检索结果-内蒙古大学图书馆

21st International Symposium on Applied Reconfigurable Computing, ARC 2025

作者： Danilowicz, Michal Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031879944

Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and real-time embedded platforms is highly desirable. Modern MOT algorithms should be able to track objects of a given class (e.g. people or vehicles). In addition, the number of objects to be tracked is not known in advance, and they may appear and disappear at any time, as well as be obscured. For these reasons, the most popular and successful approaches have recently been based on the tracking paradigm. Therefore, the presence of a high quality object detector is essential, which in practice accounts for the vast majority of the computational and memory complexity of the whole MOT system. In this paper, we propose an FPGA (Field-Programmable Gate Array) implementation of an embedded MOT system based on a quantized YOLOv8 detector and the SORT (Simple Online Realtime Tracker) tracker. We use a modified version of the FINN framework to utilize external memory for model parameters and to support operations necessary required by YOLOv8. We discuss the evaluation of detection and tracking performance using the COCO and MOT15 datasets, where we achieve 0.21 mAP and 38.9 MOTA respectively. As the computational platform, we use an MPSoC system (Zynq UltraScale+ device from AMD/Xilinx) where the detector is deployed in reprogrammable logic and the tracking algorithm is implemented in the processor system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Long-Range Vehicle Detection of LiDAR using Adaboost Classification

Long-Range Vehicle Detection of LiDAR using Adaboost Classif...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Lim, Na-Young Lee, Jeon-Hyeok Park, Tae-Hyoung Chungbuk National University Department of Intelligent Systems & Robotics Cheongju Korea Republic of Chungbuk National University Department of Control & Robot Engineering Cheongju Korea Republic of

ISBN: (纸本)9798331531614

In recent developments, autonomous racing has garnered attention as it aims to overcome the limitations of standard autonomous driving systems. Achieving safe racing conditions necessitates both fast and long-range perception. However, current 3D LiDAR object detection methods face challenges with high computational costs and limited detection ranges. These issues make them unsuitable for racing scenarios. To address these challenges, this paper proposes a clustering-based long-range vehicle detection method that relies solely on LiDAR. First, the method removes ground points and foreground points and clusters the remaining points. Subsequently, these clusters are classified as vehicles using AdaBoost, generating 2D bounding boxes in the range view. Experimental results demonstrate superior performance, achieving a computational efficiency of 53 Hz and a long-range detection accuracy of over 80%, compared to voxel-based and range-based methods. This approach offers a viable solution for autonomous racing environments. © 2025 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

LiFT: Lightweight, FPGA-Tailored 3D Object Detection Based on LiDAR Data 18th

LiFT: Lightweight, FPGA-Tailored 3D Object Detection Based o...

引用

18th International Workshop on Design and Architecture for Signal and Image Processing, DASIP 2025

作者： Lis, Konrad Kryjak, Tomasz Gorgoń, Marek Embedded Vision Systems Group Department of Automatic Control and Robotics AGH University of Krakow Al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (纸本)9783031878961

This paper presents LiFT, a lightweight, fully quantized 3D object detection algorithm for LiDAR data, optimized for real-time inference on FPGA platforms. Through an in-depth analysis of FPGA-specific limitations, we identify a set of FPGA-induced constraints that shape the algorithm’s design. These include a computational complexity limit of 30 GMACs (billion multiply-accumulate operations), INT8 quantization for weights and activations, 2D cell-based processing instead of 3D voxels, and minimal use of skip connections. To meet these constraints while maximizing performance, LiFT combines novel mechanisms with state-of-the-art techniques such as reparameterizable convolutions and fully sparse architecture. Key innovations include the Dual-bound Pillar Feature Net, which boosts performance without increasing complexity, and an efficient scheme for INT8 quantization of input features. With a computational cost of just 20.73 GMACs, LiFT stands out as one of the few algorithms targeting minimal-complexity 3D object detection. Among comparable methods, LiFT ranks first, achieving an mAP of 51.84% and an NDS of 61.01% on the challenging NuScenes validation dataset. The code will be available at https://***/vision-agh/lift. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： 3d object detection FPGA LiDAR NuScenes quantisation

来源：评论

学校读者我要写书评

暂无评论

Development of a Model for Texture Analysis of Machined Parts on CNC Machines

Development of a Model for Texture Analysis of Machined Part...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Ilya Kovalev David Malykh Alexander Kiselev department of Computer Control Systems MSUT “STANKIN” Moscow Russia department of Robotics and Mechatronics MSUT “STANKIN” Moscow Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

This work is devoted to the development of a software module for analyzing the textures of machined parts on CNC machines using computer vision methods. The main goal of the research is to create a tool capable of analyzing geometric parameters of products based on texture properties of materials, which is especially relevant in the conditions of high-volume production. The paper considers modern methods of texture analysis, as well as their robustness to various disturbances such as illumination changes, noise, blurring, rotation and image scaling. An analysis system that combines binocular and texture methods of image processing is proposed, which makes it possible to improve the accuracy of measuring distances to objects on the basis of binocular algorithm, by means of additional analysis of texture properties of surfaces of the processed part.

关键词： Computer vision Image analysis Software algorithms Noise User interfaces Software Robustness Classification algorithms Surface texture Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Cascade LTI System for Acoustic Emission Digital Signal Processing: Result Visualization via Scalogram for Defect Pattern Representation

Cascade LTI System for Acoustic Emission Digital Signal Proc...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Yeldos A. Altay Alexey V. Fedorov Department of Robotics and Technical Means of Automation Satbayev University Almaty Kazakhstan Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russian Federation

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

Modern acoustic emission (AE) diagnostic systems are sensitive instruments for detecting developing defects. A significant limitation of the AE method is the difficulty of isolating signals against the background of interference, which significantly reduces the signal-to-interference ratio. Therefore, in this article a cascade filtering scheme for visualizing acoustic signatures through a scalogram is proposed to isolate AE signals that characterize the process of defect formation. Acoustic portraits of the isolated signals characterizing the process of defect formation are given. It is shown that the amplitude of the AE signal from a defective structure during crack formation is characterized by the highest values of the signal amplitude and has a rich frequency-time structure, the signal shape of which is determined by discrete AE.

关键词： Linear systems Visualization Time-frequency analysis Filtering Shape Instruments Interference Digital signal processing Acoustic emission Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Deterministic Learning-Based Tracking control for Parabolic PDE systems With Infinite-Dimensional Nonlinear Uncertain Dynamics

引用

IEEE Transactions on Automatic control 2025年第5期70卷 3272-3287页

作者： Zhang, Jingting Yuan, Chengzhi Wu, Fen Wang, Cong Cheng, Hong University of Electronic Science and Technology of China Center for Robotics School of Automation Engineering Chengdu611731 China University of Rhode Island Mechanical Industrial and Systems Engineering Department KingstonRI02881 United States North Carolina State University Mechanical and Aerospace Engineering Department RaleighNC27695 United States Shandong University School of Control Science and Engineering Jinan250061 China

In this article, we investigate the joint problem of dynamics learning and tracking control for a class of parabolic partial differential equation (PDE) systems with infinite-dimensional uncertain nonlinear dynamics. A new learning control scheme is proposed based on the deterministic learning (DL) theory. One key feature of the proposed scheme is its capability of accurately learning the system's nonlinear uncertain dynamics during real-time tracking control with provable stability and convergence of the overall PDE closed-loop system. Specifically, the Galerkin method is first employed to deal with the infinite dimensionality of the PDE system;a novel DL-based adaptive learning control scheme is then proposed using dual radial basis function neural networks (RBF NNs), in which a pair of RBF NNs are employed to address, respectively, the matched and unmatched components of uncertain nonlinear system dynamics. This control scheme is finally examined on the original PDE system, and it is rigorously proved that: first the PDE system's state tracks the prescribed reference trajectory with guaranteed closed-loop stability and tracking accuracy;and second locally accurate identification of the PDE system's dominant nonlinear uncertain dynamics can be achieved with provable convergence of associated NN weights to their optimal values, thereby the learned knowledge can be ultimately stored and represented by the convergent constant RBF NN models. Based on this, an experience-based control scheme is further proposed, which is capable of recalling the associated learned knowledge in real-time to further improve control performance and reduce computational complexity with maintained provable stabilization. It is worth stressing that although this work is focused particularly on parabolic PDE systems, it is groundbreaking with important technical breakthroughs that would facilitate a more complete extension of the DL theory from traditional ordinary differential equation syste

关键词： Galerkin methods

来源：评论

学校读者我要写书评

暂无评论

Improving Collision-Free Success Rate For Object Goal Visual Navigation Via Two-Stage Training With Collision Prediction

arXiv

引用

arXiv 2025年

作者： Lian, Shiwei Zhang, Feitian Robotics and Control Laboratory Department of Advanced Manufacturing and Robotics College of Engineering State Key Laboratory of Turbulence and Complex Systems Peking University Beijing100871 China

The object goal visual navigation is the task of navigating to a specific target object using egocentric visual observations. Recent end-to-end navigation models based on deep reinforcement learning have achieved remarkable performance in finding and reaching target objects. However, the collision problem of these models during navigation remains unresolved, since the collision is typically neglected when evaluating the success. Although incorporating a negative reward for collision during training appears straightforward, it results in a more conservative policy, thereby limiting the agent’s ability to reach targets. In addition, many of these models utilize only RGB observations, further increasing the difficulty of collision avoidance without depth information. To address these limitations, a new concept—collision-free success is introduced to evaluate the ability of navigation models to find a collision-free path towards the target object. A two-stage training method with collision prediction is proposed to improve the collision-free success rate of the existing navigation models using RGB observations. In the first training stage, the collision prediction module supervises the agent’s collision states during exploration to learn to predict the possible collision. In the second stage, leveraging the trained collision prediction, the agent learns to navigate to the target without collision. The experimental results in the AI2-THOR environment demonstrate that the proposed method greatly improves the collision-free success rate of different navigation models and outperforms other comparable collision-avoidance methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multi-Object Tracking using YOLOv8 and SORT on a SoC FPGA

arXiv

引用

arXiv 2025年

作者： Danilowicz, Michal Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Krakow Poland

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Long-Range Vehicle Detection of LiDAR using Adaboost Classification*

Long-Range Vehicle Detection of LiDAR using Adaboost Classif...

引用

IEEE/SICE International Symposium on System Integration

作者： Na-Young Lim Jeon-Hyeok Lee Tae-Hyoung Park Department of Intelligent Systems & Robotics Chungbuk National University Cheongju South Korea Department of Control & Robot Engineering Chungbuk National University Cheongju South Korea

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

关键词： Laser radar Three-dimensional displays Accuracy Vehicle detection System integration Object detection Computational efficiency Faces Standards Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Embedded Hierarchical MPC for Autonomous Navigation

引用

IEEE Transactions on robotics 2025年

作者： Benders, Dennis Kohler, Johannes Niesten, Thijs Babuska, Robert Alonso-Mora, Javier Ferranti, Laura Delft University of Technology department of Cognitive Robotics CD Delft2628 Netherlands ETH Zürich Institute for Dynamic Systems and Control CH 8092 Switzerland Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Republic

To efficiently deploy robotic systems in society, mobile robots must move autonomously and safely through complex environments. Nonlinear model predictive control (MPC) methods provide a natural way to find a dynamically feasible trajectory through the environment without colliding with nearby obstacles. However, the limited computation power available on typical embedded robotic systems, such as quadrotors, poses a challenge to running MPC in real time, including its most expensive tasks: constraints generation and optimization. To address this problem, we propose a novel hierarchical MPC scheme that consists of a planning and a tracking layer. The planner constructs a trajectory with a long prediction horizon at a slow rate, while the tracker ensures trajectory tracking at a relatively fast rate. We prove that the proposed framework avoids collisions and is recursively feasible. Furthermore, we demonstrate its effectiveness in simulations and lab experiments with a quadrotor that needs to reach a goal position in a complex static environment. The code is efficiently implemented on the quadrotor's embedded computer to ensure real-time feasibility. Compared to a state-of-the-art single-layer MPC formulation, this allows us to increase the planning horizon by a factor of 5, which results in significantly better performance. © 2004-2012 IEEE.

关键词： Mobile robots

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：