检索结果-内蒙古大学图书馆

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Moosmann, Julian Giordano, Marco Vogt, Christian Magno, Michele Center for Project Based Learning - Eth Zürich Switzerland

ISBN: (纸本)9798350332674

This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5 MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422 k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180 fps and an ultra-low energy consumption of only 196 μJ per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper. © 2023 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

LEDNet: a multimodal foundation model for robust deepfake detection

引用

Science China(Information Sciences) 2025年第06期 86-100页

作者： Renshuai TAO Shijie TANG Haotong QIN Wei WANG Yunchao WEI Yao ZHAO Institute of Information Science Beijing Jiaotong University Center for Project-Based Learning (PBL) D-ITET ETH Zürich

The proliferation of artificial intelligence(AI)-generated content on social media has escalated concerns regarding misinformation, privacy, and security. Current deepfake detection methods struggle to generalize effectively, failing to keep pace with evolving generative models like generative adversarial networks(GANs) and diffusion models. Inspired by the robustness of “real” and “fake” descriptions in the language world, in this paper, we introduce the language-enhanced deepfake detection network(LEDNet), a multimodal foundation model that leverages both linguistic and visual information to improve detection accuracy and adaptability. We are the first to exploit multi-modal technologies for generalized deepfake detection through an un-trained-backbone mechanism, which utilizes pre-trained vision-language models without the need for additional retraining. The model is powered by two key components: language-guided knowledge aggregation(LKA),which assembles a linguistic knowledge base of real and fake indicators, and attention-based vision-language mutualism(AVM), which aligns multimodal features to enhance detection precision. Extensive experiments across 25 popular deepfake datasets demonstrate that LEDNet outperforms state-of-the-art methods, achieving superior accuracy and generalization across diverse deepfake generation techniques. This work sets a new benchmark in multimodal deepfake detection, advancing the application of foundation models in this domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KP2Dtiny: Quantized Neural Keypoint Detection and Description on the Edge 5

KP2Dtiny: Quantized Neural Keypoint Detection and Descriptio...

引用

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Ruegg, Thomas Giordano, Marco Magno, Michele D-ITET Eth Zurich Zurich Switzerland Eth Zurich Center for Project Based Learning Zurich Switzerland

ISBN: (纸本)9798350332674

Detection and description of keypoints in images is a fundamental component of a wide range of tasks such as Simultaneous Localization And Mapping (SLAM), image alignment and structure from motion (SfM). Efficient computation of these features is crucial for real-time applications and has been addressed by multiple handcrafted algorithms and, recently, by deep neural network-based detectors. Learned detectors achieve high detection performance, but pose high computational requirements, making them slow and impractical for low-power resource constraint platforms. This paper presents a quantized neural keypoint detector and descriptor optimized for edge devices exploiting two recent AI platforms such as MAX78000 by Analog Devices and the Coral AI USB accelerator from Google. To accommodate the diverse constraints and requirements of various applications, we propose and evaluate two model architectures (KP2DtinySmall and KP2DtinyFast) and deploy them on the aforementioned platforms using full 8-bit integer quantization. Furthermore, we extensively evaluate these models in terms of power, latency and accuracy, reporting results on three image sizes (88x88, 320x240 and 640x480), evaluating both quantized and non-quantized models. Fully quantized, KP2DtinySmall reduces network size by a factor of 54x while improving homographic estimation accuracy on 88x88 images on the most stringent threshold (Correctness d1) by 32.4% (0.550) and on 320x240 images by 10.7% (0.648) compared to the KeypointNet architecture by Yang You et. al. This result is achieved by designing a new network with low power platforms in mind, particularly addressing the lower resolution by increasing the density of detectable features. Deployed on the MAX78000 MCU, inference of low-resolution images is run at 59 FPS, consuming 1.1 mJ per image. On the Coral usb accelerator, KP2DtinyFast runs inference on low-resolution images at 527 FPS consuming 3.1 mJ, on high resolution it achieves 70 FPS at 19.9 mJ pe

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robustness Evaluation of Localization Techniques for Autonomous Racing

Robustness Evaluation of Localization Techniques for Autonom...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Tian Yi Lim Edoardo Ghignone Nicolas Baumann Michele Magno Center for Project-Based Learning ETH Zürich

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

This work introduces SynPF, an MCL-based algorithm tailored for high-speed racing environments. Benchmarked against Cartographer, a state-of-the-art pose-graph SLAM algorithm, SynPF leverages synergies from previous particle-filtering methods and synthesizes them for the high-performance racing do-main. Our extensive in-field evaluations reveal that while Cartogra-pher excels under nominal conditions, it struggles when subjected to wheel-slip-a common phenomenon in a racing scenario due to varying grip levels and aggressive driving behaviour. Conversely, SynPF demonstrates robustness in these challenging conditions and a low-latency computation time of 1.25 ms on on-board computers without a GPU. Using the FITENTH platform, a 1:10 scaled autonomous racing vehicle, this work not only highlights the vulnerabilities of existing algorithms in high-speed scenarios, tested up until $7.6 \text{ms}^{-1}$ , but also emphasizes the potential of SynP F as a viable alternative, especially in deteriorating odometry conditions.

关键词： Location awareness Computers Simultaneous localization and mapping Computational modeling Graphics processing units Filtering algorithms Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

3D Hand Tracking with Induced Magnetic Field

3D Hand Tracking with Induced Magnetic Field

引用

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Bian, Sizhen Zhou, Bo Lukowicz, Paul Liu, Mengxi Magno, Michele Guo, Kexuan Center for Project-Based Learning D-ITET Eth Zürich Zürich Switzerland German Research Center for Artificial Intelligence Kaiserslautern Germany

ISBN: (纸本)9781665453813

Sensor-based 3D hand tracking is still challenging despite the massive exploration of different sensing modalities in the past decades. This work describes the design, implementation, and evaluation of a novel induced magnetic field-based 3D hand tracking system, aiming to address the shortcomings of existing approaches and supply an alternative solution. The system is composed of transmitters for magnetic field generation, a wrist-worn receiver for field strength sensing, and Zigbee units for synchronization. In more detail, the transmitters generate the oscillating magnetic fields with a registered sequence, the receiver coil senses the strength of the induced magnetic field by a customized three axes orthogonal coil, which is configured as the LC oscillator with the same oscillating frequency so that an induced current shows up when the receiver is located in the field of the generated magnetic field. Five scenarios are explored to evaluate the performance of the proposed system in hand tracking regarding the transmitters' deployment: 'in front of a whiteboard', 'above a table', 'in front of and in a shelf', 'in front of the waist and chest', and 'around the waist'. The true-range multilateration method is used to compute the coordinates of the hand in 3D space. Compared with the ground truth collected by a commercial ultrasound positioning system, the presented magnetic field-based system shows a robust accuracy of around ten centimeters with the transmitters deployed both off-body and on-body(in front of the waist and chest), which indicates the feasibility of the proposed sensing modality in 3D hand tracking. © 2023 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

Robustness Evaluation of Localization Techniques for Autonomous Racing

arXiv

引用

arXiv 2024年

作者： Lim, Tian Yi Ghignone, Edoardo Baumann, Nicolas Magno, Michele Center for Project-Based Learning ETH Zürich Switzerland

This work introduces SynPF, an MCL-based algorithm tailored for high-speed racing environments. Bench-marked against Cartographer, a state-of-the-art pose-graph SLAM algorithm, SynPF leverages synergies from previous particle-filtering methods and synthesizes them for the high-performance racing domain. Our extensive in-field evaluations reveal that while Cartographer excels under nominal conditions, it struggles when subjected to wheel-slip—a common phenomenon in a racing scenario due to varying grip levels and aggressive driving behaviour. Conversely, SynPF demonstrates robustness in these challenging conditions and a low-latency computation time of 1.25 ms on on-board computers without a GPU. Using the F1TENTH platform, a 1:10 scaled autonomous racing vehicle, this work not only highlights the vulnerabilities of existing algorithms in high-speed scenarios, tested up until 7.6 m s−1, but also emphasizes the potential of SynPF as a viable alternative, especially in deteriorating odometry conditions. Code is available here: https://***/ForzaETH/particle_filter. © 2024, CC BY.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

WIP: A Study Report in the Web Technologies Course: What Makes Feedback Effective for project-based learning?

WIP: A Study Report in the Web Technologies Course: What Mak...

引用

2023 ASEE Annual Conference and Exposition - The Harbor of Engineering: Education for 130 Years, ASEE 2023

作者： Jaber, Alaa Lechasseur, Kimberly Mottakin, Khairul Song, Zheng Computer and Information Science Department University of Michigan Dearborn United States Center for Project-based Learning Worcester Polytechnic Institute United States

In this work-in-progress paper, we report our experience of applying project-based learning (PjBL) in a web technology course, with a focus on how different feedback tactics affect students' learning outcomes. Giving high-quality feedback can have an immediate impact on students' learning progress. Although process-level feedback is considered more effective than task-level feedback in traditional pedagogies, it is still unclear whether this conclusion can be exacerbated or mitigated when applied to PjBL, as PjBL emphasizes students' ownership and authenticity. We divided students into two groups and applied different feedback strategies. We report findings and insights to help instructors develop feedback policies and practices that are effective and likely to benefit students. Our results suggest that giving low-level feedback still improves students' learning outcomes in the context of PjBL, especially for technical tasks. © American Society for Engineering Education, 2023.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

TC-Driver: A Trajectory-Conditioned Reinforcement learning Approach to Zero-Shot Autonomous Racing

IEEE Transactions on Field Robotics

引用

IEEE Transactions on Field Robotics 2024年 1卷 527-536页

作者： Edoardo Ghignone Nicolas Baumann Michele Magno Department of Information Technology and Electrical Engineering Center for Project-Based Learning ETH Zurich Zurich Switzerland

Autonomous racing challenges perception, planning, and control algorithms, serving as a testbed for general autonomous driving. While traditional methods, such as model predictive control (MPC), can generate optimal control sequences, they are sensitive to modeling parameter accuracy. This article introduces trajectory-conditioned RL controller (TC-Driver), a reinforcement learning (RL) approach for robust control in autonomous racing, addressing tire parameter modeling inaccuracies. TC-Driver is conditioned by a trajectory from any high-level planner, combining RL’s learning capabilities with the reliability of traditional planning. Trained under varying tire conditions, it aims to generalize across different model parameters, enhancing real-world racing performance. Experimental results show TC-Driver improves generalization robustness compared with a state-of-the-art (SotA) end-to-end architecture. It achieves a 29-fold improvement in crash ratio when facing model mismatch and successfully transfers to unseen tracks with new features, while the baseline fails. In physical deployment, TC-Driver demonstrates zero-shot Sim2Real capabilities, outperforming end-to-end agents tenfold in crash ratio while maintaining similar driving characteristics in reality as in simulation. This hybrid RL architecture leverages traditional planning methods’ reliability while exploiting RL’s ability to handle model uncertainties, offering a robust solution for autonomous racing challenges.

关键词： Tires Computer architecture Trajectory Training Automobiles Robots Planning Computational modeling Robustness Friction

来源：评论

学校读者我要写书评

暂无评论

TinyssimoRadar: In-Ear Hand Gesture Recognition with Ultra-Low Power mmWave Radars

TinyssimoRadar: In-Ear Hand Gesture Recognition with Ultra-L...

引用

IEEE International Conference on Internet-of-Things Design and Implementation (IoTDI)

作者： Andrea Ronco Philipp Schilk Michele Magno Center for Project-Based Learning D-ITET ETH Zürich

ISBN: (数字)9798350370256

ISBN: (纸本)9798350370263

Smart Internet of Things (IoT) devices are on the rise in popularity, with innovative use cases and applications emerging every year. Including intelligence in these novel systems presents the challenge of integrating interaction and communication in scenarios where traditional interfaces are not viable. Hand Gesture Recognition (HGR) has been proposed as an intuitive Human-Machine Interface, potentially suitable for controlling several classes of devices in the context of the Internet of Things. This paper proposes a low-power in-ear HGR system based on mm-wave radars, efficient spatial and temporal Convolutional Neural Networks and an energy-optimized hardware design. The design is suitable for battery-operated devices, with stringent size and energy constraints, enabling user interaction with wearable devices, but also suitable for home appliances and industrial applications. The proposed machine learning model is characterized thoroughly for robustness and generalization capabilities, achieving 94.9% (single subject) and 86.1% (Leave-One-Out Cross-validation) accuracy on a set of 11+1 gestures with a model size of only 36KiB and inference latency of 32.4ms on a 64MHz Cortex-M33 microcontroller, making it compatible with real-time applications. The system is demonstrated in a fully integrated, miniaturized in-ear device with a full-system average power consumption of 18.4mW, a more than 6x improvement on the current state of the art.

关键词： Measurement Accuracy Power demand Radar Gesture recognition Real-time systems Hardware

来源：评论

学校读者我要写书评

暂无评论

SwiftEagle: An Advanced Open-Source, Miniaturized FPGA UAS Platform with Dual DVS/Frame Camera for Cutting-Edge Low-Latency Autonomous Algorithms

SwiftEagle: An Advanced Open-Source, Miniaturized FPGA UAS P...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Christian Vogt Michael Jost Michele Magno Center for Project Based Learning D-ITET ETH Zurich Switzerland

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Low-latency sensing and decision-making processing are critical requirements for the highly dynamic control and perception applications often found in Unmanned Areal Systems (UASs). Novel sensors such as Dynamic Vision Sensors (DVSs) are enhancing the pure performance of the perception component with orders of magnitude lower latency. However, they are typically not optimally integrated with the computing hardware, which effectively reduces the potential in both latency and power consumption. In addition to the non-optimal integration, low latency processing of such high data rate generating sensors is often challenging on resource-constrained platforms. Here, Field Programmable Gate Arrays (FPGAs) platforms offer a promising set of features, including low-level access to hardware and memories, as well as high-speed interfaces. On the other hand, FPGA platforms are not as popular on UASs due to their complex programming and development environments, steep initial learning curve, and challenges in achieving optimal performance. To accelerate future development, this paper presents SwiftEagle, an open-source, cutting-edge 720g FPGA based UAS based on a custom hardware design including a dual camera interface RGB/DVSs on a multi-sensors subsystem and an initial software and firmware stack designed for high precision recording of machine learning datasets in-flight with sub-micro-second time resolution and on-FPGA rendering of DVS event frames. Utilizing this developed platform, as proof-of-concept the end-to-end latency of a novel, just released DVS is shown to be below 210µs as a worst-case scenario, enabling future cutting-edge autonomous algorithms.

关键词： Software algorithms Cameras Hardware Software Sensors Recording Voltage control Low latency communication Field programmable gate arrays Microprogramming

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：