检索结果-内蒙古大学图书馆

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

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

TS-CGNet: Temporal-Spatial Fusion Meets centerline-Guided Diffusion for BEV Mapping

arXiv

引用

arXiv 2025年

作者： Hong, Xinying Li, Siyu Zeng, Kang Shi, Hao Peng, Bomin Yang, Kailun Li, Zhiyong The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China

Bird’s Eye View (BEV) perception technology is crucial for autonomous driving, as it generates top-down 2D maps for environment perception, navigation, and decision-making. Nevertheless, the majority of current BEV map generation studies focusing on visual map generation lack depth-aware reasoning capabilities. They exhibit limited efficacy in managing occlusions and handling complex environments, with a notable decline in perceptual performance under adverse weather conditions or low-light scenarios. Therefore, this paper proposes TS-CGNet, which leverages Temporal-Spatial fusion with centerline-Guided diffusion. This visual framework, grounded in prior knowledge, is designed for integration into any existing network for building BEV maps. Specifically, this framework is decoupled into three parts: Local mapping system involves the initial generation of semantic maps using purely visual information;The Temporal-Spatial Aligner Module (TSAM) integrates historical information into mapping generation by applying transformation matrices;The centerline-Guided Diffusion Model (CGDM) is a prediction module based on the diffusion model. CGDM incorporates centerline information through spatial-attention mechanisms to enhance semantic segmentation reconstruction. We construct BEV semantic segmentation maps by our methods on the public nuScenes and the robustness benchmarks under various corruptions. Our method improves 1.90%, 1.73%, and 2.87% for perceived ranges of 60×30m, 120×60m, and 240×60m in the task of BEV HD mapping. TS-CGNet attains an improvement of 1.92% for perceived ranges of 100×100m in the task of BEV semantic mapping. Moreover, TS-CGNet achieves an average improvement of 2.92% in detection accuracy under varying weather conditions and sensor interferences in the perception range of 240×60m. The source code will be publicly available at https://***/krabs-H/TS-CGNet. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

CT-UIO: Continuous-Time UWB-Inertial-Odometer Localization Using Non-Uniform B-spline with Fewer Anchors

arXiv

引用

arXiv 2025年

作者： Sun, Jian Sun, Wei Zhang, Genwei Yang, Kailun Li, Song Meng, Xiangqi Deng, Na Tan, Chongbin National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410012 China College of Electrical and Information Engineering Hunan University China School of Robotics Hunan University Changsha410012 China State Key Laboratory of NBC Protection for Civilian Beijing102205 China

Ultra-wideband (UWB) based positioning with fewer anchors has attracted significant research interest in recent years, especially under energy-constrained conditions. However, most existing methods rely on discrete-time representations and smoothness priors to infer a robot’s motion states, which often struggle with ensuring multi-sensor data synchronization. In this paper, we present an efficient UWB-Inertial-odometer localization system, utilizing a non-uniform B-spline framework with fewer anchors. Unlike traditional uniform B-spline-based continuous-time methods, we introduce an adaptive knot-span adjustment strategy for non-uniform continuous-time trajectory representation. This is accomplished by adjusting control points dynamically based on movement speed. To enable efficient fusion of IMU and odometer data, we propose an improved Extended Kalman Filter (EKF) with innovation-based adaptive estimation to provide short-term accurate motion prior. Furthermore, to address the challenge of achieving a fully observable UWB localization system under few-anchor conditions, the Virtual Anchor (VA) generation method based on multiple hypotheses is proposed. At the backend, we propose a CT-UIO factor graph with an adaptive sliding window for global trajectory estimation. Comprehensive experiments conducted on corridor and exhibition hall datasets validate the proposed system’s high precision and robust performance. The codebase and datasets of this work will be open-sourced at https://***/JasonSun623/CT-UIO. Copyright © 2025, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

arXiv

引用

arXiv 2024年

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan The College of Electrical and Information Engineering Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology Hunan Changsha China The College of Information Science and Engineering Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Changsha China

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 21.5% and 11.3% on mean mAP drop rate, respectively. The code of MTGA will be released after the paper is accepted. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-based Fault-Tolerant control for Unmanned Aerial Vehicles

Reinforcement Learning-based Fault-Tolerant Control for Unma...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Guoqi Wang Xudong Wang Yang Li Ziwei Gao Zhaoke Ning National Engineering Research Center of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle College of Mechanical and Vehicle Engineering Hunan University Changsha China School of Aeronautics and Astronautics Sichuan University Chengdu China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

This paper focuses on the fault-tolerant control (FTC) problem for unmanned aerial vehicles (UAVs) subject to possible multiple actuator failures, which is a tough problem to solve with traditional FTC methods since they usually require accurate mathematical models. To address the limitation of traditional FTC methods, a model-free FTC approach is proposed based on reinforcement learning (RL). Subsequently, the proposed approach is applied to construct fault-tolerant controller for UAVs without any knowledge of the quadrotor dynamic information. Then, an end-to-end control policy that can tolerant actuator failures is obtained, which can map the state of the UAVs directly to the control commands of the four rotors after learning. Finally, the effectiveness of the proposed fault-tolerant approach is demonstrated by using the flexible modular quadrotor simulator.

关键词： Fault tolerance Actuators Trajectory tracking Fault tolerant systems Autonomous aerial vehicles Stability analysis Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Three-Degree-of-Freedom Pose through Temporal Phase-Shifted Low-Coherence Spatial Interferograms 16

Reconstructing Three-Degree-of-Freedom Pose through Temporal...

引用

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Shi, Liheng Zhang, Jinxu Gu, Yingying Gai, Fangqin Liu, Jing Wu, Guanhao Tsinghua University State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision Instrument Beijing100084 China Yangtze Delta Region Institute of Tsinghua University Zhejiang Research Center of Opto-electronic Sensing Zhejiang 314006 China Beijing Institute of Control Engineering Space Optoelectronic Measurement and Perception Lab. Beijing100190 China China Academy of Space Technology National Key Laboratory of Space Intelligent Control Beijing100094 China

We introduce a method for measuring three degrees of freedom using low-coherence light and temporal phase-shifting to discern position and orientation from the coherence envelope shape, enabling direct measurement wit... 详细信息

ISBN: (纸本)9798350372076

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

A Muti-stage Selection Filter Based on Wavelet Packet and 2DCNN for Fault Diagnosis of Rotating Machinery

A Muti-stage Selection Filter Based on Wavelet Packet and 2D...

引用

Chinese control Conference (CCC)

作者： Wenbin He Jianxu Mao Li Liu Zhe Li Miao Yang Yaonan Wang College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha China State Grid Hunan Electric Power Company Limited Research Institute Changsha China

Fault information of rotating machinery is often drowned in strong noise signals, so it is crucial to accurately identify faults from high-intensity noise signals. In this article, an end-to-end fault diagnosis model is developed, which consists of a multi-stage selection filter based on wavelet packet and 2D-CNN. First, the original measured mechanical signals were processed by the three-level wavelet packet decomposition to obtain eight sub-bands with coefficient matrices. Second, the signal is reconstructed using different numbers of sub-bands, where the number is increased by one at a time to obtain eight different multi-stage reconstructed signals. Third, the reconstructed signals are reorganized into 2D signal maps; and a parallel training network is constructed using signal maps and 2D-CNN to achieve fault classification. Then, guided by the training results, eight parallel classification results are compared, so as to train the best fault diagnosis model. Finally, the simulation experiment based on a bearing data set illustrates the proposed multi-stage selection filter is effective and feasible in application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments

arXiv

引用

arXiv 2023年

作者： Chen, Yifei Peng, Kunyu Roitberg, Alina Schneider, David Zhang, Jiaming Zheng, Junwei Chen, Yufan Liu, Ruiping 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

To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions—a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods. In this work, we propose IosPSTL, a simple and effective self-supervised learning framework designed to handle occlusions. IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy. First, we pre-train the model on occluded skeleton sequences. Then, we introduce a cluster-agnostic KNN imputer that performs semantic grouping using k-means clustering on sequence embeddings. It imputes missing skeleton data by applying K-Nearest Neighbors in the latent space, leveraging nearby sample representations to restore occluded joints. This imputation generates more complete skeleton sequences, which significantly benefits downstream self-supervised models. To further enhance learning, the OPSTL module incorporates Adaptive Spatial Masking (ASM) to make better use of intact, high-quality skeleton sequences during training. Our method achieves state-of-the-art performance on the occluded versions of the NTU-60 and NTU-120 datasets, demonstrating its robustness and effectiveness under challenging conditions. Code is available at https://***/cyfml/OPSTL. Copyright © 2023, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Modality Unified Attack for Omni-Modality Person Re-Identification

arXiv

引用

arXiv 2025年

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan the College of Electrical and Information Engineering Hu nan University National Engineering Research Center of Robot Vi sual Perception and Control Technology Hunan Changsha China the College of Information Science and Engineering Hunan Normal University Hunan Provincial Key Laboratory of Intel ligent Computing and Language Information Processing Hunan Changsha China

Deep learning based person re-identification (reid) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality reid models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omni-modality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

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：