulators, but has so far remained open for continuous variable quantum systems. In this Letter, we develop a machine learning algorithm for comparing unknown continuous variable states using limited and noisy data. The algorithm works on non-Gaussian quantum states for which similarity testing could not be achieved with previous techniques. Our approach is based on a convolutional neural network that assesses the similarity of quantum states based on a lower-dimensional state representation built from measurement data. The network can be trained off-line with classically simulated data from a fiducial set of states sharing structural similarities with the states to be tested, with experimental data generated by measurements on the fiducial states, or with a combination of simulated and experimental data. We test the performance of the model on noisy cat states and states generated by arbitrary selective number-dependent phase gates. Our network can also be applied to the problem of comparing continuous variable states across different experimental platforms, with different sets of achievable measurements, and to the problem of experimentally testing whether two states are equivalent up to Gaussian unitary transformations.

关键词： Machine learning Quantum information processing with continuous variables Quantum verification