检索结果-内蒙古大学图书馆

Efficient Semantic Splatting for Remote Sensing Multiview Segmentation

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Qi, Zipeng Chen, Hao Zhang, Haotian Zou, Zhengxia Shi, Zhenwei Beihang University School of Astronautics State Key Laboratory of Virtual Reality Technology and Systems Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies Ministry of Education Department of Aerospace Intelligent Science and Technology Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China

Remote sensing multiview image segmentation is essential for achieving accurate and consistent stereoscopic perception of target scenes. This task involves processing RGB images from multiple viewpoints to generate high-accuracy, view-consistent semantic segmentation across all views. Traditional training-based methods struggle with maintaining cross-view consistency, while optimization-driven approaches using implicit neural networks improve view consistency but suffer from slow parameter optimization and inference. To overcome these limitations, we propose a novel Gaussian splatting-based semantic segmentation framework. Our method efficiently projects the color attributes and semantic features of 3-D Gaussians onto the image plane, enabling the simultaneous generation of both RGB images and segmentation outputs. By leveraging explicit spatial structures and a splatting rendering strategy, our approach significantly enhances optimization efficiency and rendering speed. In addition, we incorporate SAM2 to generate pseudo-labels for boundary regions, addressing the lack of supervision in sparsely labeled views (e.g., 3%). To further enforce cross-view consistency and feature coherence of 3-D Gaussians, we introduce a two-level aggregation loss that operates at both the 2-D feature map and 3-D spatial levels. Extensive experiments across nine datasets demonstrate the superiority of our method, achieving competitive segmentation quality with limited supervisory views. Notably, our approach reduces rendering (inference) times by 90%, while improving the average mean intersection over union (mIoU) by up to 3.5%. © 1980-2012 IEEE.

关键词： Semantic Segmentation

A Smooth Distributed Formation Control Method for Quadrotor UAVs under Event-Triggering Mechanism and Switching Topologies

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular technology 2025年

作者： Huang, Yi Xu, Xiangfan Meng, Ziyang Sun, Jian Beijing Institute of Technology State Key Laboratory of Autonomous Intelligent Unmanned Systems School of Automation Beijing100081 China Tsinghua University Department of Precision Instrument Beijing100084 China

This paper focuses on the formation control problem of a team of quadrotor unmanned aerial vehicles (UAVs) subject to switching directed topologies. We present a distributed event-triggered formation control algorithm via hierarchical framework, which achieves the formation control objective with weak assumptions on switching topologies. In particular, we develop a distributed control force that enables the achievement of the target formation, which only relies on the neighbors' position information under event-triggering mechanism. The proposed algorithm can maintain smooth characteristics when confronted with discontinuities stemming from event-triggering mechanism and switching interactions among agents. Additionally, the boundedness of the command control force can be guaranteed by employing an auxiliary system. Subsequently, we develop an attitude tracking control algorithm to guarantee that the attitude error almost globally exponentially converges to zero. Finally, a numerical example is carried out to validate the theoretical results. © 2025 IEEE.

关键词： Topology

SLC2-SLAM: Semantic-guided Loop Closure using Shared Latent Code for NeRF SLAM

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ming, Yuhang Ma, Di Dai, Weichen Yang, Han Fan, Rui Zhang, Guofeng Kong, Wanzeng School of Computer Science Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province Hangzhou Dianzi University Hangzhou310018 China College of Electronics & Information Engineering Shanghai Institute of Intelligent Science and Technology Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China State Key Lab of CAD&CG Zhejiang University Hangzhou310058 China

Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC2-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not fully exploited, as they are only used for better reconstruction. In this paper, we propose a simple yet effective way to detect potential loops using the same latent codes as local features. To further improve the loop detection performance, we use the semantic information, which are also decoded from the same latent codes to guide the aggregation of local features. Finally, with the potential loops detected, we close them with a graph optimization followed by bundle adjustment to refine both the estimated poses and the reconstructed scene. To evaluate the performance of our SLC2-SLAM, we conduct extensive experiments on Replica and ScanNet datasets. Our proposed semantic-guided loop closure significantly outperforms the pre-trained NetVLAD and ORB combined with Bag-of-Words, which are used in all the other NeRF SLAM with loop closure. As a result, our SLC2-SLAM also demonstrated better tracking and reconstruction performance, especially in larger scenes with more loops, like ScanNet. Copyright © 2025, The Authors. All rights reserved.

关键词： SLAM robotics

Heterogeneous Mixture of Experts for Remote Sensing Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Bowen Chen, keyan Yang, Mohan Zou, Zhengxia Shi, Zhenwei Department of Aerospace Intelligent Science and Technology School of Astronautics Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Remote sensing image super-resolution (SR) aims to reconstruct high-resolution remote sensing images from low-resolution inputs, thereby addressing limitations imposed by sensors and imaging conditions. However, the inherent characteristics of remote sensing images, including diverse ground object types and complex details, pose significant challenges to achieving high-quality reconstruction. Existing methods typically employ a uniform structure to process various types of ground objects without distinction, making it difficult to adapt to the complex characteristics of remote sensing images. To address this issue, we introduce a Mixture of Experts (MoE) model and design a set of heterogeneous experts. These experts are organized into multiple expert groups, where experts within each group are homogeneous while being heterogeneous across groups. This design ensures that specialized activation parameters can be employed to handle the diverse and intricate details of ground objects effectively. To better accommodate the heterogeneous experts, we propose a multi-level feature aggregation strategy to guide the routing process. Additionally, we develop a dual-routing mechanism to adaptively select the optimal expert for each pixel. Experiments conducted on the UCMerced and AID datasets demonstrate that our proposed method achieves superior SR reconstruction accuracy compared to state-of-the-art methods. The code will be available at https://***/Mr-Bamboo/MFG-HMoE. Copyright © 2025, The Authors. All rights reserved.

关键词： Reconstruction (structural)

GaitFormer: Two-Stream Transformer Gait Recognition Using Wearable IMU Sensors in the Context of Industry 5.0

学校读者我要写书评

暂无评论

IEEE Sensors Journal 2025年

作者： Lu, Zhangli Zhou, Huiying Wang, Longqiang Kong, Depeng Lyu, Honghao Wu, Haiteng Chen, Bing Chen, Fuguo Dong, Na Yang, Geng Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Hangzhou310058 China Innovation Institute Co. Ltd China Hangzhou Shenhao Technology Key Laboratory of Intelligent Robot for Operation and Maintenance of Zhejiang province Hangzhou China

The rising attention to human-centricity, a core value of Industry 5.0, makes researchers propose various methods to place humans in the center of production, such as the Human Digital Twin (HDT) and gait identity recognition. However, previous HDT applications in the Industry 5.0 era have less consideration of identity recognition, the vital way to link physical signals to personal archives in cyber systems. Herein GaitFormer, a Two-Stream Transformer gait recognition method is proposed for application with the wearable inertial measurement unit (IMU) motion capture system. GaitFormer consists of Temporal and Channel Modules enclosing Gaussian Range Encoding, multi-head Auto-Correlation mechanism, and multi-scale as convolutional neural network (CNN) layers. It outperforms state-of-the-art architectures with extensive experiments over publicly available IMU-based datasets respectively: whuGait and OU-ISIR. Then the study intends to combine the motion capture system and gait identity recognition algorithm to propose an application of personal monitoring in the Human-Cyber-Physical-System (HCPS), which uses GaitFormer to recognize the identity of the user with motion capture system and show their corresponding customized HDT. This work may contribute to making a connection between gait identity recognition and HDT, constructing personal working profiles in the environment of Industry 5.0. © 2001-2012 IEEE.

关键词： Convolutional neural networks

Moving Target Defense Meets Artificial Intelligence-Driven Network: A Comprehensive Survey

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年第10期12卷 13384-13397页

作者： Zhang, Tao Kong, Fanyu Deng, Dongshang Tang, Xiangyun Wu, Xuangou Xu, Changqiao Zhu, Liehuang Liu, Jiqiang Ai, Bo Han, Zhu Deng, Robert H. Beijing Jiaotong University School of Cyberspace Science and Technology Beijing100044 China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui243002 China Minzu University of China School of Information Engineering Beijing100081 China Chongqing University College of Computer Science Chongqing400044 China Anhui University of Technology School of Computer Science and Technology Anhui Province Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui243002 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Beijing Jiaotong University School of Electronic and Information Engineering Frontiers Science Center for Smart High-speed Railway System Beijing100044 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Singapore Management University Department of Information Systems Singapore Singapore

Based on emerging Artificial Intelligence (AI) tasks, cloud-edge-terminal architecture can provide powerful computing, intelligent interconnection, and real-time response, which can also be regarded as AI-driven network. Unfortunately, multiple network layers in the AI-driven network usually face various types of network threats such as malicious network reconnaissance, side-channel attacks, and Distributed Denial of Service (DDoS). Traditional security solutions respond to network threats after the occurrence of attacks. To solve this problem, the concept of Moving Target Defense (MTD) has been proposed as a proactive defense mechanism that aims to defend against cyber attacks before they occur. In this paper, we firstly provide a thorough analysis of the threats in the cloud-edge-terminal network. Then we conduct a comprehensive survey to discuss the concept, design principles, and main classifications of MTD. Next, we further introduce the development potential in terms of AI-powered MTD on each network layer. Meanwhile, we also explore how MTD improves the security of AI algorithms. Lastly, we describe the existing challenges and research directions of MTD. The aim of this paper is to provide an in-depth understanding for the readers on how to realize the integration between MTD and AI-driven network. © 2014 IEEE.

关键词： Cloud security

II-NVM: Enhancing Map Accuracy and Consistency With Normal Vector-Assisted Mapping

学校读者我要写书评

暂无评论

IEEE Robotics and Automation Letters 2025年第6期10卷 5465-5472页

作者： Zhao, Chengwei Li, Yixuan Jian, Yina Xu, Jie Wang, Linji Ma, Yongxin Jin, Xinglai Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Hangzhou Qisheng Intelligent Techology Company Ltd Hangzhou311217 China Columbia University in the City of New York Department of Computer Science New YorkNY10027 United States Harbin Institute of Technology State Key Laboratory of Robotics and Systems Harbin150001 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore

SLAM technology plays a crucial role in indoor mapping and localization. A common challenge in indoor environments is the "double-sided mapping issue", where closely positioned walls, doors, and other surfaces are mistakenly identified as a single plane, significantly hindering map accuracy and consistency. To addressing this issue this letter introduces a SLAM approach that ensures accurate mapping using normal vector consistency. We enhance the voxel map structure to store both point cloud data and normal vector information, enabling the system to evaluate consistency during nearest neighbor searches and map updates. This process distinguishes between the front and back sides of surfaces, preventing incorrect point-to-plane constraints. Moreover, we implement an adaptive radius KD-tree search method that dynamically adjusts the search radius based on the local density of the point cloud, thereby enhancing the accuracy of normal vector calculations. To further improve real-time performance and storage efficiency, we incorporate a Least Recently Used (LRU) cache strategy, which facilitates efficient incremental updates of the voxel map. The code is released as open-source and validated in both simulated environments and real indoor scenarios. Experimental results demonstrate that this approach effectively resolves the "double-sided mapping issue" and significantly improves mapping precision. Additionally, we have developed and open-sourced the first simulation and real-world dataset specifically tailored for the "double-sided mapping issue". © 2016 IEEE.

关键词： Mapping

CoIn-SafeLink: Safety-critical Control With Cost-sensitive Incremental Random Vector Functional Link Network

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Songqiao Liu, Zeyi He, Xiao Shen, Zhen Department of Automation Tsinghua University Beijing100084 China State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences China

Control barrier functions (CBFs) play a crucial role in achieving the safety-critical control of robotic systems theoretically. However, most existing methods rely on the analytical expressions of unsafe state regions, which is often impractical for irregular and dynamic unsafe regions. In this paper, a novel CBF construction approach, called CoIn-SafeLink, is proposed based on cost-sensitive incremental random vector functional-link (RVFL) neural networks. By designing an appropriate cost function, CoIn-SafeLink achieves differentiated sensitivities to safe and unsafe samples, effectively achieving zero false-negative risk in unsafe sample classification. Additionally, an incremental update theorem for CoIn-SafeLink is proposed, enabling precise adjustments in response to changes in the unsafe region. Finally, the gradient analytical expression of the CoIn-SafeLink is provided to calculate the control input. The proposed method is validated on a 3-degree-of-freedom drone attitude control system. Experimental results demonstrate that the method can effectively learn the unsafe region boundaries and rapidly adapt as these regions evolve, with an update speed approximately five times faster than comparison methods. The source code is available at https://***/songqiaohu/CoIn-SafeLink. Copyright © 2025, The Authors. All rights reserved.

关键词： Aircraft control

Diffusion-Based mmWave Radar Point Cloud Enhancement Driven by Range Images

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Ruixin Li, Zihan Wang, Jin Xu, Xiangyu Yu, Huan Zheng, Zhi Huang, Kaixiang Lu, Guodong The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310058 China Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Zhejiang University Hangzhou310058 China Robotics Research Center of Yuyao City Ningbo315400 China State Key Laboratory of Robotics and Systems Department of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China

Millimeter-wave (mmWave) radar has attracted significant attention in robotics and autonomous driving. However, despite the perception stability in harsh environments, the point cloud generated by mmWave radar is relatively sparse while containing significant noise, which limits its further development. Traditional mmWave radar enhancement approaches often struggle to leverage the effectiveness of diffusion models in super-resolution, largely due to the unnatural range-azimuth heatmap (RAH) or bird’s eye view (BEV) representation. To overcome this limitation, we propose a novel method that pioneers the application of fusing range images with image diffusion models, achieving accurate and dense mmWave radar point clouds that are similar to LiDAR. Benefitting from the projection that aligns with human observation, the range image representation of mmWave radar is close to natural images, allowing the knowledge from pre-trained image diffusion models to be effectively transferred, significantly improving the overall performance. Extensive evaluations on both public datasets and self-constructed datasets demonstrate that our approach provides substantial improvements, establishing a new state-of-the-art performance in generating truly three-dimensional LiDAR-like point clouds via mmWave radar. Copyright © 2025, The Authors. All rights reserved.

关键词： Radar imaging