检索结果-内蒙古大学图书馆

Single Frame Lidar-Camera Calibration Using Registration of 3D Planes

学校读者我要写书评

暂无评论

Single Frame Lidar-Camera Calibration Using Registration of ...

IEEE International Conference on Robotic Computing (IRC)

作者： Ashutosh Singandhupe Hung Manh La Quang Phuc Ha Department of Computer Science and Engineering Advanced Robotics and Automation (ARA) Lab University of Nevada Reno NV USA School of Electrical and Data Engineering University of Technology Sydney Australia

ISBN: (纸本)9781665472616

This work focuses on finding the extrinsic parameters (rotation and translation) between Lidar and an RGB camera sensor. We use a planar checkerboard and place it inside the Field-of-View (FOV) of both sensors, where we extract the 3D plane information of the checkerboard acquired from the sensor’s data. The plane coefficients extracted from the sensor’s data are used to construct a well-structured set of 3D points. These 3D points are then ’aligned,’ which gives the relative transformation between the two sensors. We use our proposed Correntropy Similarity Matrix Iterative Closest Point (CoSMICP) Algorithm to estimate the relative transformation. This work uses a single frame of the point cloud data acquired from the Lidar sensor and a single frame from the calibrated camera data to perform this operation. From the camera image, we use the projection of the calibration target’s corner points to compute the 3D points, and along the process, we calculate the 3D plane equation using the corner points. We evaluate our approach on a simulated dataset with complex environment settings, making use of the freedom to assess under multiple configurations. Through the obtained results, we verify our method under various configurations.

关键词： Point cloud compression Three-dimensional displays Laser radar Transmission line matrix methods Robot vision systems Cameras Real-time systems

A Novel Low Light Image Enhancement Method Based on Multi-Attention Generative Adversarial Networks

学校读者我要写书评

暂无评论

A Novel Low Light Image Enhancement Method Based on Multi-At...

Information Systems and Computing Technology (ISCTech), International Conference on

作者： Saijun Zhang Xu Hou School Of Computer Science And Engineering Northeastern University Shenyang China Institute of Artificial Intelligence and Marine Robotics College of Marine Electrical Engineering Dalian Maritime University Dalian China

Images taken in low light realistic conditions cannot capture enough illumination to show more details, so that the recovered images show color deviation and unclear edge textures along with much noise information in the experiments of low light image enhancement. In order to obtain high brightness and clear images, this paper designs a network based on multi-attention Generative Adversarial Networks for low light image enhancement. The network uses a low illumination enhancement module that incorporates the non-local illumination attention and edge aware attention proposed in this paper. Non-local illumination attention can combine global information to quickly capture the relationship of long-range features, solving the color deviation problem while reducing the number of convolution layers. Edge aware attention focuses on local information at the edges, highlighting the edge contours of the image while smoothing out the noise. These two attentions serve as a complement to each other. And Attentional Feature Fusion is used to fuse the features of different branches and retain more valid information. It is proved that our proposed low light enhancement network is superior to other networks in terms of color fidelity, edge clarity, and denoising.

关键词：

Machine Learning Algorithms for Natural Language Processing Tasks: A Case of COVID-19 Twitter data (Thailand)

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Natural Language Processing ...

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Kunyanuth Kularbphettong Rujijan Vichivanives Pannawat Kanjanaprakarn Jaruwan Chutrtong Nareenart Ruksuntorn Computer Science Program Suan Sunandha Rajabhat University Bangkok Thailand Faculty of Science and Technology Suan Sunandha Rajabhat University Bangkok Thailand Robotics Engineering program Faculty of Industrial Technology Suan Sunandha Rajabhat University Bangkok Thailand

This paper presents the use of natural language processing for the problem of information extraction and sentiment analysis. The dataset is from Twitter that has the information of people mentioning about COVID-19, this study has two tasks: (i) classification approach for information extraction task and (ii) deep learning approach for sentiment analysis task. In information extraction task, the data was gathered from twitter that related to COVID-19 information, and the sequence labelling method applied to classify text before giving it to classification algorithms (K-NN, Naïve Bayes, Decision Tree, Random Forest, and SVM). In sentiment analysis task, data was classified by convert the word into index and using word embedding, then to process deep learning algorithm (Bi-directional GRU). The accuracy of two tasks are 98% and 79% respectively.

关键词：

Learning Goal-based Movement via Motivational-based Models in Cognitive Mobile Robots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Berto, Letícia Costa, Paula Simões, Alexandre Gudwin, Ricardo Colombini, Esther Laboratory of Robotics and Cognitive Systems Institute of Computing University of Campinas Brazil Dept. of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas Brazil Dept. of Control and Automation Engineering Institute of Science and Technology São Paulo State University Sorocaba Brazil University of Campinas Brazil

Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action’s perceived pleasure, which is susceptible to changes over time. This makes decision-making more complex, requiring learning to balance needs and preferences according to the context. To understand how this process works and enable the development of robots with a motivational-based learning model, we computationally model a motivation theory proposed by Hull. In this model, the agent (an abstraction of a mobile robot) is motivated to keep itself in a state of homeostasis. We added hedonic dimensions to see how preferences affect decision-making, and we employed reinforcement learning to train our motivated-based agents. We run three agents with energy decay rates representing different metabolisms in two different environments to see the impact on their strategy, movement, and behavior. The results show that the agent learned better strategies in the environment that enables choices more adequate according to its metabolism. The use of pleasure in the motivational mechanism significantly impacted behavior learning, mainly for slow metabolism agents. When survival is at risk, the agent ignores pleasure and equilibrium, hinting at how to behave in harsh scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Metabolism

Fusion of Mixture of Experts and Generative Artificial Intelligence in Mobile Edge Metaverse

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Mao, Shiwen Kim, Dong In The College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The School of Electrical and Computer Engineering University of Sydney Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is slowed down by the challenges of content creation, scalability, and dynamic user interaction. Our study investigates an integration of Mixture of Experts (MoE) models with Generative Artificial Intelligence (GAI) for mobile edge computing to revolutionize content creation and interaction in the Metaverse. Specifically, we harness an MoE model's ability to efficiently manage complex data and complex tasks by dynamically selecting the most relevant experts running various sub-models to enhance the capabilities of GAI. We then present a novel framework that improves video content generation quality and consistency, and demonstrate its application through case studies. Our findings underscore the efficacy of MoE and GAI integration to redefine virtual experiences by offering a scalable, efficient pathway to harvest the Metaverse's full potential. © 2024, CC BY.

关键词： Augmented reality

Data Warehouse-Based Ad Archive for Media Analysis

学校读者我要写书评

暂无评论

Data Warehouse-Based Ad Archive for Media Analysis

International Conference on Edge Computing and Applications (ICECAA)

作者： G. Indra B. Praveen Kumar G. Hemanth Kumar MS Srikanth Department of Computer Science and Engineering R.M.K. College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering KL University Vijayawada Andhra Pradesh India School of Electronics and Communication Engineering REVA University Bengaluru Karnataka India Program Specialist TNS India Foundation Bangalore Karnataka India

Media influence's public opinion and decision-making today. Advertisements especially affect audience perceptions, actions, and purchases. A comprehensive data library on commercials and their performance is needed to understand how media affects society. Ad content, placement, and performance are stored in a data warehouse-based ad archive. The archive can evaluate marketing campaigns and discover media trends. Ad servers, social media platforms, and media monitoring tools may build the data warehouse-based ad archive. A dimensional data model helps retrieve and analyze data. Structured Query Language (SQL) queries, Online Analytical Processing (OLAP) cubes, and data visualization tools may access the archive. Media academics, marketers, and politicians may study the media environment using the data warehouse-based ad archive. Media academics may utilize the collection to study the marketing campaigns, media trends and media's influence on society. The archive may help advertisers analyze their ad campaigns, optimize media placement, and understand their target demographic. Policymakers may use the archive to monitor media outlets' advertising compliance and assess policy changes' media landscape effects.

关键词：

Spectral Extremal Connectivity of Two-State Seizure Brain Waves

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Talento, Mara Sherlin D. Richards, Jordan Pinto-Orellana, Marco Huser, Raphael Ombao, Hernando C. Statistics Program Computer Electrical and Mathematical Science & Engineering Division King Abdullah University of Science and Technology 23955 - 6900 Saudi Arabia Neuro-AI Laboratory Computer Electrical and Mathematical Science & Engineering Division King Abdullah University of Science and Technology 23955 - 6900 Saudi Arabia School of Mathematics Maxwell Institute for Mathematical Sciences University of Edinburgh EdinburghEH9 3FD United Kingdom Department of Biomedical Engineering University of California Irvine92697 United States

Coherence analysis plays a vital role in the study of functional brain connectivity. However, coherence captures only linear spectral associations, and thus can produce misleading findings when ignoring variations of connectivity in the tails of the distribution. This limitation becomes important when investigating extreme neural events that are characterized by large signal amplitudes. The focus of this paper is to examine connectivity in the tails of the distribution, as this reveals salient information that may be overlooked by standard methods. We develop a novel notion of spectral tail association of periodograms to study connectivity in the network of electroencephalogram (EEG) signals of seizure-prone neonates. We further develop a novel non-stationary extremal dependence model for multivariate time series that captures differences in extremal dependence during different brain phases, namely burst-suppression and non-burst-suppression. One advantage of our proposed approach is its ability to identify tail connectivity at key frequency bands that could be associated with outbursts of energy which may lead to seizures. We discuss these novel scientific findings alongside a comparison of the extremal behavior of brain signals for epileptic and non-epileptic patients. © 2025, CC BY.

关键词： Electroencephalography

Visualizing cortical blood perfusion after photothrombotic stroke in vivo by needle-shaped beam optical coherence tomography angiography

学校读者我要写书评

暂无评论

PhotoniX 2024年第1期5卷 605-621页

作者： Xiangyu Guo Jingjing Zhao Liqun Sun Varun Gupta Lin Du Komal Sharma Aidan Van Vleck Kaitlyn Liang Liangcai Cao Lingjie Kong Yuanmu Yang Yong Huang Adam de la Zerda Guofan Jin State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision InstrumentTsinghua UniversityBeijing 100084China Department of Structural Biology Stanford University School of MedicineStanford UniversityStanfordCA 94305USA Department of Neurosurgery Stanford University School of MedicineStanford UniversityStanfordCA 94305USA Department of Radiology Stanford University School of MedicineStanford UniversityStanfordCA 94305USA Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeley 94720USA School of Optics and Photonics Beijing Institute of TechnologyNo.5 South Zhongguancun StreetHaidianBeijing 100081China Biophysics Program Molecular Imaging Programand Bio-X Program at Stanford UniversityStanfordCA 94305USA Chan Zuckerberg Biohub San FranciscoCA 94110USA Institute of Medical Equipment Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China

Optical imaging techniques provide low-cost,non-radiative images with high spatiotemporal resolution,making them advantageous for long-term dynamic observation of blood perfusion in stroke research and other brain studies compared to non-optical ***,high-resolution imaging in optical microscopy fundamentally requires a tight optical focus,and thus a limited depth of field(DOF).Consequently,large-scale,non-stitched,high-resolution images of curved surfaces,like brains,are difficult to acquire without z-axis *** overcome this limitation,we developed a needle-shaped beam optical coherence tomography angiography(NB-OCTA)system,and for the first time,achieved a volumetric resolution of less than 8μm in a non-stitched volume space of 6.4 mm×4 mm×620μm in *** system captures the distribution of blood vessels at 3.4-times larger depths than normal OCTA equipped with a Gaussian beam(GB-OCTA).We then employed NB-OCTA to perform long-term observation of cortical blood perfusion after stroke in vivo,and quantitatively analyzed the vessel area density(VAD)and the diameters of representative vessels in different regions over 10 days,revealing different spatiotemporal dynamics in the acute,sub-acute and chronic phase of post-ischemic *** from our NB-OCTA,we revealed that the recovery process is not only the result of spontaneous reperfusion,but also the formation of new *** study provides visual and mechanistic insights into strokes and helps to deepen our understanding of the spontaneous response of brain after stroke.

关键词： Optical coherence tomography angiography Diffractive optical elements Needle-shaped beam Brain imaging Stroke Cortical blood perfusion

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models’ biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024, CC BY.

关键词： Contrastive Learning