Volumetric assessment of hepatic grafts using a light detection and ranging system for 3D scanning:Preliminary data

BACKGROUND Liver transplantation has evolved into a safe life-saving operation and remains the golden standard in the treatment of end stage liver disease.The main limiting factor in the application of liver transplantation is graft shortage.Many strategies have been developed in order to alleviate graft shortage,such as living donor partial liver transplantation and split liver transplantation for adult and pediatric patients.In these strategies,liver volume assessment is of paramount importance,as size mismatch can have severe consequences in the success of liver transplantation.AIM To evaluate the safety,feasibility,and accuracy of light detection and ranging(LIDAR)3D photography in the prediction of whole liver graft volume and mass.METHODS Seven liver grafts procured for orthotopic liver transplantation from brain deceased donors were prospectively measured with an LIDAR handheld camera and their mass was calculated and compared to their actual weight.RESULTS The mean error of all measurements was 17.03 g(range 3.56-59.33 g).Statistical analysis of the data yielded a Pearson correlation coefficient index of 0.9968,indicating a strong correlation between the values and a Student’s t-test P value of 0.26.Mean accuracy of the measurements was calculated at 97.88%.CONCLUSION Our preliminary data indicate that LIDAR scanning of liver grafts is a safe,cost-effective,and feasible method of ex vivo determination of whole liver volume and mass.More data are needed to determine the precision and accuracy of this method.

Predicting the provisioning potential of forest ecosystem services using airborne laser scanning data and forest resource maps

Background: Remote sensing-based mapping of forest Ecosystem Service(ES) indicators has become increasingly popular. The resulting maps may enable to spatially assess the provisioning potential of ESs and prioritize the land use in subsequent decision analyses. However, the mapping is often based on readily available data, such as land cover maps and other publicly available databases, and ignoring the related uncertainties.Methods: This study tested the potential to improve the robustness of the decisions by means of local model fitting and uncertainty analysis. The quality of forest land use prioritization was evaluated under two different decision support models: either using the developed models deterministically or in corporation with the uncertainties of the models.Results: Prediction models based on Airborne Laser Scanning(ALS) data explained the variation in proxies of the suitability of forest plots for maintaining biodiversity, producing timber, storing carbon, or providing recreational uses(berry picking and visual amenity) with RMSEs of 15%–30%, depending on the ES. The RMSEs of the ALS-based predictions were 47%–97%of those derived from forest resource maps with a similar resolution. Due to applying a similar field calibration step on both of the data sources, the difference can be attributed to the better ability of ALS to explain the variation in the ES proxies.Conclusions: Despite the different accuracies, proxy values predicted by both the data sources could be used for a pixel-based prioritization of land use at a resolution of 250 m~2, i.e., in a considerably more detailed scale than required by current operational forest management. The uncertainty analysis indicated that maps of the ES provisioning potential should be prepared separately based on expected and extreme outcomes of the ES proxy models to fully describe the production possibilities of the landscape under the uncertainties in the models.

Rail-Pillar Net:A 3D Detection Network for Railway Foreign Object Based on LiDAR

Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,we propose Rail-PillarNet,a three-dimensional(3D)LIDAR(Light Detection and Ranging)railway foreign object detection method based on the improvement of PointPillars.Firstly,the parallel attention pillar encoder(PAPE)is designed to fully extract the features of the pillars and alleviate the problem of local fine-grained information loss in PointPillars pillars encoder.Secondly,a fine backbone network is designed to improve the feature extraction capability of the network by combining the coding characteristics of LIDAR point cloud feature and residual structure.Finally,the initial weight parameters of the model were optimised by the transfer learning training method to further improve accuracy.The experimental results on the OSDaR23 dataset show that the average accuracy of Rail-PillarNet reaches 58.51%,which is higher than most mainstream models,and the number of parameters is 5.49 M.Compared with PointPillars,the accuracy of each target is improved by 10.94%,3.53%,16.96%and 19.90%,respectively,and the number of parameters only increases by 0.64M,which achieves a balance between the number of parameters and accuracy.

Development of vehicle-recognition method on water surfaces using LiDAR data:SPD^(2)(spherically stratified point projection with diameter and distance)

Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces.For monitoring natural environments and conducting security activities within a certain range using a surface vehicle,the swarm robot system is more efficient than the operation of a single object as the former can reduce cost and save time.It is necessary to detect adjacent surface obstacles robustly to operate a cluster of unmanned surface vehicles.For this purpose,a LiDAR(light detection and ranging)sensor is used as it can simultaneously obtain 3D information for all directions,relatively robustly and accurately,irrespective of the surrounding environmental conditions.Although the GPS(global-positioning-system)error range exists,obtaining measurements of the surface-vessel position can still ensure stability during platoon maneuvering.In this study,a three-layer convolutional neural network is applied to classify types of surface vehicles.The aim of this approach is to redefine the sparse 3D point cloud data as 2D image data with a connotative meaning and subsequently utilize this transformed data for object classification purposes.Hence,we have proposed a descriptor that converts the 3D point cloud data into 2D image data.To use this descriptor effectively,it is necessary to perform a clustering operation that separates the point clouds for each object.We developed voxel-based clustering for the point cloud clustering.Furthermore,using the descriptor,3D point cloud data can be converted into a 2D feature image,and the converted 2D image is provided as an input value to the network.We intend to verify the validity of the proposed 3D point cloud feature descriptor by using experimental data in the simulator.Furthermore,we explore the feasibility of real-time object classification within this framework.

Multi-Scale Feature Extraction for Joint Classification of Hyperspectral and LiDAR Data

With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.

Intelligent Risk-Identification Algorithm with Vision and 3D LiDAR Patterns at Damaged Buildings

Existingfirefighting robots are focused on simple storage orfire sup-pression outside buildings rather than detection or recognition.Utilizing a large number of robots using expensive equipment is challenging.This study aims to increase the efficiency of search and rescue operations and the safety offirefigh-ters by detecting and identifying the disaster site by recognizing collapsed areas,obstacles,and rescuers on-site.A fusion algorithm combining a camera and three-dimension light detection and ranging(3D LiDAR)is proposed to detect and loca-lize the interiors of disaster sites.The algorithm detects obstacles by analyzingfloor segmentation and edge patterns using a mask regional convolutional neural network(mask R-CNN)features model based on the visual data collected from a parallelly connected camera and 3D LiDAR.People as objects are detected using you only look once version 4(YOLOv4)in the image data to localize persons requiring rescue.The point cloud data based on 3D LiDAR cluster the objects using the density-based spatial clustering of applications with noise(DBSCAN)clustering algorithm and estimate the distance to the actual object using the center point of the clustering result.The proposed artificial intelligence(AI)algorithm was verified based on individual sensors using a sensor-mounted robot in an actual building to detectfloor surfaces,atypical obstacles,and persons requiring rescue.Accordingly,the fused AI algorithm was comparatively verified.

基于Transformer和动态3D卷积的多源遥感图像分类

多源遥感数据具有互补性和协同性,近年来,基于深度学习的方法已经在多源遥感图像分类中取得了一定进展,但当前方法仍面临关键难题,如多源遥感图像特征表达不一致,融合困难,基于静态推理范式的神经网络缺乏对不同类别地物的适应性。为解决上述问题,提出了基于跨模态Transformer和多尺度动态3D卷积的多源遥感图像分类模型。为提高多源特征表达的一致性,设计了基于Transformer的融合模块,借助其强大的注意力建模能力挖掘高光谱和LiDAR数据特征之间的相互作用;为提高特征提取方法对不同地物类别的适应性,设计了多尺度动态3D卷积模块,将输入特征的多尺度信息融入卷积核的调制,提高卷积操作对不同地物的适应性。采用多源遥感数据集Houston和Trento对所提方法进行验证,实验结果表明:所提方法在Houston和Trento数据集上总体准确率分别达到94.60%和98.21%,相比MGA-MFN等主流方法,总体准确率分别至少提升0.97%和0.25%,验证了所提方法可有效提升多源遥感图像分类的准确率。

基于点云特征的改进RANSAC地面分割算法

针对室外复杂场景下,轻量级和地面优化的激光雷达里程计与测图(LeGO-LOAM)算法由于地面分割不精确而导致算法定位精度降低的问题,提出一种基于改进随机一致性采样(RANSAC)的多线程地面分割算法:相较于传统RANSAC算法,该算法舍弃从全部原始数据中随机选取种子点拟合地面模型的迭代方式,首先利用点云高程、曲率等点特征信息挑选出所有小于高程、曲率等阈值的种子点以构建种子点集合,并根据种子点集合中的种子点数量判断是否需要多线程处理;然后根据判断结果从种子点集合中选择种子点子集进行地面拟合;最后比较各地面模型所包含的点云数量以获得最优地面模型参数以及地面点云集;地面分割精度的提高有效地降低了LeGO-LOAM算法的定位误差。实验结果表明,在室外复杂场景下所提出的地面分割算法分割效果更好,杂点更少;相较于原LeGO-LOAM算法,改进算法的定位误差降低至3.73 m,平面均方根误差降低了20.8%。

基于深度学习的机载点云屋顶平面提取算法

为了准确提取不同类型建筑物屋顶点云的各个平面,采用度量学习的方式,将每个平面视为单独的实例,为每个平面上的点学习单独的高维深度特征。利用所提取的高维深度特征对平面点进行初步的聚类,通过简单的欧氏距离和特征空间距离进行综合度量将未聚类的点分配至各个平面;所提出的方法分别在合成数据集和公开的机载点云建筑物屋顶数据集RoofN3D上进行了训练和测试。结果表明,在合成数据集上,所提取的建筑物平面的准确率、召回率和F_(1)分数分别为0.990、0.998和0.994;在机载点云数据集RoofN3D上,所提取的建筑物平面的准确率、召回率和F_(1)分数分别为0.945、0.971和0.957。该方法不仅可以准确有效地提取出不同建筑物屋顶平面,且平面边缘非常准确,还可以准确区分建筑物屋顶平面内容和非平面内容,为建筑物3维建模提供重要帮助。

基于不同数据源的数字孪生小流域底板模型精度检验

为解决小流域综合治理规划设计中基础地形数据获取困难等问题,基于合成孔径雷达卫星遥感影像、倾斜摄影影像、光探测测距影像等3种主流遥感数据源,分别建立栖龙湾小流域数字孪生底板模型,进而提取主沟道纵断面、2块梯田样地边界、10个林地样区的郁闭度,与人工解译和实测结果对比进行精度检验,结果表明:以光探测测距影像为数据源的提取精度最高,以倾斜摄影影像为数据源的提取精度次之,以孔径雷达卫星遥感影像为数据源的提取精度最低。鉴于3种数据源小流域底板模型各有优缺点,可根据实际工作需要进行多源数据融合,以改善数字孪生技术在小流域综合治理规划设计中的应用效果。在栖龙湾小流域内选择石坎梯田地块进行合成孔径雷达卫星遥感影像与倾斜摄影影像数据融合、选择科普展览馆进行倾斜摄影影像与光探测测距影像数据融合,均取得良好的效果。

激光雷达超远距离测距技术

针对超远距离多功能交会对接激光雷达需求,开展基于非相干测距技术的远距离激光测距通信一体化模块研制,在不改变原有雷达主机架构和信号体制下,实现对远距离高动态合作目标的通信测距功能。推导出测距原理,对动态、时钟性能等因素产生的测距误差进行理论分析,给出速度、时钟性能对测距误差的影响公式。得出在高动态环境下,相对速度与测距周期、双方钟差共同作用产生测距系统误差,且速度越大系统误差越大的结论。设计测距通信一体化演示验证平台,完成测距通信算法的软硬件评估,实测结果与理论推导相符,为后续新体制激光雷达原理样机研制奠定技术基础。

基于点云稀疏空间特征聚合激励的单阶段3D目标检测模型

针对目前基于点云的3D目标检测中单阶段体素法存在感受野固定、特征尺度单一,导致模型对点云特征学习不够充分、模型检测效果存在瓶颈等问题,提出了一种可端对端训练的基于体素的单阶段3D目标检测模型.首先,利用多尺度稀疏空间特征聚合模块,聚合点云在不同稀疏空间尺度上的特征,使特征充分保留点云的空间信息;然后,对特征进行分层激励,通过多尺度感受野对特征进行分层学习,强化特征的表达能力,降低噪声信息对检测结果的影响;最后,将特征输入检测头进行候选框的分类和回归.在公开的自动驾驶数据集KITTI上与主流单阶段3D目标检测模型进行了对比实验,包含对3类目标共9个的难度等级目标的检测.所提模型在其中5个等级中的平均准确率有明显提升,尤其对点云稀疏的目标,表现出较好的检测效果.实验结果表明,所提模型能够充分提取点云空间信息并有效地学习点云多尺度特征.

城市森林结构多样性预测冠下地面温度的潜力研究

城市森林冠层具有调控城市森林微气候的能力,但现有研究尚未阐明冠层结构对冠下地面温度的影响及其预测潜力。文章基于无人机机载激光雷达(UAV-LiDAR)提取哈尔滨林业示范基地的城市森林冠层结构多样性特征指标,探究单一结构多样性特征对冠下地面温度的影响,以及结构多样性多因子组合对温度的预测潜力。结果表明:1)城市森林结构多样性的8个特征因子与冠下地面温度呈显著相关关系(P<0.05),其中深间隙(DG)、深间隙分数(DGF)、覆盖分数(CF)、间隙分数分布(GFP)表征了结构多样性的覆盖/开放度特征;冠层高度标准差(H_(std))、冠层高度最大值(H_(max))、95%分位点高度(ZQ_(95))表征了高度特征;垂直复杂指数(VCI)表征了异质性特征。2)城市森林冠层结构多样性的覆盖/开放度特征对冠下地面温度的响应更强(R^(2)为0.15~0.5),强于高度指标(R^(2)为0.14~0.19)以及异质性指标(R^(2)=0.14)。3)结合高度指标、覆盖/开放度指标以及异质性指标的多因子预测模型2(R^(2)=0.61,RMSE=0.51,MSE=0.26,AIC=62.74),对于冠下地面温度的预测性能更优。研究明晰了城市森林结构多样性的多因子变量及其特征组合预测冠下地面温度的潜力,为城市森林冠层结构调控内部小气候环境研究提供了科学参考。

激光雷达与相机联合标定进展研究

针对激光雷达与相机标定精度会极大地影响定位初始化,融合定位算法对标定参数的准确性非常敏感,会严重降低融合定位算法的性能和可靠性等问题,提出一种激光雷达与相机联合标定分类方法:论述激光雷达与相机联合标定领域的最新的研究进展;重点分析和总结基于特征的标定方法、基于运动的标定方法、基于互信息的标定方法和基于深度学习的标定方法的突出研究成果;总结出4种标定方法的开源代码工具集,并对这4种标定方法的特点、标定精度和自动化程度进行分析比较;最后,展望激光雷达与相机联合标定研究的发展趋势。

高动态范围条纹结构光在机检测技术及应用进展

条纹结构光技术是近年来发展迅速的非接触式测量方法,为机械加工在机检测提供了新的解决方案。由于加工环境光线复杂且金属零件本身具有高反光的特性,造成结构光在机检测的精度降低。将高动态范围(High Dynamic Range,HDR)技术应用于结构光检测中,可抑制高反光的影响,实现金属零件在复杂场景的测量。本文首先介绍了结构光测量原理,总结出HDR结构光在机检测面临的难点;其次,对HDR结构光技术进行了全面综述,以机械加工在机检测为背景,对基于硬件设备的HDR技术和基于条纹算法的HDR技术分别进行了归纳分析;然后,根据在机检测的条件需求,对各类技术进行总结,并比较不同方法的优缺点和在机检测的适用性;最后,结合近年来先进制造技术和精密测量的研究热点,对潜在应用进行分析,提出技术展望。

集成多源遥感与极限梯度提升的竹林地上生物量估测

森林生物量遥感精准估测是评估森林碳汇潜力的重要依据,通过对比机载激光雷达(LiDAR)与机载多光谱数据在竹林地上生物量(AGB)估测中的差异,探索不同光学与激光点云数据协同估测森林AGB的潜力。以福建特色竹种黄甜竹(Acidosasa edulis)人工林为研究对象,同步采集无人机载多光谱影像和LiDAR数据,提取并优选单一LiDAR的优选特征集、单一多光谱影像数据优选特征集、联合机载LiDAR和多光谱影像的优选特征集,采用多元线性回归模型(MLR)和支持向量机(SVM)、随机森林(RF)、极限梯度提升(XGBoost)拟合竹林AGB估测模型。结果表明:(1)LiDAR数据的高度特征和密度特征是竹林AGB估测的重要特征,基于多源异构数据的特征集对竹林AGB估测的效果优于单一的遥感数据;(2)竹林AGB估测中,基于机器学习算法的非参数模型优于多元线性回归模型;集成XGBoost与多源特征集的黄甜竹AGB估测模型最优,R^(2)达0.64,Erms为9.90 t·hm^(-2)。竹林具有特殊冠层结构,应用LiDAR数据源能够有效获取林分垂直结构信息,联合多源异构数据能提高生物量估测模型精度。

无人机激光雷达技术和倾斜摄影技术在地形测绘中的应用

针对地形落差大、植被茂密、通视条件差的区域,本文提出了一种综合利用无人机激光雷达(LiDAR)技术与倾斜摄影技术完成测图的方法。利用激光雷达穿透性强,高密度、高精度获取数据的优势,可准确获取地面高程信息;利用倾斜摄影建模技术可准确地获取地物的平面位置信息,实现比较直观的可视化效果,可快速进行矢量数据采集工作。通过两种技术手段的结合,可实现高精度地形图的生产。本文从实际出发,以黑龙江某项目为例,论证了此方法能够完全满足1∶500数字地形图的精度要求。

林区机载LiDAR点云的多分辨率层次布料模拟滤波

针对现有机载LiDAR(light detection and ranging)点云滤波方法在地形起伏剧烈的林区适用性不足的问题,提出一种多分辨率层次布料模拟滤波方法。首先,通过多尺度形态学开运算选择大量种子地面点;然后,基于种子地面点,使用布料模拟法由低至高逐层构建参考地形,以快速获取高分辨率参考地形;最后,基于点至参考地形的高差区分地面点和非地面点。利用国际摄影测量和遥感学会提供的数据集和参考方法,评估该方法性能。利用在中国、美国多个代表性林区的点云数据,评估该方法的可推广性。结果表明,该方法的Kappa系数和运行时间是83.72%和34.11 s,精度和效率较经典布料模拟滤波方法提高10.49%和52.17%。相比8种参考方法,该方法能够获得更高精度,并且具有稳定的可推广性。

基于多尺度注意力机制的实时激光雷达点云语义的分割

为既能提高分割精度,又能克服车载计算资源局限,提出一种面向移动机器人平台的车载实时点云语义分割方法,并进行了综合实验。该方法采用基于投影的激光雷达语义分割方法,将三维点云投影到球面图像,并结合二维卷积进行分割。引入多头注意力机制(MHSA),实现轻量级语义分割模型,以一种全新的方式,将一种深度学习模型架构Transformer映射到卷积。将Transformer的MHSA迁移至卷积,以形成多尺度自注意力机制(MSSA)。结果表明:与当前主流方法CENet、FIDNet、PolarNet相比,本方法在NVIDIA JETSON AGX Xavier计算平台上保持了较高的分割精度(平均交并比为63.9%)及较高的检测速率(41帧/s),从而证明了其对移动机器人平台的适用性。

低空复杂风场全天候雷达精细探测技术

低空复杂风场通常指距离地面高度600 m以下,局地风速、风向快速变化的风场.其全天候大范围精细探测是雷达科学、气象学等领域的长期难题.低空复杂风场的全天候雷达精细探测涉及传感器设计、三维风场反演和全天候融合等关键技术.本文从激光雷达探测、微波雷达探测、全天候融合及特征危害提取等方面对风场探测的技术内涵及研究现状进行了梳理,并分析了发展趋势,为低空复杂风场全天候精细探测技术发展与应用提供参考.