检索结果-内蒙古大学图书馆

BirdSLAM: Monocular multibody SLAM in bird’s-eye view 16

BirdSLAM: Monocular multibody SLAM in bird’s-eye view

16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2021

作者： Daga, Swapnil Nair, Gokul B. Ramesh, Anirudha Sajnani, Rahul Ansari, Junaid Ahmed Madhava Krishna, K. Robotics Research Center KCIS IIIT Hyderabad India Embedded Systems and Robotics TCS Innovation Labs Kolkata India

ISBN: (纸本)9789897584886

In this paper, we present BirdSLAM, a novel simultaneous localization and mapping (SLAM) system for the challenging scenario of autonomous driving platforms equipped with only a monocular camera. BirdSLAM tackles challenges faced by other monocular SLAM systems (such as scale ambiguity in monocular reconstruction, dynamic object localization, and uncertainty in feature representation) by using an orthographic (bird’s-eye) view as the configuration space in which localization and mapping are performed. By assuming only the height of the ego-camera above the ground, BirdSLAM leverages single-view metrology cues to accurately localize the ego-vehicle and all other traffic participants in bird’s-eye view. We demonstrate that our system outperforms prior work that uses strictly greater information, and highlight the relevance of each design decision via an ablation analysis. Copyright © 2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Cooperative Aerial Slung Load Transportation Using a Novel Adaptive Sliding Mode Controller

Cooperative Aerial Slung Load Transportation Using a Novel A...

引用

2021 International Conference on Unmanned Aircraft systems, ICUAS 2021

作者： N S, Abhinay Shobhit, Shubhankar Sridhar, Nithya Das, Kaushik Embedded Systems and Robotics Reserach Group Tcs Research India

ISBN: (纸本)9780738131153

This paper presents a decentralized approach to transport a cable suspended load using multiple Unmanned Aerial Vehicles (UAVs). The proposed approach is decentralized in the sense that the trajectory for each of the UAVs is computed offline using the kinematics of the system and the desired path of the load. This approach enabled the task of cooperative transportation to be treated as a problem of multiple UAVs, each carrying a cable suspended load. A neural adaptive sliding mode controller proposed by the authors in an earlier work is then deployed on each of the UAVs to track the trajectory while minimizing the load swing. Since the system of an UAV carrying a suspended load is underactuated, the conditions on the sliding surface variables that ensure the stability of the system are also given. The performance of the proposed approach is tested with payloads of non-uniform density and uncertain mass, using Gazebo simulations. The performance is compared against an adaptive sliding mode controller which motivated the design of the proposed controller. © 2021 IEEE.

关键词： Cables

来源：评论

学校读者我要写书评

暂无评论

Designing and evaluating a system for studying EarEEG signals

Designing and evaluating a system for studying EarEEG signal...

引用

Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers

作者： Adarsh Meghana Kartik Muralidharan Jayavardhana Gubbi Ramesh Kumar Ramakrishnan Arpan Pal TCS Research India Tata Consultancy Services India Embedded Systems and Robotics TCS Research India

ISBN: (纸本)9781450394239

Electroencephalography (EEG) allows the study of the brain in humans with applications in areas of Psychology, Brain-Computer Interfaces, and Neuromarketing. The conventional systems limit the applications of EEG to lab environments, but recent developments towards portable EEG have allowed brain studies outside the laboratory in more realistic situations. One such direction is the Ear EEG, a wearable concept for recording the EEG using an ear worn device. This paper discusses a system design to study the Ear EEG compared to the scalp EEG using the OpenBCI. We evaluate the signal quality obtained with Ear EEG using a customized earpiece and demonstrate the feasibility of recording alpha attenuation using Ear EEG.

关键词： EEG EarEEG

来源：评论

学校读者我要写书评

暂无评论

Speech-Driven Facial Animation Using Cascaded GANs for Learning of Motion and Texture 16th

Speech-Driven Facial Animation Using Cascaded GANs for Learn...

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Das, Dipanjan Biswas, Sandika Sinha, Sanjana Bhowmick, Brojeshwar Embedded Systems and Robotics TCS Research Kolkata India

ISBN: (纸本)9783030585761

Speech-driven facial animation methods should produce accurate and realistic lip motions with natural expressions and realistic texture portraying target-specific facial characteristics. Moreover, the methods should also be adaptable to any unknown faces and speech quickly during inference. Current state-of-the-art methods fail to generate realistic animation from any speech on unknown faces due to their poor generalization over different facial characteristics, languages, and accents. Some of these failures can be attributed to the end-to-end learning of the complex relationship between the multiple modalities of speech and the video. In this paper, we propose a novel strategy where we partition the problem and learn the motion and texture separately. Firstly, we train a GAN network to learn the lip motion in a canonical landmark using DeepSpeech features and induce eye-blinks before transferring the motion to the person-specific face. Next, we use another GAN based texture generator network to generate high fidelity face corresponding to the motion on person-specific landmark. We use meta-learning to make the texture generator GAN more flexible to adapt to the unknown subjects traits of the face during inference. Our method gives significantly improved facial animation than the state-of-the-art methods and generalizes well across the different datasets, different languages, and accents, and also works reliably well in presence of noises in the speech. © 2020, Springer Nature Switzerland AG.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

VacciNet: Towards a Smart Framework for Learning the Distribution Chain Optimization of Vaccines for a Pandemic

arXiv

引用

arXiv 2022年

作者： Mondal, Jayeeta Dutta, Jeet Barua, Hrishav Bakul Embedded Device & Intelligent Systems Group TCS Research West Bengal Kolkata India Robotics & Autonomous Systems Group TCS Research West Bengal Kolkata India

Vaccinations against viruses have always been the need of the hour since long past. However, it is hard to efficiently distribute the vaccines (on time) to all the corners of a country, especially during a pandemic. Considering the vastness of the population, diversified communities, and demands of a smart society, it is an important task to optimize the vaccine distribution strategy in any country/state effectively. Although there is a profusion of data (Big Data) from various vaccine administration sites that can be mined to gain valuable insights about mass vaccination drives, very few attempts has been made towards revolutionizing the traditional mass vaccination campaigns to mitigate the socio-economic crises of pandemic afflicted countries. In this paper, we bridge this gap in studies and experimentation. We collect daily vaccination data which is publicly available and carefully analyze it to generate meaning-full insights and predictions. We put forward a novel framework leveraging Supervised Learning and Reinforcement Learning (RL) which we call VacciNet, that is capable of learning to predict the demand of vaccination in a state of a country as well as suggest optimal vaccine allocation in the state for minimum cost of procurement and supply. At the present, our framework is trained and tested with vaccination data of the *** Codes Artificial intelligence, Machine learning, Deep learning Copyright © 2022, The Authors. All rights reserved.

关键词： Vaccines

来源：评论

学校读者我要写书评

暂无评论

Transparency Enhancement in Teleoperation: An Improved Model-Free Predictor for Varying Network Delay in Telerobotic Application

Transparency Enhancement in Teleoperation: An Improved Model...

引用

European Control Conference (ECC)

作者： Nithya Sridhar Rolif Lima Utsav Rai Vismay Vakharia Kaushik Das Balamuralidhar P Embedded Systems and Robotics Research Group of TCS Research Bangalore India

This work proposes a useful modification to an existing model-free predictor for handling network delays in teleoperation. This modification consists of an adaptively varying parameter that depends on delay at the current instant and the latest prediction error terms, which was not in use in the existing method. The conception of the proposed modification was obtained through theoretical analysis and later implemented for a mobile robotic platform. It was observed that the modified predictor adapted well to the varying delay and improved the system transparency by a maximum of 86% and by 15% in average. Additionally, this work also proposes a method to compensate for missing data using the same model-free predictor, showing a maximum transparency improvement by 12%.

关键词： Adaptation models Europe Predictive models Data models Delays Telerobotics

来源：评论

学校读者我要写书评

暂无评论

Deep Dictionary Learning for Inpainting 7th

Deep Dictionary Learning for Inpainting

引用

7th National Conference on Computer Vision, Pattern Recognition, Image Processing, and Graphics, NCVPRIPG 2019

作者： Seemakurthy, K. Majumdar, A. Gubbi, J. Sandeep, N.K. Varghese, A. Deshpande, S. Girish Chandra, M. Balamurali, P. Embedded Systems and Robotics TCS Research and Innovation Bengaluru India Electronics and Communications Engineering IIIT Delhi New Delhi India

ISBN: (纸本)9789811586965

Sparse coding techniques have shown to perform well in solving the conventional inverse imaging problems like inpainting and denoising. In the recent past, the performance of deep learning architectures in solving these inverse imaging problems have exceeded the conventional approaches several times. The only limitation of these architectures is the requirement of large volumes of training data. Deep dictionary learning (DDL) is an emerging approach and has been shown to solve some important classification problems in the scenarios where there is a scarcity of training data. DDL framework effectively combines the advantages of sparse coding and deep learning. In this paper, DDL framework is adapted to solve the inverse imaging problem with specific focus on imaging inpainting. An alternating minimization (AM) approach is proposed to derive the dictionaries and their corresponding sparse coefficients at each level of the DDL framework. The aim of this work is to show that the multilevel dictionaries can be leveraged to derive the sparse representations without compromising on the restoration quality of streaked multispectral images. Inspite of being a conventional machine learning based technique, we show that the performance of our approach is better to the state-of-the-art deep learning approaches for multispectral image inpainting. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Multi-object Monocular SLAM for Dynamic Environments 31

Multi-object Monocular SLAM for Dynamic Environments

引用

31st IEEE Intelligent Vehicles Symposium, IV 2020

作者： Nair, Gokul B. Daga, Swapnil Sajnani, Rahul Ramesh, Anirudha Ansari, Junaid Ahmed Jatavallabhula, Krishna Murthy Krishna, K. Madhava Robotics Research Center Kcis Iiit Hyderabad India Embedded Systems and Robotics Tcs Innovation Labs Kolkata India Mila Universite de Montreal Canada

In this paper, we tackle the problem of multibody SLAM from a monocular camera. The term multibody, implies that we track the motion of the camera, as well as that of other dynamic participants in the scene. The quintessential challenge in dynamic scenes is unobservability: it is not possible to unambiguously triangulate a moving object from a moving monocular camera. Existing approaches solve restricted variants of the problem, but the solutions suffer relative scale ambiguity (i.e., a family of infinitely many solutions exist for each pair of motions in the scene). We solve this rather intractable problem by leveraging single-view metrology, advances in deep learning, and category-level shape estimation. We propose a multi pose-graph optimization formulation, to resolve the relative and absolute scale factor ambiguities involved. This optimization helps us reduce the average error in trajectories of multiple bodies over real-world datasets, such as KITTI [1]. To the best of our knowledge, our method is the first practical monocular multi-body SLAM system to perform dynamic multi-object and ego localization in a unified framework in metric scale. © 2020 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Identity-Preserving Realistic Talking Face Generation

Identity-Preserving Realistic Talking Face Generation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Sanjana Sinha Sandika Biswas Brojeshwar Bhowmick Embedded Systems and Robotics TCS Research and Innovation

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Speech-driven facial animation is useful for a variety of applications such as telepresence, chatbots, etc. The necessary attributes of having a realistic face animation are 1) audiovisual synchronization (2) identity preservation of the target individual (3) plausible mouth movements (4) presence of natural eye blinks. The existing methods mostly address the audiovisual lip synchronization, and few recent works have addressed synthesis of natural eye blinks for overall video realism. In this paper, we propose a method for identity-preserving realistic facial animation from speech. We first generate person-independent facial landmarks from audio using DeepSpeech features for invariance to different voices, accents, etc. To add realism, we impose eye blinks on facial landmarks using unsupervised learning and retarget the person-independent landmarks to person-specific landmarks to preserve the identity-related facial structure which helps in generation of plausible mouth shapes of the target identity. Finally, we use LSGAN to generate the facial texture from person-specific facial landmarks, using an attention mechanism that helps to preserve identity-related texture. An extensive comparison of our proposed method with the current state-of-the-art methods demonstrate a significant improvement in terms of lip synchronization accuracy, image reconstruction quality, sharpness, and identity-preservation. A user study also reveals improved realism of our animation results over the state-of-the-art methods. To the best of our knowledge, this is the first work in speech-driven 2D facial animation that simultaneously addresses all the above-mentioned attributes of a realistic speech driven face animation.

关键词： Faces Image color analysis Mouth Facial animation Shape Lips Synchronization

来源：评论

学校读者我要写书评

暂无评论

ReNEW: A practical module for reliable routing in networks of energy-harvesting wireless sensors

ReNEW: A practical module for reliable routing in networks o...

引用

作者： Prasad, R. Venkatesha Rao, Vijay S. Sarkar, Chayan Niemegeers, Ignas Embedded and Networked Systems Group Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2600 AA Netherlands Robotics and Autonomous Systems TCS Research and Innovation Labs Kolkata700160 India Faculty of Electrical Engineering Eindhoven University of Technology Eindhoven5612 AZ Netherlands

It is a huge challenge to run IoT devices/sensors powered solely through ambient harvested energy. Since the harvested energy is less and is stochastic in nature, it is extremely challenging to achieve low latency and high reliability. To this end, we propose a distributed, energy-management module called ReNEW, using Constructive Interference (CI) to achieve our target of increased reliability, especially in the low harvesting regimes. We choose CI-based protocols to leverage low latency guarantees. Specifically, we propose a Markov-Decision model to maximize the energy utility in the infinite horizon by allocating energy optimally using a threshold-optimal policy. Since an energy scheduler is insufficient we propose distributed techniques to conserve energy on redundant nodes in the network, and dynamically activate them based on feedback. We implement ReNEW on Indriya and FlockLab testbeds for real-world scenarios in a network of 20 source nodes out of the 30 nodes. ReNEW collects data periodically with 2.5 times higher packet reception compared to LWB when the harvested energy is as low as 50μ J/s for 100B packets every 30s with a saving of 25% higher residual energy. In a nutshell, by integrating ReNEW with CI based protocols, we enable guaranteed latency and increased reliability in battery-less devices/networks. © 2017 IEEE.

关键词： Energy harvesting

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：