检索结果-内蒙古大学图书馆

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yuyang Cong, Yang Goswami, Dipam Liu, Xialei van de Weijer, Joost State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China University of Chinese Academy of Sciences China South China University of Technology China Computer Vision Center Barcelona Spain VCIP CS Nankai University China Department of Computer Science Universitat Autònoma de Barcelona Spain

In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model 1 © 2023, CC BY.

关键词： Object detection

Automatic and robust single-camera specular highlight removal in cardiac images

学校读者我要写书评

暂无评论

Automatic and robust single-camera specular highlight remova...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Samar M. Alsaleh Angelica I. Aviles Pilar Sobrevilla Alicia Casals James K. Hahn Department of Computer Science George Washington University Washington DC U.S.A. Intelligent Robotics and Systems Group Universitat Politecnica de Cataluya Barcelona Spain Department of Applied Mathematics II Universitat Politecnica de Cataluya Barcelona Spain Institute for Bioengineering of Catalonia Universitat Politecnica de Cataluya Barcelona Spain

In computer-assisted beating heart surgeries, accurate tracking of the heart's motion is of huge importance and there is a continuous need to eliminate any source of error that might disturb the tracking process. One source of error is the specular reflection that appears on the glossy surface of the heart. In this paper, we propose a robust solution for the detection and removal of specular highlights. A hybrid color attributes and wavelet based edge projection approach is applied to accurately identify the affected regions. These regions are then recovered using a dynamic search-based inpainting with adaptive windowing. Experimental results demonstrate the precision and efficiency of the proposed method. Moreover, it has a real-time performance and can be generalized to various other applications.

关键词： Image color analysis Heart Image edge detection Wavelet transforms Surgery Tracking

Decentralized MPC based obstacle avoidance for multi-robot target tracking scenarios

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Tallamraju, Rahul Rajappa, Sujit Black, Michael Karlapalem, Kamalakar Ahmad, Aamir Perceiving Systems Department Max Planck Institute for Intelligent Systems Tübingen Germany Chair of Cognitive Systems Department of Computer Science University of Tubingen Tübingen Germany Agents and Applied Robotics Group International Institute for Information Technology Hyderabad India

In this work, we consider the problem of decentralized multi-robot target tracking and obstacle avoidance in dynamic environments. Each robot executes a local motion planning algorithm which is based on model predictive control (MPC). The planner is designed as a quadratic program, subject to constraints on robot dynamics and obstacle avoidance. Repulsive potential field functions are employed to avoid obstacles. The novelty of our approach lies in embedding these nonlinear potential field functions as constraints within a convex optimization framework. Our method convexifies non-convex constraints and dependencies, by replacing them as pre-computed external input forces in robot dynamics. The proposed algorithm additionally incorporates different methods to avoid field local minima problems associated with using potential field functions in planning. The motion planner does not enforce predefined trajectories or any formation geometry on the robots and is a comprehensive solution for cooperative obstacle avoidance in the context of multi-robot target tracking. Video of simulation studies: https://***/umkdm82Tt0M. Copyright © 2018, The Authors. All rights reserved.

关键词： Multipurpose robots

Force-feedback sensory substitution using supervised recurrent learning for robotic-assisted surgery

学校读者我要写书评

暂无评论

Force-feedback sensory substitution using supervised recurre...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Angelica I. Aviles Samar M. Alsaleh Pilar Sobrevilla Alicia Casals Intelligent Robotics and Systems Group Universitat Politecnica de Cataluya Barcelona Spain Department of Computer Science George Washington University Washington DC U.S.A. Department of Applied Mathematics II Universitat Politecnica de Cataluya Barcelona Spain Institute for Bioengineering of Catalonia Universitat Politecnica de Cataluya Barcelona Spain

The lack of force feedback is considered one of the major limitations in Robot Assisted Minimally Invasive Surgeries. Since add-on sensors are not a practical solution for clinical environments, in this paper we present a force estimation approach that starts with the reconstruction of a 3D deformation structure of the tissue surface by minimizing an energy functional. A Recurrent Neural Network-Long Short Term Memory (RNN-LSTM) based architecture is then presented to accurately estimate the applied forces. According to the results, our solution offers long-term stability and shows a significant percentage of accuracy improvement, ranging from about 54% to 78%, over existing approaches.

关键词： computer architecture Microprocessors Force Surgery Robot sensing systems Estimation

Fixed-time Adaptive Neural Control for Physical Human-Robot Collaboration with Time-Varying Workspace Constraints

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Yuzhu Van, Mien McIlvanna, Stephen Nhat, Nguyen Minh McLoone, Seán Ceglarek, Dariusz Ge, Shuzhi Sam The Centre for Intelligent Autonomous Manufacturing Systems School of Electronics Electrical Engineering and Computer Science Queen’s University Northern Ireland Belfast United Kingdom The Warwick Manufacturing Group University of Warwick Coventry United Kingdom The Department of Electrical and Computer Engineering Social Robotics Laboratory National University of Singapore Singapore

Physical human-robot collaboration (pHRC) requires both compliance and safety guarantees since robots coordinate with human actions in a shared workspace. This paper presents a novel fixed-time adaptive neural control methodology for handling time-varying workspace constraints that occur in physical human-robot collaboration while also guaranteeing compliance during intended force interactions. The proposed methodology combines the benefits of compliance control, time-varying integral barrier Lyapunov function (TVIBLF) and fixed-time techniques, which not only achieve compliance during physical contact with human operators but also guarantee time-varying workspace constraints and fast tracking error convergence without any restriction on the initial conditions. Furthermore, a neural adaptive control law is designed to compensate for the unknown dynamics and disturbances of the robot manipulator such that the proposed control framework is overall fixed-time converged and capable of online learning without any prior knowledge of robot dynamics and disturbances. The proposed approach is finally validated on a simulated two-link robot manipulator. Simulation results show that the proposed controller is superior in the sense of both tracking error and convergence time compared with the existing barrier Lyapunov functions based controllers, while simultaneously guaranteeing compliance and safety. Copyright © 2023, The Authors. All rights reserved.

关键词： Lyapunov functions

Early Prediction of Cryptocurrency Price Decline: A Deep Learning Approach

学校读者我要写书评

暂无评论

Early Prediction of Cryptocurrency Price Decline: A Deep Lea...

International Conference on computer and Information Technology (ICCIT)

作者： Mst Shapna Akter Hossain Shahriar Md Abdur Rahman Muhammad Rahman Alfredo Cuzzocrea Department of Intelligent Systems and Robotics University of West Florida USA Center for Cybersecurity University of West Florida USA Department of Mathematics Jahangirnagar University Savar Dhaka Bangladesh Department of Computer Science Clayton State University USA iDEA Lab University of Calabria Rende Italy

In recent times, the cryptocurrency market has emerged as one of the fastest-growing financial markets worldwide. It is, however, known for its high volatility and illiquidity compared to traditional markets such as equities, foreign exchange, and commodities. This inherent risk creates uncertainty among investors. The aim of this research is to forecast the level of risk in the cryptocurrency market. To assist cryptocurrency investors in navigating these challenges, we propose an approach that involves calculating the risk factor based on existing parameters. We employed various machine learning algorithms, including CNN, LSTM, BiLSTM, and GRU, to predict the risk factor in twenty elements of the cryptocurrency market. Through extensive experimentation, we developed a new model that outperformed existing models, achieving the highest Root Mean Square Error (RMSE) value of 1.3229 and the lowest RMSE value of 0.0089. Furthermore, we tested the generalization ability of our proposed model on a new dataset, different from the one used for training. Even with this new dataset, our model displayed robust performance. In contrast, the other existing models achieved higher RMSE values, with the highest being 14.5092 and the lowest 0.02769. By adopting our approach, investors can trade more confidently in complex and challenging financial assets such as Bitcoin, Ethereum, and Dogecoin. Our proposed model demonstrates superior performance and generalization capabilities, providing valuable insights for participants in the cryptocurrency market.

关键词：

Spiral coverage path planning for Multi-UAV photovoltaic panel inspection applications

学校读者我要写书评

暂无评论

Spiral coverage path planning for Multi-UAV photovoltaic pan...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Marco Andrés Luna Mohammad Sadeq Ale Isaac Miguel Fernandez-Cortizas Carlos Santos Ahmed Refaat Ragab Martin Molina Pascual Campoy Computer Vision and Aerial Robotics Group (CVAR) Centre for Automation and Robotics (C.A.R.) Universidad Politécnica de Madrid (UPM-CSIC) Madrid Spain Department of Signal Theory and Communications University of Alcala (UAH) Madrid Spain Department of Network Faculty of Information Systems and Computer Science October 6 University Giza Egypt Department of Artificial Intelligence Universidad Politécnica de Madrid Madrid Spain

This paper deals with the problem of coverage path planning for multiple UAVs in disjoint regions. For this purpose, a spiral-coverage path planning algorithm is proposed. Additionally, task assignment methods for multi-region inspection with a swarm of UAVs are applied. The centralized system architecture is described, and an adaptive sliding mode controller is designed. Furthermore, we evaluate the performance of the proposed techniques by obtaining numerical results and simulations with the controller. The results show that the spiral pattern optimizes the cost of the mission and improves the task distribution of the mission planning system. Additionally, the performance of the proposed controller is robust to simulated disturbances.

关键词：

Extracting Semantic Knowledge from GANs with Unsupervised Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Jianjin Zhang, Zhaoxiang Hu, Xiaolin The School of Mathematics and Computer Science Panzhihua University The Department of Computer Science and Technology Tsinghua University China The Insitute of Automation Chinese Academy of Sciences The Centre for Artificial Intelligence and Robotics Hong Kong Innovation and Science Insitute Chinese Academy of Sciences Hong Kong The Department of Computer Science and Technology Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems THU-Bosch JCML Center THBI IDG/McGovern Institute for Brain Research BNRist Tsinghua University Beijing China Beijing China

Recently, unsupervised learning has made impressive progress on various tasks. Despite the dominance of discriminative models, increasing attention is drawn to representations learned by generative models and in particular, Generative Adversarial Networks (GANs). Previous works on the interpretation of GANs reveal that GANs encode semantics in feature maps in a linearly separable form. In this work, we further find that GAN’s features can be well clustered with the linear separability assumption. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN’s features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects, e.g., car, portrait, animals, and so on. With KLiSH, we can sample images from GANs along with their segmentation masks and synthesize paired image-segmentation datasets. Using the synthesized datasets, we enable two downstream applications. First, we train semantic segmentation networks on these datasets and test them on real images, realizing unsupervised semantic segmentation. Second, we train image-to-image translation networks on the synthesized datasets, enabling semantic-conditional image synthesis without human annotations. © 2022, CC BY-SA.

关键词： Unsupervised learning

Fuel consumption analysis of driven trips with respect to route choice

学校读者我要写书评

暂无评论

Fuel consumption analysis of driven trips with respect to ro...

International Conference on Data Engineering Workshops

作者： Ekaterina Gilman Satu Tamminen Anja Keskinarkaus Theodoros Anagnostopoulos Xiang Su Susanna Pirttikangas Jukka Riekki Center for Ubiquitous Computing University of Oulu Finland Biomimetics and Intelligent Systems Group University of Oulu Finland Center for Machine Vision and Signal Analysis University of Oulu Finland Department of Infocommunication Technologies ITMO University Saint Petersburg Russia Department of Computer Science University of Helsinki Finland

ISBN: (数字)9781728142661

ISBN: (纸本)9781728142678

Advances in technology equip traffic domain with instruments to gather and analyse data for safe and fuel-efficient traveling. In this article, we elaborate on the effects that taxi drivers' route selection has on fuel efficiency. For this purpose, we fuse real driving behaviour data from taxi cabs, weather, digital map, and traffic situation information to gain understanding of how the routes are selected and what are the effects in terms of fuel-efficiency. Analysis of actually driven trips and their quickest and shortest counterparts is conducted to find out the fuel-efficiency consequences on route selection. The judgments are used for developing a fuel-consumption model, exploring further the route characteristics and external factors affecting fuel consumption.

关键词： Roads Fuels Public transportation Vehicles Meteorology Meters Fuses