检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sun, Jingtao Wang, Yaonan Feng, Mingtao Ding, Chao Shou, Mike Zheng Mian, Ajmal Saeed The College of Electrical and Information Engineering The National Engineering Research Centre for Robot Visual Perception and Control Hunan University Changsha410082 China Department of Electrical and Computer Engineering and Show Lab National University of Singapore Singapore117583 Singapore 2006 Australia

Fully-supervised category-level pose estimation aims to determine the 6-DoF poses of unseen instances from known categories, requiring expensive mannual labeling costs. Recently, various self-supervised category-level pose estimation methods have been proposed to reduce the requirement of the annotated datasets. However, most methods rely on synthetic data or 3D CAD model for self-supervised training, and they are typically limited to addressing single-object pose problems without considering multi-objective tasks or shape reconstruction. To overcome these challenges and limitations, we introduce a diffusion-driven self-supervised network for multi-object shape reconstruction and categorical pose estimation, only leveraging the shape priors. Specifically, to capture the SE(3)-equivariant pose features and 3D scale-invariant shape information, we present a Prior-Aware Pyramid 3D Point Transformer in our network. This module adopts a point convolutional layer with radial-kernels for pose-aware learning and a 3D scale-invariant graph convolution layer for object-level shape representation, respectively. Furthermore, we introduce a pretrain-to-refine self-supervised training paradigm to train our network. It enables proposed network to capture the associations between shape priors and observations, addressing the challenge of intra-class shape variations by utilising the diffusion mechanism. Extensive experiments conducted on four public datasets and a self-built dataset demonstrate that our method significantly outperforms state-of-the-art self-supervised category-level baselines and even surpasses some fully-supervised instance-level and category-level methods. The project page is released at Self-SRPE. Copyright © 2024, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation

Fourier Prompt Tuning for Modality-Incomplete Scene Segmenta...

引用

IEEE Symposium on Intelligent Vehicle

作者： Ruiping Liu Jiaming Zhang Kunyu Peng Yufan Chen Ke Cao Junwei Zheng M. Saquib Sarfraz Kailun Yang Rainer Stiefelhagen Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Mercedes-Benz Tech Innovation Germany School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework. However, the modality incompleteness in multi-modal segmentation remains under-explored. In this work, we establish a task called Modality-Incomplete Scene Segmentation (MISS), which encompasses both system-level modality absence and sensor-level modality errors. To avoid the predominant modality reliance in multi-modal fusion, we introduce a Missing-aware Modal Switch (MMS) strategy to proactively manage missing modalities during training. Utilizing bit-level batch-wise sampling enhances the model’s performance in both complete and incomplete testing scenarios. Furthermore, we introduce the Fourier Prompt Tuning (FPT) method to incorporate representative spectral information into a limited number of learnable prompts that maintain robustness against all MISS scenarios. Akin to fine-tuning effects but with fewer tunable parameters (1.1%). Extensive experiments prove the efficacy of our proposed approach, showcasing an improvement of 5.84% mIoU over the prior state-of-the-art parameter-efficient methods in modality missing. The source code is publicly available at https://***/RuipingL/MISS.

关键词： Training Rain Source coding Semantic segmentation Semantics Switches Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Beyond the Field-of-View: Enhancing Scene Visibility and perception with Clip-Recurrent Transformer

arXiv

引用

arXiv 2022年

作者： Shi, Hao Jiang, Qi Yang, Kailun Yin, Xiaoting Wang, Ze Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation the National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Company Ltd Shanghai201210 China

Vision sensors are widely applied in vehicles, robots, and roadside infrastructure. However, due to limitations in hardware cost and system size, camera Field-of-View (FoV) is often restricted and may not provide sufficient coverage. Nevertheless, from a spatiotemporal perspective, it is possible to obtain information beyond the camera’s physical FoV from past video streams. In this paper, we propose the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety. To achieve this, we introduce the FlowLens architecture, which explicitly employs optical flow and implicitly incorporates a novel clip-recurrent transformer for feature propagation. FlowLens offers two key features: 1) FlowLens includes a newly designed Clip-Recurrent Hub with 3D-Decoupled Cross Attention (DDCA) to progressively process global information accumulated over time. 2) It integrates a multi-branch Mix Fusion Feed Forward Network (MixF3N) to enhance the precise spatial flow of local features. To facilitate training and evaluation, we derive the KITTI360 dataset with various FoV mask, which covers both outer- and inner FoV expansion scenarios. We also conduct both quantitative assessments and qualitative comparisons of beyond-FoV semantics and beyond-FoV object detection across different models. We illustrate that employing FlowLens to reconstruct unseen scenes even enhances perception within the field of view by providing reliable semantic context. Extensive experiments and user studies involving offline and online video inpainting, as well as beyond-FoV perception tasks, demonstrate that FlowLens achieves state-of-the-art performance. The source code and dataset are made publicly available at https://github. com/MasterHow/FlowLens. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Human Action Recognition with Noisy Labels

arXiv

引用

arXiv 2024年

作者： Xu, Yi Peng, Kunyu Wen, Di Liu, Ruiping Zheng, Junwei Chen, Yufan Zhang, Jiaming Roitberg, Alina Yang, Kailun Stiefelhagen, Rainer Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Institute for Artificial Intelligence University of Stuttgart Germany School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model’s training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so far. In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark. Observations reveal that these baselines yield only marginal performance when dealing with sparse skeleton data. Consequently, we introduce a novel methodology, NoiseEraSAR, which integrates global sample selection, co-teaching, and Cross-Modal Mixture-of-Experts (CM-MOE) strategies, aimed at mitigating the adverse impacts of label noise. Our proposed approach demonstrates better performance on the established benchmark, setting new state-of-the-art standards. The source code for this study is accessible at https://***/xuyizdby/NoiseEraSAR. Copyright © 2024, The Authors. All rights reserved.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based SLAM Method Assisted by visual Marker in the Degenerate Scenes

A Graph-Based SLAM Method Assisted by Visual Marker in the D...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Jieqingxin Zhang Hui Zhang Xidong Zhou Bo Chen Xiangchuan Wang Tao Xu College of Electrical and Information Engineering Changsha University of Science and Technology Hunan China College of Robotics also with Robot Visual Perception and Control Technology National Engineering Research Center Hunan University Hunan China College of Electrical and Information Engineering Hunan University Hunan China

In the post-COVID-19 pandemic era, hospitals and other places have an urgent need for mobile robots with autonomous disinfection ability, and robots need to complete SLAM tasks to realize autonomous navigation. Lidar is widely used for indoor SLAM. However, due to the lack of geometric structure in the indoor environment, two-dimensional lidar information degrades, rendering the robot unable to obtain effective positioning. Therefore, we leverage the easy identification and high robustness of ARTag to fuse vision and range sensor information. We introduce ARTag as visual marker to assist positioning, establish observation window to screen the acquired ARTag pose. We employ the pose graph optimization method to optimize the visual markers and laser scanning results in the back end. This reduces the positioning errors caused by the degradation of lidar information and reduces the frequency of optimization by improving the back end optimization strategy. This method is applied in a UltraViolet C (UVC) Disinfection robot experiment. Experimental results show that our method effectively improves the positioning accuracy and robustness of the robot in the environments with degraded laser information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation in visual Reinforcement Learning via Self-Expert Imitation with Purifying Latent Feature

Domain Adaptation in Visual Reinforcement Learning via Self-...

引用

IEEE/RSJ International Conference on Intelligent robots and Systems (IROS)

作者： Lin Chen Jianan Huang Zhen Zhou Yaonan Wang Yang Mo Zhiqiang Miao Kai Zeng Mingtao Feng Danwei Wang School of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Visual Perception and Control Technology Changsha China School of Computer Science and Technology Xidian University Xian China School of Electrical and Electrical Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Generalizing visual reinforcement learning is fundamental to robot visual navigation, involving the acquisition of a policy from interactions with source environments to facilitate adaptation to analogous, yet unfamiliar target environments. Recent advancements capitalize on data augmentation techniques, self-supervised learning methods, and the generative adversarial network framework to train policy neural networks with enhanced generalizability. However, current methods, upon extracting domain-general latent features, further utilize these features to train the reinforcement learning policy, resulting in a decline in the performance of the learned policy guiding the agent to accomplish tasks. To tackle these challenges, a framework of self-expert imitation with purifying latent features was devised, empowering the policy to achieve robust and stable zero-shot generalization performance in visually similar domains previously unseen, without diminishing the performance of guiding the agent to accomplish tasks. The extraction method of domain-general latent features is proposed to enhance their quality based on the variational autoencoder. Extensive experiments have shown that our policy, compared with state-of-the-art counterparts, does not diminish the performance of the policy guiding the agent to accomplish tasks after generalization.

关键词： Training visualization Navigation Semantic segmentation Autoencoders Neural networks Reinforcement learning Self-supervised learning Feature extraction Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

L₁ Adaptive control-Based Formation Tracking of Multiple Quadrotors Without Linear Velocity Feedback Under Unknown Disturbances

引用

IEEE Transactions on Automation Science and engineering 2024年 22卷 5804-5815页

作者： Yang Hu Zhiqiang Miao Yaonan Wang Haoming Tang Xiangke Wang Wei He College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Visual Perception and Control Changsha China College of Intelligence Science and Technology National University of Defense Technology Changsha China School of Intelligence Science and Technology and the Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education University of Science and Technology Beijing Beijing China

This paper addresses the problem of formation control for a quadrotor swarm (QS) system with directed graph topology under external environmental disturbances and unreliable internal state acquisition. The proposed distributed robust control framework, based on a gemetric controller, incorporates ${\mathcal {L}}_control$ adaptive controllers and differentiator systems. First, the geometric formation controller is designed to implement the formation control of the nominal system. Then, ${\mathcal {L}}_control$ adaptive controllers are designed separately for each quadrotor’s position loop and attitude loop subsystems to address the effects of uncertainties such as external time-varying disturbances (matched and unmatched disturbances) and different mass variations of quadrotors. Furthermore, the differentiator system is devised to accurately estimate the higher-order derivatives of the non-directly-measurable velocity information and the virtual translation control signal, which enhances system accuracy while reducing computational complexity. The Lyapunov stability theory is employed to analyze the stability of the closed-loop system. Finally, the effectiveness and exceptional performance of this approach in QS formation control were validated through numerical simulation and experimental results. Note to Practitioners—The inspiration for this article comes from the issue of formation control in a cluster of quadrotor drones, which is also applicable to formation control in other types of drones. In this paper, a formation control algorithm based on ${\mathcal {L}}_control$ adaptive control strategy and arbitrary-order differentiation is designed. This algorithm can address not only the issue of time-varying wind disturbances frequently encountered during quadrotor drone flights but also the effects of unpredictable velocities and inconsistent masses of quadrotor drones. The disturbance rejection capability of this scheme enables quadrotor drones to be applied more safely and r

关键词： Quadrotors Formation control Adaptive control Topology Drones Autonomous aerial vehicles Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers

arXiv

引用

arXiv 2024年

作者： Jiao, Jianbin Cheng, Xina Chen, Weijie Yin, Xiaoting Shi, Hao Yang, Kailun School of Artificial Intelligence Xidian University China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer interaction, scene understanding, and rehabilitation training. Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content. Given the remarkable self-attention mechanism of transformers, capable of capturing the spatial-temporal correlation from multi-view video datasets, we propose a multi-stage framework for 3D sequence-to-sequence (seq2seq) human pose detection. Firstly, the spatial module represents the human pose feature by intra-image content, while the frame-image relation module extracts temporal relationships and 3D spatial positional relationship features between the multi-perspective images. Secondly, the self-attention mechanism is adopted to eliminate the interference from non-human body parts and reduce computing resources. Our method is evaluated on Human3.6M, a popular 3D human pose detection dataset. Experimental results demonstrate that our approach achieves state-of-the-art performance on this dataset. The source code will be available at https://***/WUJINHUAN/3D-human-pose. Copyright © 2024, The Authors. All rights reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Towards Single-Lens controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions

arXiv

引用

arXiv 2024年

作者： Qian, Xiaolong Jiang, Qi Gao, Yao Gao, Shaohua Yi, Zhonghua Sun, Lei Wei, Kai Li, Haifeng Yang, Kailun Wang, Kaiwei Bai, Jian State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China School of Robotics Hunan University Changsha410012 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China

controllable Depth-of-Field (DoF) imaging commonly produces amazing visual effects based on heavy and expensive high-end lenses. However, confronted with the increasing demand for mobile scenarios, it is desirable to achieve a lightweight solution with Minimalist Optical Systems (MOS). This work centers around two major limitations of MOS, i.e., the severe optical aberrations and uncontrollable DoF, for achieving single-lens controllable DoF imaging via computational methods. A Depth-aware controllable DoF Imaging (DCDI) framework is proposed equipped with All-in-Focus (AiF) aberration correction and monocular depth estimation, where the recovered image and corresponding depth map are utilized to produce imaging results under diverse DoFs of any high-end lens via patch-wise convolution. To address the depth-varying optical degradation, we introduce a Depth-aware Degradation-adaptive Training (DA2T) scheme. At the dataset level, a Depth-aware Aberration MOS (DAMOS) dataset is established based on the simulation of Point Spread Functions (PSFs) under different object distances. Additionally, we design two plug-and-play depth-aware mechanisms to embed depth information into the aberration image recovery for better tackling depth-aware degradation. Furthermore, we propose a storage-efficient Omni-Lens-Field model to represent the 4D PSF library of various lenses. With the predicted depth map, recovered image, and depth-aware PSF map inferred by Omni-Lens-Field, single-lens controllable DoF imaging is achieved. To the best of our knowledge, we are the first to explore the single-lens controllable DoF imaging solution. Comprehensive experimental results demonstrate that the proposed framework enhances the recovery performance, and attains impressive single-lens controllable DoF imaging results, providing a seminal baseline for this field. The source code and the established dataset will be publicly available at https://***/XiaolongQian/DCDI. Copyright © 2024, The A

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers

Towards Precise 3D Human Pose Estimation with Multi-Perspect...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jianbin Jiao Xina Cheng Weijie Chen Xiaoting Yin Hao Shi Kailun Yang School of Artificial Intelligence Xidian University China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as humancomputer interaction, scene understanding, and rehabilitation training. Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content. Given the remarkable selfattention mechanism of transformers, capable of capturing the spatial-temporal correlation from multi-view video datasets, we propose a multi-stage framework for 3D sequence-to-sequence (seq2seq) human pose detection. Firstly, the spatial module represents the human pose feature by intra-image content, while the frame-image relation module extracts temporal relationships and 3D spatial positional relationship features between the multiperspective images. Secondly, the self-attention mechanism is adopted to eliminate the interference from non-human body parts and reduce computing resources. Our method is evaluated on Human3.6M, a popular 3D human pose detection dataset. Experimental results demonstrate that our approach achieves stateof-the-art performance on this dataset. The source code will be available at https://***/WUJINHUAN/3D-human-pose.

关键词： Training Three-dimensional displays Correlation Computational modeling Source coding Pose estimation Video sequences

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：