检索结果-内蒙古大学图书馆

Hybrid-Fusion Mamba for Multitask Point Cloud Learning With Visual Perception sensors

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 10183-10193页

作者： Dong, Hongwei Na, Shun Hu, Fengye Jilin Univ Coll Commun Engn Changchun 130012 Peoples R China Heilongjiang Univ Business & Technol Coll Informat & Electromech Engn Harbin 150025 Peoples R China Inner Mongolia Univ Coll Elect Informat Engn Hohhot 010021 Peoples R China

Mobile robots and autonomous vehicles rely on 3-D point cloud technology for environmental perception, which often employ various visual perception sensors within their Internet of Things (IoT) systems to acquire point cloud information. Nevertheless, the obtained point cloud data is frequently incomplete, making it difficult to effectively perform perception tasks. Multitask point cloud learning networks can not only achieve point cloud reconstruction under high occlusion rates but also assist the system in accomplishing various point cloud tasks. However, existing multitask point cloud learning models based on advanced Transformer frameworks often suffer from quadratic complexity, limiting their performance in massive point cloud data learning. In this article, we propose a novel approach named Hybrid-Fusion Mamba (HFMamba), as a pretraining network model specifically designed for multitask point cloud learning. Compared to Transformer-based networks, the proposed HFMamba possesses linear complexity, which can significantly reduce IoT systems' computational cost. HFMamba employs a unique first-layer feature fusion design that integrates point cloud features from three different perspectives, enabling it to capture deeper dependencies among the point clouds. Moreover, a hybrid scan strategy is proposed to separately scan the hidden states and residuals, aiming to model the sequence from different directions. Experimental results demonstrate that the proposed HFMamba network model outperforms many state-of-the-art methods without applying any serialization strategies to the original point cloud data. In particular, the proposed HFMambda approach achieves classification accuracies of 93.7% and 93.89% on ModelNet40 and ScanObjectNN, respectively.

关键词： Point cloud compression Transformers data models Computational modeling Three-dimensional displays Multitasking Visual perception sensor systems visualization Laser radar Feature fusion Hybrid-Fusion Mamba (HFMamba) hybrid scan multitask point cloud learning pretraining

来源：评论

学校读者我要写书评

暂无评论

Quantum radar: A Brief Review of Current Progress and New Methods of Understanding and Signal Processing, Validated by Experimental Results 27

Quantum Radar: A Brief Review of Current Progress and New Me...

引用

conference on radar sensor technology XXVII

作者： Brandsema, Matthew J. Szigethy, Xavier Penn State Appl Res Lab 225 Sci Pk Rd State Coll PA 16801 USA

ISBN: (纸本)9781510661844;9781510661851

Modern approaches to quantum radar implementation utilize the intrinsic correlations of two-mode squeezed vacuum photon pairs emerging from a nonlinear interaction. The most popular approach has been the use of delay lines for the idler and performing joint measurements on the idler and returning signal together. In this paper, it is argued and shown that this sort of implementation is not necessary to extract the quantum cross correlation terms. Immediate detection of the idler and later cross correlation on a large enough data set will yield identical covariance terms. Moreover, immediate idler detection facilitates the use of conventional radar signal processing which allows existing waveform toolboxes of classical radar to be utilized for quantum radar. This allows a much more relaxed set of constraints on the implementation of quantum radar techniques. This paper discusses these concepts, including new detection techniques from the author, and validates the framework with some preliminary experimental data. The presented data, as well as the recent work of others allows for the possibility of a much larger quantum advantage than previously thought, particularly when comparing to real-world practical classical sensors.

关键词： quantum radar quantum lidar remote sensing signal processing matched filter current progress quantum sensing quantum science

来源：评论

学校读者我要写书评

暂无评论

Ground Penetrating radar Signal Denoising Based on Multi-Scale Feature Fusion Network 4

Ground Penetrating Radar Signal Denoising Based on Multi-Sca...

引用

4th International conference on Artificial Intelligence, Virtual Reality and visualization, AIVRV 2024

作者： Zheng, Mingjun Tong, Yao Dai, Rongnan Yang, Zhongli Ningbo Electric Power Design Institute Co Ningbo China China Three Gorges University of Electrical Engineering & New Energy Yichang China

ISBN: (纸本)9798331528744

With the rapid development of electronic information technology, Ground Penetrating radar (GPR) technology has become an indispensable tool in fields such as urban construction, archaeology, and the military. However, due to the heterogeneity of underground media, scattering of electromagnetic waves, and equipment errors, GPR signals are often disturbed by noise, affecting detection accuracy. Therefore, this paper designs a multi-scale feature fusion network to enhance the robustness of denoising models for denoising GPR signals with different characteristics. The network is constructed based on the Inception architecture and consists of three parts: an encoder structure for extracting multi-scale features of GPR signals, a disentangler structure for classifying data features and generating corresponding feature masks, and a decoder for reconstructing the denoised signal. Additionally, ID-Net can also extract noise features, enhancing the model's interpretability. Experiments have proven that ID-Net outperforms traditional denoising models in removing GPR noise and demonstrates good denoising capabilities on datasets with different characteristics, proving the robustness of ID-Net in denoising GPR noise signals with different features. © 2024 IEEE.

关键词： Ground penetrating radar systems

来源：评论

学校读者我要写书评

暂无评论

Experimental Progress using Quantum Binary Waveforms and Immediate Idler Detection Techniques for Remote Sensing 28

Experimental Progress using Quantum Binary Waveforms and Imm...

引用

conference on radar sensor technology XXVIII

作者： Brandsema, Matthew J. Ross, Leslie A. Semone, Sky Kalyanapuram, Nikhil Argyropoulos, Christos Ozdemir, Sahin K. Penn State Univ Appl Res Lab State Coll PA 16803 USA Penn State Univ Dept Elect Engn University Pk PA 16802 USA Penn State Univ Dept Engn Sci & Mech University Pk PA 16802 USA Penn State Univ Mat Res Inst University Pk PA 16802 USA

ISBN: (纸本)9781510674158;9781510674141

Two current hurdles of quantum radar/LiDAR technology are i.) The use of joint measurement techniques, whereby the idler remains in a delay line or a quantum memory to be measured later with the returning signal, and ii.) The difficulty in creating high photon flux signals for long range sensing. Our measurement and detection protocol using immediate-idler-detection (IID) helps to alleviate both of these issues. We present our recent experimental data from characterizing our proof-of-concept IID quantum LiDAR system and show that similar to delay line approaches, we achieve strong correlation even in extremely noisy channels where the noise level exceeds the signal strength by as much as one hundred times. We have found that even in very lossy channels, the integration time remains extremely short and roughly the same value even as the noise is increased. We also show preliminary results through foggy free space channels and found positive correlation SNR even when the visibility was as low as 15%. Our measurement and detection protocol was designed to align closely with classical radar and LiDAR signal processing to better align the quantum and classical sensor regimes and allows for the potential to scale upwards and produce higher photon-flux signals from multiple photon pair sources.

关键词： quantum radar quantum lidar experiment remote sensing signal processing matched filter quantum sensing quantum science

来源：评论

学校读者我要写书评

暂无评论

Multi-IMU and mmWave radar Integration for Robust Land Vehicle Navigation 6

Multi-IMU and mmWave Radar Integration for Robust Land Vehic...

引用

6th International conference on Communications Signal Processing and their Applications

作者： Mounier, Eslam de Araujo, Paulo Ricardo Marques Korenberg, Michael Noureldin, Aboelmagd Queens Univ Kingston ON Canada Ain Shams Univ Cairo Egypt Royal Mil Coll Canada Kingston ON Canada

ISBN: (纸本)9798350384826;9798350384819

Despite the crucial role of the Global Navigation Satellite System (GNSS) for land vehicle navigation, it is prone to wireless signal degradation challenges that can compromise positioning accuracy and availability. Integrating GNSS with Dead Reckoning (DR) systems like the Inertial Navigation System (INS) offers a solution. Still, it is hindered by drifting errors and the limitations of Micro-Electro-Mechanical Systems (MEMS) technology. This paper aims to address the challenges faced by land vehicle navigation systems, particularly during extended GNSS outages, by leveraging the synergistic integration of data from multiple redundant Inertial Measurement Units (IMUs) and mmWave radar technology. To be specific, a Kalman Filter framework is employed to fuse raw measurements from multiple homogeneous IMUs, yielding refined and robust measurements. An Autoencoder model calibrates and denoises raw radar measurements, ensuring accurate and reliable forward velocity estimates. The enhanced measurements are then processed by a mechanization algorithm, yielding a navigation solution with significantly reduced drifting errors. The effectiveness of this approach has been validated with real-world data collected from IMUs and radar during road tests in downtown Kingston, Ontario, Canada. Our comprehensive testing across various scenarios has shown that the proposed method significantly improves navigation performance, achieving average heading and position accuracy enhancements of 89% and 62%, respectively.

关键词： Land vehicle navigation GNSS outages Inertial measurement unit mmWave radar sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Real-Time Dashboarding using Big data Tools 7

Real-Time Dashboarding using Big Data Tools

引用

7th International conference on Inventive Computation Technologies, ICICT 2024

作者： Sanjay, R. Pulakhandam, Dheeraj Nirmalrani, V. Sathyabama Institute of Science And Technology Dept. Computer Science And Engineering Chennai India

ISBN: (纸本)9798350359299

Real-time dashboarding software empowers organizations to harness the burgeoning IoT data stream, transforming raw sensor readings into actionable insights through a secure and scalable architecture. data from connected devices seamlessly flows via lightweight protocols like MQTT and is managed by a robust streaming platform like Kafka. Big data tools like Spark then extract meaning from this high-velocity data, preparing it for visualization on dynamic dashboards hosted by cloud platforms. These user-centric dashboards track key metrics, identify trends, and drive informed decision-making, but tackling challenges like scalability, security, and data quality is crucial to unlock the full potential of this transformative technology. © 2024 IEEE.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional DBSCAN Clustering Approach for Millimeter Wave radar Point Cloud data 16

Multi-dimensional DBSCAN Clustering Approach for Millimeter ...

引用

16th International conference on Microwave and Millimeter Wave technology (ICMMT)

作者： Li, Hanchen Fu, Chaowei Xi, Guangrong Wang, Qingmian Peng, Hongli Shanghai Jiao Tong Univ State Key Lab Radio Frequency Heterogeneous Integ Shanghai Peoples R China Shanghai Radio Equipment Res Inst Shanghai Peoples R China Shanghai Shentian Ind Co Ltd Shanghai Peoples R China

ISBN: (纸本)9798350389968

Addressing the poor resolution challenge of traditional Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithms in differentiating objects in close proximity, this paper introduces a multi-dimensional DBSCAN (MD-DBSCAN) clustering approach, considering the Doppler characteristics of millimeter wave (mmW) radar. Our approach is based on the idea that the whole clustering procedure is divided into two stages, i.e., velocity clustering and spatial one. Specifically, for each group, the clusters of varying radial velocities are firstly segmented, then followed by spatial dimension clustering. Experimental results demonstrate a 14.2% improvement in number of point clouds with this approach over traditional methods, underscoring its effectiveness in more accurately distinguishing closely situated objects in autonomous driving scenarios.

关键词： mmW radar DBSCAN Clustering Algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of SAC Methods for radar Dynamic Object Classification 18th

Performance Comparison of SAC Methods for Radar Dynamic Obje...

引用

18th International conference on Intelligent Autonomous Systems (IAS)

作者： Park, Yeong Sang Choi, Dooseop Min, Kyoung-Wook ETRI Daejeon South Korea

ISBN: (纸本)9783031449802;9783031449819

The sample consensus (SAC) methods have become increasingly important in the field of radar-based dynamic object classification for applications such as ego-motion estimation and obstacle avoidance. This paper presents a comprehensive performance comparison of several SAC methods for classifying dynamic objects using radar data. Our extensive experiments show that each SAC method's pros and cons, and provide insights into the effective use of SAC methods for radar-based dynamic object classification. It is expected that this study will help to increase the accuracy of dynamic object classification in real-world scenarios and guide future research in this area.

关键词： Dynamic object classification radar sensor Sample consensus

来源：评论

学校读者我要写书评

暂无评论

Grating Lobe Suppression in MIMO radar Networks using Kaiser-Kalmus Sum-Difference Beam Cancellation 2

Grating Lobe Suppression in MIMO Radar Networks using Kaiser...

引用

2nd IEEE International conference on Signal, Information and data Processing, ICSIDP 2024

作者： Zhao, Ke Wang, Jun Yang, Bin He, Jiacheng Geng, Xueyin Beihang University School of Electronic and Information Engineering Beijing China

ISBN: (纸本)9798331515669

MIMO radar networks are composed of multiple separated MIMO sensors and each radar sensor can be viewed as a subarray. Although the MIMO radar networks can obtain a larger virtual aperture, excessive node or subarray spacing will lead to a wider grating lobe distribution. In order to solve the grating lobe problem, this paper proposes a Kaiser-Kalmus sum and difference beam cancellation method, which uses subarray beam to suppress array factor's grating lobes. In the MIMO radar networks imaging scenario, the effectiveness of this algorithm was verified through simulation and experiments. © 2024 IEEE.

关键词： radar imaging

来源：评论

学校读者我要写书评

暂无评论

RoLM: radar on LiDAR Map Localization

RoLM: Radar on LiDAR Map Localization

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Mai, Yukai Zhao, Xiangrui Li, Han Gu, Yaqing Lang, Xiaolei Liu, Yong Zhejiang Univ Inst Cyber Syst & Control Hangzhou Peoples R China

ISBN: (纸本)9798350323658

Multi-sensor fusion-based localization technology has achieved high accuracy in autonomous systems. How to improve the robustness is the main challenge at present. The most commonly used LiDAR and camera are weather-sensitive, while the FMCW radar has strong adaptability but suffers from noise and ghost effects. In this paper, we propose a heterogeneous localization method of radar on LiDAR Map (RoLM), which can eliminate the accumulated error of radar odometry in real-time to achieve higher localization accuracy without dependence on loop closures. We embed the two sensor modalities into a density map and calculate the spatial vector similarity with offset to seek the corresponding place index in the candidates and calculate the rotation and translation. We use the ICP to pursue perfect matching on the LiDAR submap based on the coarse alignment. Extensive experiments on Mulran radar dataset, Oxford radar RobotCar dataset, and our data verify the feasibility and effectiveness of our approach.

关键词： Optical radar

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：