检索结果-内蒙古大学图书馆

IEEE Latin American Robotics Symposium, LARS

作者： Gabryel Silva Ramos Amaro Azevedo De Lima Luciana F. Almeida Jose Lima Milena Faria Pinto Electronic Engineering Department CEFET-RJ Rio de Janeiro Brazil Research Centre in Digitalization and Intelligent Robotics (CeDRI) Instituto Politécnico de Bragança Bragança Portugal

Mobile multi-robot systems are versatile alternatives for improving single-robot capacities in many applications, such as logistics, environmental monitoring, search and rescue, photogrammetry, etc. In this sense, this kind of system must have a reliable communication network between the vehicles, ensuring that information exchanged within the nodes has little losses. This work simulates and evaluates the use of autoencoders for image compression in a multi-UAV simulation with ROS and Gazebo for a generic surveillance application. The autoencoder model was developed with the Keras library, presenting good training and validation results, with training and validation accuracy of 70%, and a Peak signal Noise Ratio (PSNR) of 40dB. The use of the CPU for the simulated UAVs for processing and sending compressed images through the network is 25% faster. The results showed that this compression methodology is a good choice for improving the system’s performance without losing too much information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sign Language Classification through Reservoir Computing and Depth Camera Technology

Enhancing Sign Language Classification through Reservoir Com...

引用

image processing and Robotics (ICIP), International Conference on

作者： Witchuda Thongking Chinthaka Premachandra Ardi Wiranata Shingo Maeda Department of Engineering and Science Shibaura Institute of Technology Tokyo Japan Department of Electronic Engineering Shibaura Institute of Technology Tokyo Japan Department of Mechanical and Industrial Engineering University of Gadjah Mada Yogyakarta Indonesia Department of Mechanical Engineering Tokyo Institute of Technology Tokyo Japan Living Systems Materialogy (LiSM) Research Group International Research Frontiers Initiative (IRFI) Tokyo Institute of Technology Tokyo Japan

ISBN: (数字)9798350374766

ISBN: (纸本)9798350374773

The depth camera has emerged as an efficacious tool for facilitating interactions between individuals and machines. Its advantageous features, including a lightweight design, high durability, completeness, superior image quality, and versatility, have prompted researchers to explore its integration into advanced applications. Currently, the prevailing methods for classifying sign language exhibit certain limitations, such as suboptimal accuracy and inefficiency in gesture recognition technologies. In this study, we conduct a comprehensive examination of hand language characteristics rooted in American Sign Language (ASL), utilizing gesture-based interactions and augmenting sensing performance through preprocessing and the application of reservoir computing in the training model. We conduct a comprehensive evaluation of the gesture characteristics captured by the depth camera, elucidating a methodology encompassing preprocessing, machine learning, and the technical prediction of salient gesture features derived from conventional depth camera video footage. This endeavor aims to establish a robust signal model for enhanced understanding and representation of the analyzed gestures. Our machine-learning models adeptly predict American Sign Language signs. Correlation values derived from the depth camera data demonstrate a pronounced alignment with naturally occurring variations in metrics observed within specific gestures. Our methodologies for quantifying gestures with depth cameras contribute to heightened accessibility in quantitative motion analysis. The outcomes of the reservoir computing implementation exhibit the successful classification of three hand language signs, thereby manifesting high precision and recall. The robust performance of the classification is pivotal for practical applications and underscores the efficacy of our approach.

关键词： Training Sign language Tracking Computational modeling Machine learning Assistive technologies Cameras

来源：评论

学校读者我要写书评

暂无评论

An Efficient YOLOv5n Based Object Detection Heterogeneous SoC Implementation for Remote Sensing images

An Efficient YOLOv5n Based Object Detection Heterogeneous So...

引用

Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Heming Liu Bowen Yao Rong Xu Yu Peng Liansheng Liu School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Shanghai Institute of Satellite Engineering Shanghai China School of Electronics and Information Engineering Harbin Institute of Technology Yantai China

ISBN: (数字)9798331529192

ISBN: (纸本)9798331529208

Convolutional neural networks (CNNs) are widely used in the field of remote sensing image object detection due to their high accuracy. However, the large number of parameters and high computational complexity of CNNs make it challenging to deploy them in real-time on embedded devices with limited computational and storage resources. This significantly restricts their practical application. To address this challenge, lightweight YOLOv5n model is chosen to realize object detection. The model is further optimized by activation function modification and parameter quantization to be more hardware-friendly. In addition, deploying a Deep Learning processing Unit (DPU) on the Zynq heterogeneous SoC by hardware-software co-design to significantly accelerate the YOLOv5n based remote sensing object detection. Experimental results show that the optimized YOLOv5n model reaches a lossless accuracy at 61.4% on the DIOR dataset when implemented on an embedded platform based on Zynq. The experimental platform achieves an image throughput of 232.1 FPS with a power consumption of 19.4W. performance per watt (FPS/W) is 9.0× and 1.8× higher than that of i7-12700H CPU and RTX 3070Ti GPU respectively.

关键词： performance evaluation Accuracy Quantization (signal) Computational modeling Object detection Throughput Real-time systems Energy efficiency Convolutional neural networks Remote sensing

来源：评论

学校读者我要写书评

暂无评论

processing Continuous-Valued signals for Multimodal Spike-Based Pose Regression

Processing Continuous-Valued Signals for Multimodal Spike-Ba...

引用

2025 IEEE International Conference on simulation, modeling, and Programming for Autonomous Robots, SIMPAR 2025

作者： Sudevan, Vidya Zayer, Fakhreddine Kausar, Rizwana Javed, Sajid Karki, Hamad De Masi, Giulia Dias, Jorge Khalifa University Center for Autonomous Robotic Systems Abu Dhabi United Arab Emirates Sorbonne University Dept. Science and Engineering Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331516857

In underwater missions, energy-efficient operation is critical to maximize the operability of an autonomous robots and mission duration. At the same time, accurate pose estimation at reduced computational cost is essential for various underwater robotics and exploration applications. This paper presents an energy-efficient model for pose regression tasks based on direct Spike-Coding-Decoding (SCD) with adaptive threshold mechanism. The proposed approach enables efficient processing of multimodal continuous-valued images and IMU data. The effectiveness of the proposed module is tested using an open-sourced underwater simulator. In underwater robotics domain, real-world testing remains critical due to limited access to actual underwater environment, making simulators invaluable for rapid algorithm development and refinement. Accordingly, HoloOcean simulator is utilized to collect images and IMU sensor data from various underwater scenarios, which are then fed into a pose estimation framework. The SCD module uses 2D and 1D convolutional layers followed by LIF neurons with adaptive threshold to convert continuous-valued data into sparse spike-based signals. During spike decoding, the spike-based signals are converted back to continuous-values by utilizing the accumulated membrane potential of the output LIF neurons. The feasibility of SCD module is evaluated by its ability to introduce sparsity in spike-based representations with minimal information loss that enables efficient signal reconstruction. Custom multimodal data is collected using the HoloOcean simulator and is used to train the network. We compared the performance of the adaptive learnable threshold method with fixed threshold methods. The experimental results show that spike coding with an adaptive threshold mechanism is highly effective compared to a fixed threshold mechanism, as it can encode the continuous-valued input to its spike-based representation with ≈ 2× higher sparsity and a lesser spike rate. ©

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Dual-Tree Complex Wavelet Coefficient Magnitude modeling Using Scale Mixtures of Rayleigh Distribution for image Denoising

引用

CIRCUITS systems AND signal processing 2020年第6期39卷 2968-2993页

作者： Saeedzarandi, Mansoore Nezamabadi-pour, Hossein Jamalizadeh, Ahad Shahid Bahonar Univ Kerman Dept Elect Engn IDPL Kerman Iran Shahid Bahonar Univ Kerman Fac Math & Comp Dept Stat Kerman Iran

Denoising an image, while retaining the important features of the image, has been a fundamental problem in image processing. Dual-tree complex wavelet transform is a recently created transform that offers both near shift invariance and improved directional selectivity properties. This transform has been used in many techniques, including denoising. However, these techniques have used the real and imaginary components of the complex-valued sub-band coefficients separately. This paper proposes the use of coefficient magnitudes to provide an improvement in image denoising. Our proposed algorithm is based on the maximum a posteriori estimator, wherein the heavy-tailed scale mixtures of bivariate Rayleigh distribution are considered as the noise-free wavelet coefficient magnitudes' prior distribution. Also, in our work, the necessary parameters of the bivariate distributions are estimated in a locally adaptive way to improve the denoising results via using the correlation between the amplitudes of neighbor coefficients. simulation results delineate the performance of the proposed algorithm in both MSSIM and PSNR metrics.

关键词： image denoising Coefficient magnitude modeling MAP estimator Dual-tree complex wavelet transform Heavy-tailed distributions Scale mixtures of bivariate Rayleigh distribution

来源：评论

学校读者我要写书评

暂无评论

Novel Test Bench for End-to-End Validation of Monocular Depth Estimation Under the Influence of Glaring Situations

Novel Test Bench for End-to-End Validation of Monocular Dept...

引用

International Conference on Intelligent Transportation

作者： Fabian Ulreich André Kaup Martin Ebert CARISSMA Institute of Automated Driving (C-IAD) Technische Hochschule Ingolstadt Ingolstadt Germany Chair of Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Faculty of Electrical Engineering and Information Technology Technische Hochschule Ingolstadt Ingolstadt Germany

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

The black-box nature of deep learning models employed in automated driving functions requires suitable evaluation tools. Efforts are being made to increase the validity of testing environments for real-world operations. Understanding the impact of the sensor characteristics and degradation on the downstream task of perception is another field of research. We propose a test environment for vision-based autonomous driving functions in which a real camera and a deep learning model can be evaluated jointly. Our approach enables the validation under real-world brightness conditions through projector technology. To demonstrate its applicability, we employed a Vision Transformer to perform monocular depth estimation. Our experimental setup included a challenging scenario involving glare to assess the differences in performance between the testing environments: camera test bench and simulation. We quantified the gap by contrasting image quality metrics of partly-synthetic and pure synthetic data with real-world data contained in the KITTI depth dataset. With our approach, we were able to produce images that are 37 % closer to real-world than synthetic image data. Also, the gap in data variability is 18 % less than with synthetic data. In addition, we found that clipping in glare situations does not necessarily lead to large errors in depth prediction.

关键词： Deep learning Depth measurement System performance Vehicle safety Closed box Detectors Cameras Transformers Testing Synthetic data

来源：评论

学校读者我要写书评

暂无评论

STAP performance evaluation for Spaceborne Radar systems with Different Clutter Distribution Models

STAP Performance Evaluation for Spaceborne Radar Systems wit...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Fan Yang Penghui Huang Xin Lin Bingliang Zhang Junli Chen Peili Xi Guozhong Chen Xingzhao Liu School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Institute of Satellite Engineering Shanghai China

As one of the main statistical characteristics of clutter, the clutter amplitude distribution plays an important role in the accurate modeling of spaceborne multi-channel radar signal as well as the subsequent, maritime radar target detection. In this paper, considering that the space-time adaptive processing (STAP) technology is usually applied to accomplish the main-lobe clutter rejection in a space-borne surveillance radar, the influence of different clutter amplitude distributions on STAP in a spaceborne multichannel radar system are analyzed. Firstly, a spaceborne multi-channel clutter model is established based on radar equation and clutter space-time steering vector. Then, Rayleigh distribution, Weibull distribution, lognormal distribution, K distribution, generalized Pareto distribution, and IG-CG distribution are used to fit the clutter amplitude. Finally, the effects of these clutter amplitude distributions on STAP performance are analyzed, respectively. The simulation results show that in the case of the same clutter power, the influence of different clutter amplitude distributions on STAP performance is approximately the same.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wideband Synthetic Aperture Test Bed for Intelligent Reflecting Surfaces

Wideband Synthetic Aperture Test Bed for Intelligent Reflect...

引用

Asilomar Conference on signals, systems & Computers

作者： Peter Vouras Mohamed Kashef Hany Sudantha Perera Carnot Nogueira Richard Candell Kate A. Remley United States Department of Defense Washington DC USA National Institute of Standards and Technology (NIST) Gaithersburg MD USA National Institute of Standards and Technology (NIST) Boulder CO USA

This paper describes a spherical beamforming implementation for wideband synthetic aperture channel sounders that can be used to predict the scattering performance of an Intelligent Reflection Surface (IRS). An IRS creates controlled propagation conditions in wireless channels that can amplify the signal power available at a receiver or can enhance communications security by reducing the signal leaking to an eavesdropper. Most IRS performance evaluations described in the technical literature to date rely on simulation and modeling approaches. These techniques necessarily produce idealized results that neglect the impact of real-world multipath. However, by incorporating wireless channel measurements taken by a synthetic aperture into a spherical beamforming framework, the detrimental effects of environmental multipath on the signal reflected from an IRS can be realistically accounted for.

关键词： Wireless communication performance evaluation Array signal processing Scattering Receivers Apertures Reflection

来源：评论

学校读者我要写书评

暂无评论

On the modeling of Reliability in Extreme Edge Computing systems

On the Modeling of Reliability in Extreme Edge Computing Sys...

引用

International Conference on Communications, signal processing, and their Applications (ICCSPA)

作者： Mhd Saria Allahham Amr Mohamed Aiman Erbad Hossam Hassanein School of Computing Queen's University Kingston ON Canada College of Engineering Qatar University Qatar College of Science and Engineering Hamad Bin Khalifa University Qatar

ISBN: (纸本)9781665482387

Extreme edge computing (EEC) refers to the end-most part of edge computing wherein computational tasks and edge services are deployed only on extreme edge devices (EEDs). EEDs are consumer or user-owned devices that offer computational resources, which may consist of wearable devices, personal mobile devices, drones, etc. Such devices are opportunistically or naturally present within the proximity of other user devices. Hence, utilizing EEDs to deploy edge services or perform computational tasks fulfills the promise of edge computing of bringing the services and computation as close as possible to the end-users. However, the lack of knowledge and control over the EEDs computational resources raises a red flag, since executing the computational tasks successfully becomes doubtful. To this end, we aim to study the EEDs randomness from the computational perspective, and how reliable is an EED in terms of executing the tasks on time. Specifically, we provide a reliability model for the EEDs that takes into account the probabilistic nature of the availability of the EEDs' computational resources. Moreover, we study the reliability of executing different types of computational tasks in EEC systems that are distributed across the EEDs. Lastly, we carry out experimental results to analyze the EEDs and the EEC systems' reliability behavior in different scenarios.

关键词： performance evaluation Computational modeling Wearable computers simulation signal processing Probabilistic logic Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Research on evaluation Method of image Blending Based image simulation

Research on Evaluation Method of Image Blending Based Image ...

引用

6th International Conference on Intelligent Computing and signal processing (ICSP)

作者： Yu Zhang Yan Zhang Zhiguang Shi Xiaoran Shi Di Liu Yuchang Suo National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science and Technology National University of Defense Technology Changsha Hunan Province China

ISBN: (纸本)9781665404136;9781665447300

Object detection and tracking algorithms for specific targets are important technologies in the fields of autonomous driving and video surveillance. The verification of related algorithms and the training of data-driven machine learning methods often rely on high-quality and large-scale data support. Therefore, data simulation methods are usually used to supplement the quantity and richness of data. This paper proposes an image simulation performance evaluation method based on the Probably Approximately Correct (PAC) learnable theory: experience consistency loss, which is used to quantitatively evaluate simulated images. Compared with the traditional performance evaluation method based on expert score and Turing test, this evaluation method can objectively and quantitatively reflect the characteristic consistency between the simulated image and the real image. The experimental results show that the evaluation results of this method are consistent with the qualitative analysis results, which can directly reflect the performance improvement of the simulation image for the machine learning model.

关键词： performance evaluation Training Analytical models Machine learning algorithms Target tracking Computational modeling Machine learning

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：