检索结果-内蒙古大学图书馆

Exploring radar data Representations in Autonomous Driving: A Comprehensive Review

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第6期26卷 7401-7425页

作者： Yao, Shanliang Guan, Runwei Peng, Zitian Xu, Chenhang Shi, Yilu Ding, Weiping Lim, Eng Gee Yue, Yong Seo, Hyungjoon Man, Ka Lok Ma, Jieming Zhu, Xiaohui Yue, Yutao Yancheng Inst Technol Sch Informat Engn Yancheng 224051 Peoples R China Xian Jiaotong Liverpool Univ Sch Adv Technol Suzhou 215123 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Thrust Artificial Intelligence & Thrust Intelligen Guangzhou 511400 Peoples R China Univ Liverpool Fac Sci & Engn Liverpool L69 3GH England Nantong Univ Sch Artificial Intelligence & Comp Sci Nantong 226019 Peoples R China City Univ Macau Fac Data Sci Macau 999078 Peoples R China

With the rapid advancements of sensor technology and deep learning, autonomous driving systems are providing safe and efficient access to intelligent vehicles as well as intelligent transportation. Among these equipped sensors, the radar sensor plays a crucial role in providing robust perception information in diverse environmental conditions. This review focuses on exploring different radar data representations utilized in autonomous driving systems. Firstly, we introduce the capabilities and limitations of the radar sensor by examining the working principles of radar perception and signal processing of radar measurements. Then, we delve into the generation process of five radar representations, including the ADC signal, radar tensor, point cloud, grid map, and micro-Doppler signature. For each radar representation, we examine the related datasets, methods, advantages and limitations. Furthermore, we discuss the challenges faced in these data representations and propose potential research directions. Above all, this comprehensive review offers an in-depth insight into how these representations enhance autonomous system capabilities, providing guidance for radar perception researchers. To facilitate retrieval and comparison of different data representations, datasets and methods, we provide an interactive website at https://***/radar.

关键词： radar Autonomous vehicles radar signal processing data visualization radar antennas Doppler radar Reviews radar detection radar cross-sections Doppler effect radar perception autonomous driving data representations intelligent vehicles intelligent transportation

来源：评论

学校读者我要写书评

暂无评论

Research and implementation of a multi-source sensing data posture fusion display system 24

Research and implementation of a multi-source sensing data p...

引用

5th International conference on Computer Science and Management technology, ICCSMT 2024

作者： Yan, Lintong Chen, Xiaobo Liu, Yijia Li, Zhiyong Information Science Academy of China Electronics Technology Group Corporation Beijing China Beijing Institute of Technology Beijing China 66242 Units of the Chinese People's Liberation Army Xilinguole Inner Mongolia China

ISBN: (纸本)9798400709999

Aiming at the problems such as vector map, image, DEM, inclined photography and other basic geographic information data and real-life photographs, surveillance video, drone video, laser point cloud, SAR radar images and other high-level geographic information data format differences, data management complexity, and difficult to integrate the situation, this paper centers on the management of multi-source sensor data and the integrated display of real-life situation to carry out research in two aspects, the use of large amounts of data Load scheduling technology, monitoring video automatic alignment technology, multi-source heterogeneous data lightweight processing technology, breakthrough multi-source sensing data situational fusion display technology, build multi-source sensing data situational fusion display system, to solve the multi-source heterogeneous data unified management, fusion processing, situational display and other issues, in order to realize the large-scale massive three-dimensional model data multi-source data management and two-three-dimensional visualization of the situational display to lay the foundation and provide the tools. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： radar imaging

来源：评论

学校读者我要写书评

暂无评论

WaterVG: Waterway Visual Grounding Based on Text-Guided Vision and mmWave radar

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第5期26卷 7275-7291页

作者： Guan, Runwei Jia, Liye Yao, Shanliang Yang, Fengyufan Xu, Sheng Purwanto, Erick Zhu, Xiaohui Man, Ka Lok Lim, Eng Gee Smith, Jeremy Hu, Xuming Yue, Yutao Univ Liverpool Fac Sci & Engn Liverpool L69 3BX England Jiangsu Ind Technol Res Inst JITRI Inst Deep Percept Technol Nanjing 210031 Peoples R China Yancheng Inst Technol Sch Informat Engn Yancheng 224051 Peoples R China Jiangsu Ind Technol Res Inst JITRI Inst Deep Percept Technol Nanjing 210031 Peoples R China Jiangsu Ind Technol Res Inst Nanjing 210031 Peoples R China Xian Jiaotong Liverpool Univ Sch Adv Technol Suzhou 215000 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Thrust Artificial Intelligence Guangzhou 511455 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Artificial Intelligence & Thrust Intelligent Trans Guangzhou 511455 Peoples R China

Waterway perception is critical for the special operations and autonomous navigation of Unmanned Surface Vessels (USVs), but current perception schemes are sensor-based, neglecting the interaction between humans and USVs for embodied perception in various operations. Therefore, inspired by visual grounding, we present WaterVG, the inaugural visual grounding dataset tailored for USV-based waterway perception guided by human prompts. WaterVG contains a wealth of prompts describing multiple targets, with instance-level annotations, including bounding boxes and masks. Specifically, WaterVG comprises 11,568 samples and 34,987 referred targets, integrating both visual and radar characteristics. The text-guided two-sensor pattern provides a fine granularity of text prompts aligned with the visual and radar features of the referent targets, containing both qualitative and numeric descriptions. To enhance the endurance and maintain the normal operations of USVs in open waterways, we propose Potamoi, a low-power visual grounding model. Potamoi is a multi-task model employing a sophisticated Phased Heterogeneous Modality Fusion (PHMF) mechanism, which includes Adaptive radar Weighting (ARW) and Multi-Head Slim Cross Attention (MHSCA). The ARW module utilizes a gating mechanism to adaptively extract essential radar features for fusion with visual inputs, ensuring prompt alignment. MHSCA, characterized by its low parameter count and computational efficiency (FLOPs), effectively integrates contextual information from both sensors with linguistic features, delivering outstanding performance in visual grounding tasks. Comprehensive experiments and evaluations on WaterVG demonstrate that Potamoi achieves state-of-the-art results compared to existing methods.

关键词： visualization Grounding radar Feature extraction sensor phenomena and characterization radar imaging sensor fusion Point cloud compression Millimeter wave communication Electronic mail Visual grounding multi-modal learning perception of unmanned surface vessels interactive perception

来源：评论

学校读者我要写书评

暂无评论

LiV-GS: LiDAR-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 421-428页

作者： Xiao, Renxiang Liu, Wei Chen, Yushuai Hu, Liang Harbin Inst Technol Sch Mech Engn & Automat Dept Automat Shenzhen 150001 Peoples R China

We present LiV-GS, a LiDAR-visual SLAM system in outdoor environments that leverages 3D Gaussian as a differentiable spatial representation. Notably, LiV-GS is the first method that directly aligns discrete and sparse LiDAR data with continuous differentiable Gaussian maps in large-scale outdoor scenes, overcoming the limitation of fixed resolution in traditional LiDAR mapping. The system aligns point clouds with Gaussian maps using shared covariance attributes for front-end tracking and integrates the normal orientation into the loss function to refines the Gaussian map. To reliably and stably update Gaussians outside the LiDAR field of view, we introduce a novel conditional Gaussian constraint that aligns these Gaussians closely with the nearest reliable ones. The targeted adjustment enables LiV-GS to achieve fast and accurate mapping with novel view synthesis at a rate of 7.98 FPS. Extensive comparative experiments demonstrate LiV-GS's superior performance in SLAM, image rendering and mapping. The successful cross-modal radar-LiDAR localization highlights the potential of LiV-GS for applications in cross-modal semantic positioning and object segmentation with Gaussian maps.

关键词： Laser radar Point cloud compression Simultaneous localization and mapping Three-dimensional displays Image reconstruction Cameras Rendering (computer graphics) visualization Image color analysis sensors Mapping SLAM range sensing multi-sensor fusion 3D Gaussian splatting

来源：评论

学校读者我要写书评

暂无评论

MMA-Net: Multi-Modal Attention Network for 2-D Object Detection in Autonomous Driving

MMA-Net: Multi-Modal Attention Network for 2-D Object Detect...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Gaur, Abhilash Goel, Shubh Goel, Kanishk Srirangarajan, Seshan Tseng, Po-Hsuan Feng, Kai-Ten New Delhi India Hsinchu Taiwan The Department of Electrical Engineering IIT Delhi New Delhi India The Department of Electrical Engineering Bharti School of Telecommunication Technology and Management IIT Delhi New Delhi India The Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan The Department of Electronics and Electrical Engineering NYCU Hsinchu Taiwan

ISBN: (纸本)9798350368741

Autonomous driving technology relies heavily on sensor data for environment perception. Heterogeneous sensors such as lidar, radar, and camera have their own strengths and limitations. Therefore, relying on any single sensor would restrict the effectiveness of autonomous driving technology. However, integrating data from such heterogeneous sensors poses challenges due to differences in their representations. This article outlines a deep learning network aimed at designing modality-agnostic multi-modal fusion architecture. We study sensor data from different modalities and learn fine-grained representations using modality-specific feature encoders independently. Then, a multi-modal attention-based network (MMA-Net) is proposed to fuse the data from heterogeneous modalities. The proposed MMA-Net fuses multi-modal sensor data by jointly exploiting the inter-modality and intra-modality relationships among camera, lidar, and radar sensors. The effectiveness of the proposed multi-modal fusion architecture is demonstrated using 2-D object detection metrics through extensive experiments on a dataset generated using the CARLA simulator. © 2025 IEEE.

关键词： autonomous driving CARLA simulator multi-modal learning object detection sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Comparison of Actual Performance between CDMA and DDMA Waveforms in Vehicle radar Application 16

Comparison of Actual Performance between CDMA and DDMA Wavef...

引用

16th International conference on Signal Processing Systems, ICSPS 2024

作者： Wang, Wanbin Zou, Lin School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781510689251

The Millimeter-wave radar has become an important sensor for advanced driver assistance systems due to its advantages such as environmental adaptability, low cost and detection accuracy. Most of current vehicle radars use Multiple Input Multiple Output (MIMO) technology to obtain better angular resolution. Among all MIMO radar waveforms, both CDMA and DDMA meet the requirements of next-generation high-performance radars and may become the mainstream radar waveforms in the future. Performance comparisons of the two waveforms are scattered in a large number of literatures and they are all from a theoretical point of view. At present, there is no literature comparing the practical performance of CDMA and DDMA. AWR6843 is a high-precision millimeter-wave radar sensor widely used in automotive safety, environmental monitoring and other applications. This SOC chip has been adopted in numerous automotive radar products. Thus, based on the data collected by a TI's AWR6843 radar evaluation board, this paper compares the performance of CDMA and DDMA in terms of waveform orthogonality, parameter estimation capability, and processing complexity. In addition, the paper discusses the merits and demerits of each technology and the limitations of its practical application, which provides an important reference for the optimization and technical route selection of future radar systems. © 2025 SPIE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

HRRP scattering center extraction method based on complex-valued neural network 3

HRRP scattering center extraction method based on complex-va...

引用

3rd International conference on Electrical, Electronics, and Information Engineering, EEIE 2024

作者： Lou, Jun Chen, Yingqing Yang, Jin Wang, Ling Hunan First Normal University Changsha410205 China

ISBN: (纸本)9781510688179

radar HRRP is easy to be obtained and contains rich target information. According to the scattering center theory, in the high frequency range, the target radar echo can be regarded as a superposition of several discrete and independent scattering center echoes. Extracting scattering center features from HRRP can be used for automatic target recognition. However, HRRP is generally complex value data, and traditional real-valued neural networks are difficult to process directly. To address this issue, this paper proposes a complex-valued neural network structure and designs the loss function based on the sparsity of the scattering center parameter space for HRRP scattering center extraction. Simulation experiments verify the effectiveness of the method. © The Authors.

关键词： radar theory

来源：评论

学校读者我要写书评

暂无评论

2025 4th International conference on Electronic Information and Communication Engineering, EICE 2025

2025 4th International Conference on Electronic Information ...

引用

4th International conference on Electronic Information and Communication Engineering, EICE 2025

The proceedings contain 27 papers. The topics discussed include: a pruned wavelet neural network noise optimization method for fiber optic gyroscope;an improved NSGA-II algorithm for multi-sensor scheduling optimization;research on automated annotation technology for radar range angle-doppler data based on visual supervision mechanism;multi-UAV deployment in complex mountain marathon: two tier relay and multi-objective genetic optimization;mobile sink path planning for data collection in three dimensional wireless sensor network;design of high voltage envelope tracking power supply based on multilevel architecture;a dynamic STC attenuation strategy based on environmental perception;and an automatic balancing algorithm for interface timing skew.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PETer: A lightweight human action recognition network based on millimeter-wave radar sparse point clouds 16

PETer: A lightweight human action recognition network based ...

引用

16th International conference on Signal Processing Systems, ICSPS 2024

作者： Sun, Kangsheng Jin, Biao Cai, Yan Li, Rongmin Jiangsu University of Science and Technology Ocean College Zhenjiang China Suzhou Zadar Vision Technology Co. Ltd. Suzhou China

ISBN: (纸本)9781510689251

Millimeter-wave radar, with its excellent environmental adaptability, high resolution, strong penetration capability, and privacy protection, is widely used in smart homes, elderly care, and security monitoring. However, due to the high sparsity of millimeter-wave point cloud data, it carries less information compared to video or LiDAR, posing significant challenges for precise and rapid human action recognition. This paper proposes a lightweight long-sequence spatiotemporal edge convolution Transformer network (PETer). The model first enhances the data, then separates the spatial and temporal information of the point cloud sequence, utilizes EdgeConv to capture the spatial geometric structure information of single-frame point clouds, and employs a Transformer to extract temporal features from the multi-frame spatial information. To validate the effectiveness of the model, this paper uses the IWR1443-ISK millimeter-wave radar as the detection sensor to capture human actions and generate a 3D point cloud dataset. This dataset covers 12 types of human actions from 7 volunteers, including walking, waving, boxing, and standing. The proposed model achieves an average accuracy of 98.50% on the dataset and 100% accuracy on the MARS human skeleton dataset. Compared to various point cloud networks, the PETer network is the smallest in size, fastest in speed, and highest in accuracy, demonstrating its superior performance in millimeter-wave radar human action recognition tasks. © 2025 SPIE.

关键词： Musculoskeletal system

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：