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

High-definition event frame generation using SoC FPGA devices 26

High-definition event frame generation using SoC FPGA device...

引用

26th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2023

作者： Blachut, Krzysztof Kryjak, Tomasz AGH University of Krakow Embedded Vision Systems Group Department of Automatic Control and Robotics Krakow Poland

ISBN: (纸本)9798350304985

In this paper we have addressed the implementation of the accumulation and projection of high-resolution event data stream (HD - 1280×720 pixels) onto the image plane in FPGA devices. The results confirm the feasibility of this approach, but there are a number of challenges, limitations and trade-offs to be considered. The required hardware resources of selected data representations, such as binary frame, event frame, exponentially decaying time surface and event frequency, were compared with those available on several popular platforms from AMD Xilinx. The resulting event frames can be used for typical vision algorithms, such as object classification and detection, using both classical and deep neural network methods. © 2023 Division of Signal Processing and Electronic systems, Poznan University of Technology (DSPES PUT).

关键词： System-on-chip

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

Traffic Sign Classification Using Deep and Quantum Neural Networks

Traffic Sign Classification Using Deep and Quantum Neural Ne...

引用

International Conference on Computer Vision and Graphics, ICCVG 2022

作者： Kuros, Sylwia 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)9783031220241

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Energy Efficient Hardware Acceleration of Neural Networks wi...

引用

International Conference on Computer Vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika 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)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

IoT-based remote control for robotic arm

引用

International Journal of systems, Control and Communications 2024年第2期15卷 146-158页

作者： Do, Tri Nhut Department of Embedded Systems and Robotics Faculty of Computer Engineering University of Information Technology Viet Nam Vietnam National University Ho Chi Minh City 1 Han Thuyen Street Linh Trung Ward Thu Duc Ho Chi Minh City71308 Viet Nam

Robotic arms can perform various tasks with high accuracy, efficiency, and safety, especially in hazardous environments. This paper presents four degrees of freedom robotic arm that can be controlled remotely by two methods: direct control via Wi-Fi and indirect control via internet. We have designed an embedded system that allows the user to manipulate the robotic arm by moving the robot hand in different directions. We have also developed two software applications for remote control: one using MIT inventor 2 tool for direct control, and another using a web-based interface for indirect control. The software applications enable the user to adjust the angles of the four servo motors that drive the robotic arm in both clockwise and counter – clockwise directions. We have conducted several experiments to demonstrate the feasibility and stability of our system under different scenarios. Our results show that our system can perform wireless control of the robotic arm effectively using various mobile devices such as phone, tablet, or computer such as laptop, personal computer. © 2024 Inderscience Enterprises Ltd.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs 27

Tangled Program Graphs as an alternative to DRL-based contro...

引用

27th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2024

作者： Szolc, Hubert Desnos, Karol Kryjak, Tomasz AGH University of Krakow Embedded Vision Systems Group Department of Automatic Control and Robotics Kraków Poland Univ Rennes INSA Rennes CNRS IETR - UMR 6164 RennesF-35000 France

ISBN: (纸本)9788362065486

Deep reinforcement learning (DRL) is currently the most popular AI-based approach to autonomous vehicle control. An agent, trained for this purpose in simulation, can interact with the real environment with a human-level performance. Despite very good results in terms of selected metrics, this approach has some significant drawbacks: high computational requirements and low explainability. Because of that, a DRL-based agent cannot be used in some control tasks, especially when safety is the key issue. Therefore we propose to use Tangled Program Graphs (TPGs) as an alternative for deep reinforcement learning in control-related tasks. In this approach, input signals are processed by simple programs that are combined in a graph structure. As a result, TPGs are less computationally demanding and their actions can be explained based on the graph structure. In this paper, we present our studies on the use of TPGs as an alternative for DRL in control-related tasks. In particular, we consider the problem of navigating an unmanned aerial vehicle (UAV) through the unknown environment based solely on the onboard LiDAR sensor. The results of our work show promising prospects for the use of TPGs in control related-tasks. © 2024 Division of Signal Processing and Electronic systems, Poznan University of Technology (DSPES PUT).

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras 26

Memory-Efficient Graph Convolutional Networks for Object Cla...

引用

26th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2023

作者： Jeziorek, Kamil Pinna, Andrea Kryjak, Tomasz AGH University of Krakow Embedded Vision Systems Group Department of Automatic Control and Robotics Krakow Poland Sorbonne Universite CNRS LIP6 ParisF-75005 France

ISBN: (纸本)9798350304985

Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resistance to image blur. One promising approach for analyzing event data is through graph convolutional networks (GCNs). However, current research in this domain primarily focuses on optimizing computational costs, neglecting the associated memory costs. In this paper, we consider both factors together in order to achieve satisfying results and relatively low model complexity. For this purpose, we performed a comparative analysis of different graph convolution operations, considering factors such as execution time, the number of trainable model parameters, data format requirements, and training outcomes. Our results show a 450-fold reduction in the number of parameters for the feature extraction module and a 4.5-fold reduction in the size of the data representation while maintaining a classification accuracy of 52.3%, which is 6.3% higher compared to the operation used in state-of-the-art approaches. To further evaluate performance, we implemented the object detection architecture and evaluated its performance on the N-Caltech101 dataset. The results showed an accuracy of 53.7% mAP@0.5 and reached an execution rate of 82 graphs per second. © 2023 Division of Signal Processing and Electronic systems, Poznan University of Technology (DSPES PUT).

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

PointPillars Backbone Type Selection for Fast and Accurate L...

引用

International Conference on Computer Vision and Graphics, ICCVG 2022

作者： Lis, Konrad Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (纸本)9783031220241

3D object detection from LiDAR sensor data is an important topic in the context of autonomous cars and drones. In this paper, we present the results of experiments on the impact of backbone selection of a deep convolutional neural network on detection accuracy and computation speed. We chose the PointPillars network, which is characterised by a simple architecture, high speed, and modularity that allows for easy expansion. During the experiments, we paid particular attention to the change in detection efficiency (measured by the mAP metric) and the total number of multiply-addition operations needed to process one point cloud. We tested 10 different convolutional neural network architectures that are widely used in image-based detection problems. For a backbone like MobilenetV1, we obtained an almost 4x speedup at the cost of a 1.13% decrease in mAP. On the other hand, for CSPDarknet we got an acceleration of more than 1.5x at an increase in mAP of 0.33%. We have thus demonstrated that it is possible to significantly speed up a 3D object detector in LiDAR point clouds with a small decrease in detection efficiency. This result can be used when PointPillars or similar algorithms are implemented in embedded systems, including SoC FPGAs. The code is available at https://***/vision-agh/pointpillars-backbone. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

THE GENERALIZED MATRIX NORM PROBLEM

arXiv

引用

arXiv 2023年

作者： Kulmburg, Adrian Department of Robotics Artificial Intelligence and Embedded Systems Technical University of Munich Germany

We study the computability of the operator norm of a matrix with respect to norms induced by linear operators. Our findings reveal that this problem can be solved exactly in polynomial time in certain situations, and we discuss how it can be approximated for other cases. Along the way, we investigate the concept of push-forward and pull-back of seminorms, which leads us to uncover novel duality principles that come into play when optimizing over the unit ball of *** Codes 15A60 (Primary), 65F35, 68Q25 Copyright © 2023, The Authors. All rights reserved.

关键词： Polynomial approximation

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：