检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： George Retsinas Panagiotis P. Filntisis Radek Daněček Victoria F. Abrevaya Anastasios Roussos Timo Bolkarr Petros Maragos Institute of Robotics Athena Research Center Maroussi Greece MPI for Intelligent Systems Tübingen Germany Institute of Computer Science (ICS) Foundation for Research & Technology - Hellas (FORTH) Greece School of Electrical & Computer Engineering National Technical University of Athens Greece

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these meth-ods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expres-sive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geom-etry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between ren-dering and input image further hinders the learning pro-cess. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the ren-dered predicted mesh geometry, and sparsely sampled pix-els of the input image, generates a face image. As the neural rendering gets color information from sampled im-age pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for di-verse expressions. Our qualitative, quantitative and partic-ularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction. For our method's source code, demo video and more, please visit our project webpage: https://***/smirk/.

关键词： Training Geometry Solid modeling Three-dimensional displays Accuracy Face recognition Training data

来源：评论

学校读者我要写书评

暂无评论

Robotic Detection of a Human-Comprehensible Gestural Language for Underwater Multi-Human-Robot Collaboration

arXiv

引用

arXiv 2022年

作者： Enan, Sadman Sakib Fulton, Michael Sattar, Junaed The Department of Computer Science & Engineering The Minnesota Robotics Institute University of Minnesota MN United States

In this paper, we present a motion-based robotic communication framework that enables non-verbal communication among autonomous underwater vehicles (AUVs) and human divers. We design a gestural language for AUV-to-AUV communication which can be easily understood by divers observing the conversation unlike typical radio frequency, light, or audio based AUV communication. To allow AUVs to visually understand a gesture from another AUV, we propose a deep network (RRCommNet) which exploits a self-attention mechanism to learn to recognize each message by extracting maximally discriminative spatio-temporal features. We train this network on diverse simulated and real-world data. Our experimental evaluations, both in simulation and in closed-water robot trials, demonstrate that the proposed RRCommNet architecture is able to decipher gesture-based messages with an average accuracy of 88-94% on simulated data, 73-83% on real data (depending on the version of the model used). Further, by performing a message transcription study with human participants, we also show that the proposed language can be understood by humans, with an overall transcription accuracy of 88%. Finally, we discuss the inference runtime of RRCommNet on embedded GPU hardware, for real-time use on board AUVs in the field. Copyright © 2022, The Authors. All rights reserved.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Generating Manipulation Sequences using Reinforcement Learning and Behavior Trees for Peg-In-Hole Task

Generating Manipulation Sequences using Reinforcement Learni...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Xu, Jiahua Lin, Yunhan Zhou, Haotian Min, Huasong Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Reinforcement Learning (RL), a method of learning skills through trial-and-error, has been successfully used in many robotics applications in recent years. We combine manipulation primitives (MPs), behavior trees (BTs), and reinforcement learning to propose an algorithm for peg-in-hole tasks, which speeds up the convergence of the RL model and enhance the adaptability of the dynamic environment. Manipulation primitives are used as actions for RL, which can reduce the gap between control instruction and robotic actions and speed up the convergence of the RL model. Behavior trees are used as robot behavior control, which makes robots can actively adapt to the changes in the environment. In experiments, RL-BT, from the combination of RL and BT, is designed for the peg-in-hole task in the Gazebo simulation environment by using UR5 as the actuator. The experiments are conducted on a simple peg and a complex multi-hole peg by three aspects, which include convergence speed verification experiment, adaptability of dynamic environment experiment, and algorithm robustness experiment. The experiment result proves that our RL-BT can speed up the convergence and adapt to the changes in the environment. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StereoNavNet: Learning to Navigate using Stereo Cameras with Auxiliary Occupancy Voxels

arXiv

引用

arXiv 2024年

作者： Li, Hongyu Padır, Taşkın Jiang, Huaizu Department of Computer Science Brown University ProvidenceRI United States Institute for Experiential Robotics Northeastern University BostonMA United States Khoury College of Computer Sciences Northeastern University BostonMA United States

Visual navigation has received significant attention recently. Most of the prior works focus on predicting navigation actions based on semantic features extracted from visual encoders. However, these approaches often rely on large datasets and exhibit limited generalizability. In contrast, our approach draws inspiration from traditional navigation planners that operate on geometric representations, such as occupancy maps. We propose StereoNavNet (SNN), a novel visual navigation approach employing a modular learning framework comprising perception and policy modules. Within the perception module, we estimate an auxiliary 3D voxel occupancy grid from stereo RGB images and extract geometric features from it. These features, along with user-defined goals, are utilized by the policy module to predict navigation actions. Through extensive empirical evaluation, we demonstrate that SNN outperforms baseline approaches in terms of success rates, success weighted by path length, and navigation error. Furthermore, SNN exhibits better generalizability, characterized by maintaining leading performance when navigating across previously unseen environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Visual Detection of Diver Attentiveness for Underwater Human-Robot Interaction

arXiv

引用

arXiv 2022年

作者： Enan, Sadman Sakib Sattar, Junaed Department of Computer Science & Engineering Minnesota Robotics Institute University of Minnesota MN United States

Many underwater tasks, such as cable-and-wreckage inspection, search-and-rescue, benefit from robust human-robot interaction (HRI) capabilities. With the recent advancements in vision-based underwater HRI methods, autonomous underwater vehicles (AUVs) can communicate with their human partners even during a mission. However, these interactions usually require active participation especially from humans (e.g., one must keep looking at the robot during an interaction). Therefore, an AUV must know when to start interacting with a human partner, i.e., if the human is paying attention to the AUV or not. In this paper, we present a diver attention estimation framework for AUVs to autonomously detect the attentiveness of a diver and then navigate and reorient itself, if required, with respect to the diver to initiate an interaction. The core element of the framework is a deep neural network (called DATT-Net) which exploits the geometric relation among 10 facial keypoints of the divers to determine their head orientation. Our on-the-bench experimental evaluations (using unseen data) demonstrate that the proposed DATT-Net architecture can determine the attentiveness of human divers with promising accuracy. Our real-world experiments also confirm the efficacy of DATT-Net which enables real-time inference and allows the AUV to position itself for an AUV-diver interaction. Copyright © 2022, The Authors. All rights reserved.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Physical Interaction and Manipulation of the Environment using Aerial Robots

arXiv

引用

arXiv 2022年

作者： Keipour, Azarakhsh The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

The physical interaction of aerial robots with their environment has countless potential applications and is an emerging area with many open challenges. Fully-actuated multirotors have been introduced to tackle some of these challenges. They provide complete control over position and orientation and eliminate the need for attaching a multi-DoF manipulation arm to the robot. However, there are still several open problems before they can be used in real-world applications. Researchers have introduced some methods for the physical interaction of fully-actuated multirotors in limited settings. Their experiments primarily use prototype-level software without an efficient path to integrating these methods into real-world applications. This thesis describes a new controller design that provides a cost-effective solution for integrating these robots with the existing software and hardware flight systems for real-world applications. It further expands the controller to physical interaction applications to show its flexibility and effectiveness. On the other hand, the existing control approaches for fully-actuated robots assume conservative limits for the thrusts and moments available to the robot. Using conservative assumptions for these already-inefficient robots makes their interactions even less optimal and may even result in many feasible physical interaction applications becoming infeasible. This work proposes a real-time method for estimating the complete set of instantaneously available forces and moments that robots can use to optimize their physical interaction performance. Finally, many real-world applications where aerial robots can improve the existing manual solutions deal with deformable objects. However, the perception of deformable objects and planning for their manipulation is still challenging. Additionally, no studies have been performed to analyze the requirements of aerial tasks that involve deformable objects. This research explores how aerial physical

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

PL-TD3: A Dynamic Path Planning Algorithm of Mobile Robot

PL-TD3: A Dynamic Path Planning Algorithm of Mobile Robot

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Tan, Yijian Lin, Yunhan Liu, Tong Min, Huasong Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

In this paper, Prioritized Experience Replay (PER) strategy and Long Short Term Memory (LSTM) neural network are introduced to the path planning process of mobile robots, which solves the problems of slow convergence and inaccurate perception of dynamic obstacles with the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. We dubbed this new method as PL-TD3. Firstly, we improve the convergence speed of the algorithm by introducing PER strategy. Secondly, we use LSTM neural network to achieve the improvement of the algorithm for dynamic obstacle perception. In order to verify the method of this paper, we design static environment, dynamic environment and adaptability to dynamic experiments to compare and analyze the methods before and after improvement. The experimental results show that PL-TD3 outperforms TD3 in terms of execution time and execution path length in all environments. © 2022 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Classification of Jackfruit Species Using Deep Learning Model

Classification of Jackfruit Species Using Deep Learning Mode...

引用

Recent Advances in Information Technology for Sustainable Development (ICRAIS), International Conference on

作者： Veeresha R K Shilpa Karegoudra Bhavin Kumar Pavan Pavan Department of Robotics and Artificial Intelligence NMAM Institute of Technology (NMAMIT) Nitte (Deemed to be University) Udupi India Department of Computer Science and Engineering NMAM Institute of Technology (NMAMIT) Nitte (Deemed to be University) Udupi India

ISBN: (数字)9798350354461

ISBN: (纸本)9798350354522

Identifying Jackfruit spices using a deep learning model involves leveraging advanced neural network architectures to classify spices accurately. The model is trained on a dataset containing images of various spices commonly used with Jackfruit, such as deng surya, manmohan, prakashchandra, vietnamearly, and others. Through multiple layers of convolutional neural networks (CNNs) and possibly recurrent neural networks (RNNs), the model learns intricate patterns and features within the images to differentiate between different species. Transfer learning techniques might also be employed to adapt pre-trained models to the specific task of spice identification. The model's performance is evaluated on a separate test dataset to measure its accuracy, precision, recall, and F1 score. The paper provides a comprehensive overview of the deep learning approach to identifying Jackfruit spices, highlighting its potential applications in culinary research, food industry automation, and dietary analysis.

关键词： Deep learning Training Productivity Adaptation models Accuracy Recurrent neural networks Transfer learning Predictive models Sustainable development Information technology

来源：评论

学校读者我要写书评

暂无评论

Analysis on Chest X-ray and Computed Tomography Images to Detect COVID-19 Based on Deep Learning Techniques

Analysis on Chest X-ray and Computed Tomography Images to De...

引用

2022 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2022

作者： Kanimozhi, J. Mohanasuganthi, N. Priyadharshini, A. Rohini, M.S. Swathilakshmi, V. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Chennai India Robotics and Automation Engineering Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Computer Science and Engineering Sri Manakula Vinayagar Engineering College Puducherry India

ISBN: (纸本)9798350333848

More than 6.3 million individuals have died as a result of the Corona Virus Disease 2019 (COVID-19), which spoiled many more human health globally. Since COVID-19 is a pandemic that is rapidly spreading, early discovery is essential to halting the infection's spread. Images of the lungs are utilised to identify coronavirus infection. For the identification of Corona Virus Disease, chest X-ray (CXR) and computed tomography (CT) images are available. Deep learning methods are proved to be effective and perform better in medical imaging applications. This study examines lung CT pictures, classifies and segments them, and uses the results to identify whether a patient tested is affected by COVID-19 or not using Deep learning techniques. The COVID detection performance of the deep learning architectures GG19, MobileNet, COVID-Net (PEPX), Squeez Net, U-Net, DarkNet and VGG16 are analysed - it was shown that U-Net combined VGG16 (acc98.89%) and VGG19 (acc-98.05%) performs the best, followed by MobileNet and QueezNet. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TIGRIS: An Informed Sampling-based Algorithm for Informative Path Planning

arXiv

引用

arXiv 2022年

作者： Moon, Brady Chatterjee, Satrajit Scherer, Sebastian The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

Informative path planning is an important and challenging problem in robotics that remains to be solved in a manner that allows for wide-spread implementation and real-world practical adoption. Among various reasons for this, one is the lack of approaches that allow for informative path planning in high-dimensional spaces and non-trivial sensor constraints. In this work we present a sampling-based approach that allows us to tackle the challenges of large and high-dimensional search spaces. This is done by performing informed sampling in the high-dimensional continuous space and incorporating potential information gain along edges in the reward estimation. This method rapidly generates a global path that maximizes information gain for the given path budget constraints. We discuss the details of our implementation for an example use case of searching for multiple objects of interest in a large search space using a fixed-wing UAV with a forward-facing camera. We compare our approach to a sampling-based planner baseline and demonstrate how our contributions allow our approach to consistently out-perform the baseline by 18.0%. With this we thus present a practical and generalizable informative path planning framework that can be used for very large environments, limited budgets, and high dimensional search spaces, such as robots with motion constraints or high-dimensional configuration spaces. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：