检索结果-内蒙古大学图书馆

RED-SLAM: real-time and effective RGB-D SLAM with spatial-geometric observations and fast semantic perception for dynamic environments

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第3期36卷 036303-036303页

作者： Liu, Hailin Tian, Lianfang Du, Qiliang Duan, Ruxiang South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China Guangdong Engn Res Ctr Cloud Edge End Collaborat T Guangzhou 510640 Peoples R China Key Lab Large Model Embodied Intelligent Humanoid Guangzhou 510640 Peoples R China

Most visual simultaneous localization and mapping (vSLAM) methods assume a static scene, limiting their effectiveness in complex, real-world dynamic environments. This paper presents RED-SLAM-a real-time dynamic visual SLAM method based on the ORB-SLAM3 framework for RGB-D sensors, designed to effectively address the impact of dynamic objects. RED-SLAM leverages spatial-geometric observations combined with semantic cues to identify dynamic points within the field of view, thereby utilizing only static points for state estimation. In the geometric verification module, the initial distinction between static and dynamic points is achieved by checking the spatial projection ray distance error based on the matching between map points and feature points. To conserve computational resources, semantic segmentation is performed exclusively on designated semantic frames, which are constructed based on the changes of dynamic objects. The detected dynamic semantic objects are subsequently spread to successive frames using a semantic propagation technique. All map points associated with dynamic semantic objects are excluded to further enhance the identification accuracy of dynamic map point. Compared to existing methods that apply semantic segmentation across all frames or keyframes, RED-SLAM only performs segmentation when dynamic objects change, improving system's performance and efficiency. Experimental results on public datasets and real-world scenes demonstrate that our method enhances pose estimation accuracy in dynamic environments, achieving competitive accuracy compared to state-of-the-art methods, while maintaining reliable real-time performance.

关键词： visual SLAM RGB-D sensor semantic propagation spatial observations dynamic environments

来源：评论

学校读者我要写书评

暂无评论

Image debanding using cross-scale invertible networks with banded deformable convolutions

引用

NEURAL NETWORKS 2025年 187卷 107270页

作者： Quan, Yuhui He, Xuyi Xu, Ruotao Xu, Yong Ji, Hui South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China South China Univ Technol Inst Super Robot Guangzhou Peoples R China Key Lab Large Model Embodied Intelligent Humanoid Guangzhou Peoples R China Peng Cheng Lab Shenzhen Peoples R China Guangdong Prov Key Lab Multimodal Big Data Intelli Guangzhou Peoples R China Natl Univ Singapore Dept Math Singapore Singapore

Banding artifacts in images stem from limitations in color bit depth, image compression, or over-editing, significantly degrades image quality, especially in regions with smooth gradients. Image debanding is about eliminating these artifacts while preserving the authenticity of image details. This paper introduces a novel approach to image debanding using a cross-scale invertible neural network (INN). The proposed INN is information-lossless and enhanced by amore effective cross-scale scheme. Additionally, we present a technique called banded deformable convolution, which fully leverages the anisotropic properties of banding artifacts. This technique is more compact, efficient, and exhibits better generalization compared to existing deformable convolution methods. Our proposed INN exhibits superior performance in both quantitative metrics and visual quality, as evidenced by the results of the experiments.

关键词： Image debanding Invertible networks Banded deformable convolution

来源：评论

学校读者我要写书评

暂无评论

Double center swarm exploring varying parameter neurodynamic network for non-convex nonlinear programming

引用

NEUROCOMPUTING 2025年 619卷

作者： Zhang, Zhijun Zhu, Minghao Ren, Xiaohui South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China South China Univ Technol Key Lab Large Model Embodied Intelligent Humanoid Guangzhou 510640 Peoples R China Guangdong Artificial Intelligence & Digital Econ L Pazhou Lab Guangzhou 510335 Peoples R China Shaanxi Univ Technol Sch Mech Engn Hanzhong 723001 Peoples R China Changsha Normal Univ Sch Informat Sci & Engn Changsha 410100 Peoples R China Guangdong Univ Petrochem Technol Sch Automat Sci & Engn Maoming 525000 Peoples R China Jishou Univ Coll Comp Sci & Engn Jishou 416000 Peoples R China

To solve non-convex nonlinear programming problems, a double center swarm exploring varying parameter neurodynamic network (DCSE-VPNN) is proposed and analyzed. Firstly, a varying parameter neurodynamic network is proposed as a solver for nonlinear programming to seek local optimal solutions. Secondly, a double center particle swarm optimization algorithm is exploited, wherein each neural network serves as a particle. Each particle independently explores a local optimal solution. Through information exchange among particles, the subsequent positions to be explored are updated. Asa result, DCSE-VPNN acquires the capability of global search. Computer simulation experiments verify the efficacy of the proposed approach in solving non-convex nonlinear programming problems. In comparison with two existing methods, the results show that the proposed DCSE-VPNN approach has fewer iterations and higher search accuracy.

关键词： Varying parameter neurodynamic network Particle swarm optimization (PSO) Non-convex nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

An adaptive variable-parameter dynamic learning network for solving constrained time-varying QP problem

引用

NEURAL NETWORKS 2025年 184卷 106968页

作者： Zhang, Zhijun Sun, Xiangliang Li, Xingru Liu, Yiqi South China Univ Technol Sch Automat Sci & Engn Guangzhou Peoples R China Minist Educ Key Lib Autonomous Syst & Network Control Guangzhou Peoples R China Nanchang Univ Jiangxi Thousand Talents Plan Nanchang Peoples R China Jishou Univ Coll Comp Sci & Engn Jishou Peoples R China Guangdong Artificial Intelligence & Digital Econ Pazhou Lab Guangzhou Peoples R China Shaanxi Univ Technol Sch Mech Engn Shaanxi Prov Key Lab Ind Automat Hanzhong Peoples R China Changsha Normal Univ Sch Informat Sci & Engn Changsha Peoples R China Guangdong Univ Petrochem Technol Sch Automat Sci & Engn Maoming Peoples R China Guangdong Univ Petrochem Technol Inst Artificial Intelligence & Automat Maoming Peoples R China Key Lab Large Model Embodied Intelligent Humanoid Beijing Peoples R China

To efficiently solve the time-varying convex quadratic programming (TVCQP) problem under equational constraint, an adaptive variable-parameter dynamic learning network (AVDLN) is proposed and analyzed. Being different from existing varying-parameter and fixed-parameter convergent-differential neural network (VPCDNN and FPCDNN), the proposed AVDLN integrates the error signals into the time-varying parameter term. To do so, the TVCQP problem is transformed into a time-varying matrix equation. Second, an adaptive time-varying design formulation is designed for the error function, and then, the error function is integrated into the time-varying parameter. Furthermore, the AVDLN is designed with the adaptive time-varying design formulation. Moreover, the convergence and robustness theorems of AVDLN are proved by Lyapunov stability analysis, and Mathematical analysis demonstrates that AVDLN possesses a smaller upper bound on the convergence error and a faster error convergence rate than FPCDNN and VPCDNN. Finally, the validity of AVDLN is demonstrated by simulations, and the comparative results prove that the proposed AVDLN has a faster convergence speed and smaller error fluctuation.

关键词： Quadratic programming Adaptive control Time-varying systems Optimization algorithms Neural network

来源：评论

学校读者我要写书评

暂无评论

VPT: Video portraits transformer for realistic talking face generation

引用

NEURAL NETWORKS 2025年 184卷 107122页

作者： Zhang, Zhijun Zhang, Jian Mai, Weijian South China Univ Technol Sch Automat Sci & Engn Guangzhou Peoples R China Minist Educ Key Lib Autonomous Syst & Network Control Beijing Peoples R China Nanchang Univ Jiangxi Thousand Talents Plan Nanchang Jiangxi Peoples R China Jishou Univ Coll Comp Sci & Engn Jishou Peoples R China Pazhou Lab Guangdong Artificial Intelligence & Digital Econ Guangzhou Peoples R China Shaanxi Univ Technol Sch Mech Engn Shaanxi Prov Key Lab Ind Automat Hanzhong Peoples R China Changsha Normal Univ Sch Informat Sci & Engn Changsha Peoples R China Guangdong Univ Petrochem Technol Sch Automat Sci & Engn Maoming Peoples R China Guangdong Univ Petrochem Technol Inst Artificial Intelligence & Automat Maoming Peoples R China Key Lab Large Model Embodied Intelligent Humanoid Guangzhou Peoples R China Inst Super Robot Huangpu Guangzhou Peoples R China

Talking face generation is a promising approach within various domains, such as digital assistants, video editing, and virtual video conferences. Previous works with audio-driven talking faces focused primarily on the synchronization between audio and video. However, existing methods still have certain limitations in synthesizing photo-realistic video with high identity preservation, audiovisual synchronization, and facial details like blink movements. To solve these problems, a novel talking face generation framework, termed video portraits transformer (VPT) with controllable blink movements is proposed and applied. It separates the process of video generation into two stages, i.e., audio-to-landmark and landmark-to-face stages. In the audio- to-landmark stage, the transformer encoder serves as the generator used for predicting whole facial landmarks from given audio and continuous eye aspect ratio (EAR). During the landmark-to-face stage, the video-to-video (vid-to-vid) network is employed to transfer landmarks into realistic talking face videos. Moreover, to imitate real blink movements during inference, a transformer-based spontaneous blink generation module is devised to generate the EAR sequence. Extensive experiments demonstrate that the VPT method can produce photo- realistic videos of talking faces with natural blink movements, and the spontaneous blink generation module can generate blink movements close to the real blink duration distribution and frequency.

关键词： Talking face generation Transformer Blink movement generation

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Navigation Using ORB-SLAM3: A Multi-Modal Autonomous System

Mobile Robot Navigation Using ORB-SLAM3: A Multi-Modal Auton...

引用

Electrical Automation and Artificial Intelligence (ICEAAI), International Conference on

作者： Ariano Da Conceicao Lianfang Tian Qiliang Du Ling Yuan School of Automation Science and Engineering South China University of Technology Guangzhou China Research Institute of Modern Industrial Innovation South China University of Technology Guangzhou China Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China Key Laboratory of Autonomous Systems and Network Control of Ministry of Education Guangzhou China Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China Sino-Singapore International Joint Research Institute Guangzhou China

ISBN: (数字)9798331506797

ISBN: (纸本)9798331506803

Indoor mobile robots require reliable solutions for mapping, localization, and navigation tasks. This paper presents a mobile robot system that implements the ability to realize mapping using visual SLAM with ORB-SLAM3 and LiDAR-based mapping with Gmapping for indoor perception and navigation through a modular ROS architecture. The framework also implements autonomous navigation and an autonomous Rapidly-exploring Random Trees (RRT) exploration module with adaptive reset mechanisms. The system operates on a ROS-based platform equipped with an Intel RealSense D435i RGB-D camera and LDS-02 LiDAR scanner. Experimental validation in simulated indoor environments demonstrates the system's capabilities and the presented architecture achieves computational efficiency through selective utilization of mapping modules while maintaining mapping accuracy through complementary sensor modalities.

关键词： Visualization Simultaneous localization and mapping Accuracy Laser radar Navigation Service robots Heuristic algorithms Computer architecture Mobile robots Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Convolution for 3D Semantic Segmentation

Multi-Resolution Convolution for 3D Semantic Segmentation

引用

2024 International Conference on intelligent Robotics and Automatic Control

作者： Li, Qihui Tian, Lianfang Du, Qiliang Xie, Yuhang South China Univ Technol Sch Automat Sci & Engn Guangzhou Peoples R China Guangdong Engn Res Ctr Cloud Edge End Collaborat Guangzhou Peoples R China Key Lab Large Model Embodied Intelligent Humanoid Guangzhou Peoples R China

ISBN: (纸本)9798350389814;9798350389807

Effective capture of multi-scale features is crucial for improving performance in 3D point cloud semantic segmentation tasks. This paper introduces a novel framework that enhances the extraction of semantic information from complex objects in 3D point clouds using multi-resolution techniques. By utilizing varying voxel resolutions and convolutional kernel sizes, we integrate high-resolution voxels to capture fine details and low-resolution voxels to extract global features, achieving robust feature fusion. Experimental results demonstrate the effectiveness of our proposed network validated on the ScanNet v2 dataset, particularly excelling in the semantic segmentation task for small objects and complex scenes. This study highlights the significance of multi-resolution strategies in 3D scene understanding, providing new insights for future research in the field.

关键词： 3D Point Cloud Semantic Segmentation Muti-Resolution

来源：评论

学校读者我要写书评

暂无评论

Tightly-coupled Lidar-Visual-Inertial SLAM for Mobile Robot

Tightly-coupled Lidar-Visual-Inertial SLAM for Mobile Robot

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Qiliang Du Bojie Chen Lianfang Tian Ling Yuan School of Automation Science and Engineering South China University of Technology Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China School of Automation Science and Engineering South China University of Technology Guangzhou China Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

Simultaneous Localization and Mapping (SLAM) enables robots to perform localization and mapping in unknown environments. Currently, mainstream single-sensor Lidar SLAM (Visual SLAM) tends to diverge and fail when faced with unstructured or textureless scenes. To address this issue, this paper proposes a robust tightly-coupled Lidar-Vision-Inertial Odometry framework (LRI-LVIO) that achieves high-precision and robust SLAM. LRI-LVIO consists of two subsystems: a visual-inertial system and a lidar-inertial system. These two subsystems are tightly coupled through an error-state iterative Kalman filter, allowing one subsystem to maintain stable operation even if the other fails, thus enhancing the robustness of SLAM in textureless and featureless environments. Additionally, the depth of visual feature points is recovered using lidar point cloud information, improving the algorithm's efficiency and accuracy. Finally, LRI-LVIO incorporates loop closure detection based on lidar point cloud keyframes, further reducing cumulative errors and enhancing localization precision. Experiments conducted in various indoor and outdoor environments show that by combining the advantages of each sensor, LRI-LVIO achieves higher accuracy and stronger robustness compared to single-sensor SLAM.

关键词： Point cloud compression Location awareness Visualization Simultaneous localization and mapping Laser radar Accuracy Machine learning algorithms Robustness Odometry Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Convolution for 3D Semantic Segmentation

Multi-Resolution Convolution for 3D Semantic Segmentation

引用

intelligent Robotics and Automatic Control (IRAC), International Conference on

作者： Qihui Li Lianfang Tian Qiliang Du Yuhang Xie School of Automation Science and Engineering South China University of Technology Guangzhou China School of Automation Science and Engineering South China University of Technology Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China School of Automation Science and Engineering South China University of Technology Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China

ISBN: (数字)9798350389807

ISBN: (纸本)9798350389814

关键词： Point cloud compression Solid modeling Three-dimensional displays Convolution Semantic segmentation Semantics Feature extraction Data models Kernel Robots

来源：评论

学校读者我要写书评

暂无评论

Detection of key Components of Transmission Lines Based on the Improved YOLOv8

Detection of Key Components of Transmission Lines Based on t...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Yuhang Xie Lianfang Tian Qiliang Du Ling Yuan School of Automation Science and Engineering South China University of Technology Guangzhou China School of Automation Science and Engineering South China University of Technology Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China School of Automation Science and Engineering South China University of Technology Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

The detection of key components in transmission lines faces challenges such as significant variations in object scales, complex backgrounds, and difficulties in detecting small targets, leading to low detection accuracy and missed detections. In this study, we propose an improved YOLOv8 algorithm for detecting key components of transmission lines. First, we incorporate Deformable Convolution (DCNv3) to improve the backbone network's feature extraction capability and mitigate accuracy degradation caused by occlusion and angle variations. Subsequently, we use the Adaptively Spatial Feature Fusion (ASFF) to progressively fuse features of different scales and add same-layer skip connections, enabling efficient feature fusion and strengthening the model's ability to detect small objects. Finally, we replaced the original CIoU with the RIoU to further boost the detection capability for small objects. The modified algorithm achieves an mAP 50 of 96.5%, an mAP 50:95 of 79.2%, representing a 3.1% and 4.8% improvement compared to the original YOLOv8 model.

关键词： Power transmission lines Accuracy Convolution Shape Computational modeling Feature extraction Propagation losses Neck Standards Load modeling

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：