Surrounding Objects Detection and Tracking for Autonomous Driving Using LiDAR and Radar Fusion

Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,Radars relative to Lidars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution.In order to compensate for the low detection accuracy,incomplete target attributes and poor environmental adaptability of single sensors such as Radar and LiDAR,in this paper,an effective method for high-precision detection and tracking of surrounding targets of autonomous vehicles.By employing the Unscented Kalman Filter,Radar and LiDAR information is effectively fused to achieve high-precision detection of the position and speed information of targets around the autonomous vehicle.Finally,the real vehicle test under various driving environment scenarios is carried out.The experimental results show that the proposed sensor fusion method can effectively detect and track the vehicle peripheral targets with high accuracy.Compared with a single sensor,it has obvious advantages and can improve the intelligence level of autonomous cars.

Three-dimensional Fusion of Spaceborne and Ground Radar Reflectivity Data Using a Neural Network–Based Approach

The spaceborne precipitation radar onboard the Tropical Rainfall Measuring Mission satellite （TRMM PR） can provide good measurement of the vertical structure of reflectivity, while ground radar （GR） has a relatively high horizontal resolution and greater sensitivity. Fusion of TRMM PR and GR reflectivity data may maximize the advantages from both instruments. In this paper, TRMM PR and GR reflectivity data are fused using a neural network （NN）-based approach. The main steps included are： quality control of TRMM PR and GR reflectivity data; spatiotemporal matchup; GR calibration bias correction; conversion of TRMM PR data from Ku to S band; fusion of TRMM PR and GR reflectivity data with an NN method： interpolation of reflectivity data that are below PR＇s sensitivity; blind areas compensation with a distance weighting-based merging approach; combination of three types of data： data with the NN method, data below PR＇s sensitivity and data within compensated blind areas. During the NN fusion step, the TRMM PR data are taken as targets of the training NNs, and gridded GR data after horizontal downsampling at different heights are used as the input. The trained NNs are then used to obtain 3D high-resolution reflectivity from the original GR gridded data. After 3D fusion of the TRMM PR and GR reflectivity data, a more complete and finer-scale 3D radar reflectivity dataset incorporating characteristics from both the TRMM PR and GR observations can be obtained. The fused reflectivity data are evaluated based on a convective precipitation event through comparison with the high resolution TRMM PR and GR data with an interpolation algorithm.

基于改进Centerfusion的自动驾驶3D目标检测模型

针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。

A Heterogeneous Information Fusion Method for Maritime Radar and AIS Based on D-S Evidence Theory

Maritime radar and automatic identification systems (AIS), which are essential auxiliary equipment for navigation safety in the shipping industry, have played significant roles in maritime safety supervision. However, in practical applications, the information obtained by a single device is limited, and it is necessary to integrate the information of maritime radar and AIS messages to achieve better recognition effects. In this study, the D-S evidence theory is used to fusion the two kinds of heterogeneous information: maritime radar images and AIS messages. Firstly, the radar image and AIS message are processed to get the targets of interest in the same coordinate system. Then, the coordinate position and heading of targets are chosen as the indicators for judging target similarity. Finally, a piece of D-S evidence theory based on the information fusion method is proposed to match the radar target and the AIS target of the same ship. Particularly, the effectiveness of the proposed method has been validated and evaluated through several experiments, which proves that such a method is practical in maritime safety supervision.

BEV-radar:毫米波雷达-相机双向融合的三维目标检测

在自动驾驶场景下的3D目标检测任务中,探索毫米波雷达数据作为RGB图像输入的补充正成为多模态融合的新兴趋势。然而,现有的毫米波雷达-相机融合方法高度依赖于相机的一阶段检测结果,导致整体性能不够理想。本文提供了一种不依赖于相机检测结果的鸟瞰图下双向融合方法(BEV-radar)。对于来自不同域的两个模态的特征,BEV-radar设计了一个双向的基于注意力的融合策略。具体地,以基于BEV的3D目标检测方法为基础,我们的方法使用双向转换器嵌入来自两种模态的信息,并根据后续的卷积块强制执行局部空间关系。嵌入特征后,BEV特征在3D对象预测头中解码。我们在nu Scenes数据集上评估了我们的方法,实现了48.2 m AP和57.6 NDS。结果显示,与仅使用相机的基础模型相比,不仅在精度上有所提升,特别地,速度预测误差项有了相当大的改进。代码开源于https://github.com/Etah0409/BEV-Radar。

Investigation of system structure and information processing mechanism for cognitive skywave over-the-horizon radar

Based on the cognitive radar concept and the basic connotation of cognitive skywave over-the-horizon radar（SWOTHR）, the system structure and information processingmechanism about cognitive SWOTHR are researched. Amongthem, the hybrid network system architecture which is thedistributed configuration combining with the centralized cognition and its soft/hardware framework with the sense-detectionintegration are proposed, and the information processing framebased on the lens principle and its information processing flowwith receive-transmit joint adaption are designed, which buildand parse the work law for cognition and its self feedback adjustment with the lens focus model and five stages informationprocessing sequence. After that, the system simulation andthe performance analysis and comparison are provided, whichinitially proves the rationality and advantages of the proposedideas. Finally, four important development ideas of futureSWOTHR toward ＂high frequency intelligence information processing system＂ are discussed, which are scene information fusion, dynamic reconfigurable system, hierarchical and modulardesign, and sustainable development. Then the conclusion thatthe cognitive SWOTHR can cause the performance improvement is gotten.

New structure of Kalman filter for radar networking

Due to the different data rates of the sensors and communication delays in the radar netting, the research of the asynchronous multisensor data fusion problem is more practical than that of the synchronous one. Through discussing the sequential approach, which is the classical asynchronous multisensor data fusion algorithm, a new algorithm based on distributed computation structure is proposed. The new algorithm can meet the requirement of real-time computation of netting fusion system, and is more practical for engineering compared with the classical sequential approach. Simulation results show the validity of the presented algorithm.

Research on PCA and KPCA Self-Fusion Based MSTAR SAR Automatic Target Recognition Algorithm

This paper proposes a PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm. This algorithm combines the linear feature extracted from principal component analysis （PCA） and nonlinear feature extracted from kernel principal component analysis （KPCA） respectively, and then utilizes the adaptive feature fusion algorithm which is based on the weighted maximum margin criterion （WMMC） to fuse the features in order to achieve better performance. The linear regression classifier is used in the experiments. The experimental results indicate that the proposed self-fusion algorithm achieves higher recognition rate compared with the traditional PCA and KPCA feature fusion algorithms.

AF-CenterNet:基于交叉注意力机制的毫米波雷达和相机融合的目标检测

对于自动驾驶领域而言,确保在各种天气和光照条件下精确检测其他车辆目标是至关重要的。针对单个传感器获取信息的局限性,提出一种基于cross-attention注意力机制的融合方法(AF),用于在特征层面上融合毫米波雷达和相机信息。首先,将毫米波雷达和相机进行空间对齐,并将对齐后的点云信息投影成点云图像。然后,将点云图像在高度和宽度方向上进行扩展,以提高相机图像和点云图像之间的匹配度。最后,将点云图像和相机图像送入包含AF结构的CenterNet目标检测网络中进行训练,并生成一个空间注意力权重,以增强相机中的关键特征。实验结果表明,AF结构可以提高原网络检测各种大小目标的性能,特别是对小目标的检测提升更为明显,且对系统的实时性影响不大,是提高车辆在多种场景下检测精度的理想选择。

雷达信号与遥感地图融合的深度学习低慢小目标检测算法

雷达复杂环境低慢小目标检测是一项具有挑战性的任务,而利用深度学习以及数据特征融合等方法是解决这一难题的有效手段。本文在雷达地图融合检测网络(Radar Map fusion Detection Network,RMDN)的基础上进行了优化,主要优化方向为将雷达与地图信息在检测过程中进行重要性程度区分,具体优化内容为减少地图特征提取模块的网络深度,加入通道注意力机制,让神经网络自主学习雷达信息与地图信息特征的权重,使神经网能够更好地利用地图信息对雷达目标进行辅助检测。在此优化基础上,本文重新设计出了雷达地图融合检测网络RMDN-V2。算法的主要思想为利用卫星遥感地图来提供背景环境信息,作为雷达信号检测的辅助,通过将目标背景中的特征信息融入检测决策中,提高目标检测的准确性和鲁棒性,减少对强杂波和移动物体的干扰敏感性,改善目标检测算法在复杂环境下的表现。最后的无人机雷达实测数据实验结果表明,本文所做的针对性优化是有效的,RMDN-V2的检测性能优于原始的RMDN,同时本文算法检测性能远超传统的雷达检测算法,同时也优于目前主流的一些深度学习雷达目标检测算法。本文为解决当下低慢小目标检测的难题提出了新的算法。

融合毫米波与激光雷达的障碍物检测与跟踪方法

在园区环境中,无人车装载单一毫米波雷达或激光雷达传感器进行障碍物检测跟踪时存在探测范围有限、准确率低及稳定性差等问题。为此,提出一种基于毫米波雷达与激光雷达融合的多障碍物检测跟踪方法。利用改进欧氏聚类算法对道路内激光点云目标进行提取,基于信息筛选策略获得毫米波雷达数据中的有效目标;基于目标检测交并比与可靠性分析,对2种目标进行自适应融合,并利用跟踪门与联合概率数据关联(JPDA)算法完成前后帧数据匹配;应用多运动模型交互与无迹卡尔曼滤波实现障碍物跟踪。实车实验表明:相比单一毫米波雷达与激光雷达障碍物检测跟踪,所提方法有更好的准确性与稳定性。

Short-Term Precipitation Forecasting Rolling Update Correction Technology Based on Optimal Fusion Correction

In order to improve the availability of regional model precipitation forecast, this project intends to use the measured heavy rainfall data of dense automatic stations to carry out historical precipitation in the high resolution: the Severe Weather Automatic Nowcast System (SWAN) quantitative precipitation forecast and the High-Resolution Rapid Refresh (HRRR) regional numerical model precipitation forecast in short-term nowcasting aging. Based on the error analysis, the grid fusion technology is used to establish the measured rainfall, HRRR regional model precipitation forecast, and optical flow radar quantitative precipitation forecast (QPF) three-source fusion correction scheme, comprehensively integrate the revised forecasting effect, adjust the fusion correction parameters, establish an optimal correction plan, generate a frozen rolling update revised product based on measured dense data and short-term forecast, and put it into business operation, and perform real-time effect rolling test evaluation on the forecast product.

面向对海监视的舰船目标跟踪与航迹融合数据集

对海监视中航迹实时关联与轨迹融合任务是安全防控、区域态势监视、远程精确打击等军民应用领域的热点和难点问题,高质量的数据集对推动目标跟踪与融合技术在该领域的研究有重要作用。本研究针对目标跟踪与融合领域技术研究的数据需求以及目前公开数据集所存在的数据缺乏、场景设计针对性差、数据格式单一、数据描述不全等问题,通过仿真软件对复杂场景中多传感器多目标探测数据进行仿真,提供了一套面向典型对海监视场景(以舰船为探测对象的2D雷达与侦察传感器﹝ESM﹞)的目标跟踪与航迹融合数据集。其中仿真软件包括剧情发生器和传感器模拟器两部分,是一套成熟的目标跟踪场景仿真环境,提供逼真的探测数据模拟能力。本数据集涵盖的传感器对象包括2D雷达与侦察传感器,目标包括典型的海上舰船类别,并支持携带辐射源配置,设计了高速运动、密集交通、多传感器数据融合、特定舰船侦测和交叉定位等多种典型场景。本数据集中共包含368155条目标点迹,舰船数量为101条,时间范围15000秒,数据格式符合实际设备上报情景、探测误差模型符合实际。本数据集通过对数据误差进行正态性检验、对检测率、虚警率的场景检验以及实地调研,完成了对数据的准确性评估与数据完备性控制,可为舰船目标跟踪、轨迹融合等算法研究与验证提供基础数据。

分布式雷达信号级融合检测的数据压缩与组网架构设计

分布式探测是雷达领域热点问题,信号级融合探测比数据级融合探测能力更强,但通常需要的通信带宽较大。为此文中针对分布式非相参信号级目标融合探测,提出了基于雷达压缩数据的信号级融合目标检测方法。所提方法通过可并行化计算的信号级融合算法实现不同雷达量测值之间的去耦,通过双门限检测避免传输局部低能量的噪声信号,通过二次量化对过门限信号进行再次压缩,最终实现以点迹通信带宽逼近信号级融合检测的能力。基于4雷达组网的数值仿真结果验证表明,通信带宽缩减至原来的1/1 000,信噪比损失不超过0.7 dB,并据此探索雷达组网的体系架构设计问题,可支撑不同场合下的信号级协同探测工程应用。

多频雷达融合的顶煤结构精准探测技术

顶煤结构的准确探测是实现综放智能化开采的重要依据,然而我国煤层结构复杂且内部常含多层夹矸,易影响综放智能化开采的水平。为此,提出一种多频雷达融合的顶煤结构精准探测方法,可提高雷达天线探测深度内的浅部探测精度,同时对顶煤内部的结构信息进行解释。主要研究步骤如下:首先,对不同频率的雷达数据进行预处理和空间对齐,建立不同频率雷达数据之间的空间对应关系;其次,利用滑动窗口与小波变换加权融合方法对多频率雷达数据进行处理,根据窗口内各分段小波信号的能量占比确定各频率信号的时变权重值,并引入边缘检测算法来提高小波变换对雷达数据的融合效率,实现多频雷达数据有效融合;最后,根据煤-矸-岩的介电常数差异和电磁波传播的衰减特性,建立顶煤内部回波强度模型,并利用分层识别方法计算出顶煤内部煤-矸-岩之间的界面信息,进而反演出顶煤内部结构(包括顶煤厚度、夹矸厚度及层数、夹矸层间距等)。试验结果表明:所提出的方法能有效地将不同频率雷达数据进行融合,并能有效地探测出顶煤内部结构特征,且顶煤厚度、夹矸厚度和夹矸层间距的探测误差均小于10%。该方法有助于实现顶煤结构的精准探测,为综放智能化开采提供理论技术支撑。

基于多尺度特征融合的雷达海上目标检测方法

雷达目标检测对海上信息处理具有重要意义,目前提出的检测方法在召回率和精度上都难以满足海上检测要求。为了解决上述问题,提出基于多尺度特征的雷达海上目标检测方法。通过X波段非相参脉冲体制导航雷达采集数据,在完成预处理后检验数据集,提取雷达数据。分析杂散噪声,确定噪声范围,根据平均强度和灰度值的差值实现归一化处理。对目标进行归一化分析,融合多尺度特征实现目标选择,完成目标检测。实验结果表明,基于多尺度特征融合的雷达海上目标检测方法召回率能够在短时间内达到90%以上,精度在95%以上,能够很好地提取海上目标信息。

结合特征融合和注意力机制的SAR舰船检测算法

针对现有的合成孔径雷达目标检测算法仅利用图像底层特征进行检测存在的对小尺度舰船目标的检测率较低问题,提出一种结合特征融合和注意力机制的目标检测算法。面向SAR舰船目标检测,在原始主干网络SSD目标检测算法的基础上,引入注意力机制模块、不同层次的特征图进行特征融合、对含有小尺度目标的图像进行过采样还通过多次复制粘贴小目标实现数据增广。实验通过对SAR舰船图像数据集的大量训练和测试,结果表明本文算法能有效提升对舰船目标的综合检测性能,在公开SAR舰船目标检测数据集上平均精度可以达到94.16%。

基于双注意力机制的FMCW雷达人体行为识别

为了提高调频连续波(frequency modulated continuous wave,FMCW)雷达人体行为识别的分类精度和泛化性能,提出了一种基于双注意力机制的特征融合方法。通过设置阈值,对距离-时间谱图和微多普勒谱图中的有效频谱进行提取、拼接后送入AlexNet和VGG16神经网络来提取特征;加入空间注意力和改进的通道注意力模块,丢弃冗余信息,以增强对重要信息的关注,获取更感兴趣的特征进行特征融合分类。实验结果表明,该方法对6种日常人体行为的平均识别准确率高达97.0%。

基于特征融合的毫米波雷达行为识别算法

基于毫米波雷达的人体行为识别方法以远程非接触的方式捕获人类活动的电磁波信号并进行识别,不受烟雾和光线等的干扰,具有一定的隐私保护性,是当前的一个研究热点。针对现有的算法存在特征输入单一、模型结构复杂、泛化能力验证性不够等问题,提出了基于双分支特征融合卷积神经网络(Two Steam Features Fusion Convolutional Neural Network,2S-FCNN),使用搭载注意力机制的残差神经网络作为骨干网络,并行输入时间距离图和时间速度图,采用特征加权分数融合的方式融合特征后进行分类识别,实现了较高的识别准确率。在公开数据集和自建数据集上与现有的其他算法进行了深入的对比实验,实验结果表明所提算法在识别率和泛化能力方面都具有良好的性能。

基于多初级假设的FM广播外辐射源雷达网航迹起始算法

基于调频(FM)广播信号的外辐射源雷达有着检测概率低、虚警率高、量测精度差的特点,这给组网目标跟踪带来了极大挑战。一方面,较高的虚警率使计算量增加,组网算法的实时性受到考验;另一方面,检测概率低、方位角精度差造成冗余信息缺乏,量测关联与航迹起始变得困难。为解决这些问题,该文提出初级假设点和初级假设航迹的概念,以及基于此概念的FM广播外辐射源雷达网航迹起始算法。首先构造可能的低维关联假设,并解算出与其对应的初级假设点;随后关联不同时刻的初级假设点,形成多条可能的初级假设航迹;最后联合多场雷达网数据进行假设航迹判决,真实目标对应的初级假设航迹会得到确认,错误关联导致的虚假初级假设航迹会被剔除。相比于已有算法,所提算法有着更低的计算量,更快的航迹起始速度,仿真与实测结果均验证了所提算法的有效性。