Enhanced 3D Point Cloud Reconstruction for Light Field Microscopy Using U-Net-Based Convolutional Neural Networks

This article describes a novel approach for enhancing the three-dimensional(3D)point cloud reconstruction for light field microscopy(LFM)using U-net architecture-based fully convolutional neural network(CNN).Since the directional view of the LFM is limited,noise and artifacts make it difficult to reconstruct the exact shape of 3D point clouds.The existing methods suffer from these problems due to the self-occlusion of the model.This manuscript proposes a deep fusion learning(DL)method that combines a 3D CNN with a U-Net-based model as a feature extractor.The sub-aperture images obtained from the light field microscopy are aligned to form a light field data cube for preprocessing.A multi-stream 3D CNNs and U-net architecture are applied to obtain the depth feature fromthe directional sub-aperture LF data cube.For the enhancement of the depthmap,dual iteration-based weighted median filtering(WMF)is used to reduce surface noise and enhance the accuracy of the reconstruction.Generating a 3D point cloud involves combining two key elements:the enhanced depth map and the central view of the light field image.The proposed method is validated using synthesized Heidelberg Collaboratory for Image Processing(HCI)and real-world LFM datasets.The results are compared with different state-of-the-art methods.The structural similarity index(SSIM)gain for boxes,cotton,pillow,and pens are 0.9760,0.9806,0.9940,and 0.9907,respectively.Moreover,the discrete entropy(DE)value for LFM depth maps exhibited better performance than other existing methods.

Research on color image matching method based on feature point compensation in dark light environment

Image matching refers to the process of matching two or more images obtained at different time,different sensors or different conditions through a large number of feature points in the image.At present,image matching is widely used in target recognition and tracking,indoor positioning and navigation.Local features missing,however,often occurs in color images taken in dark light,making the extracted feature points greatly reduced in number,so as to affect image matching and even fail the target recognition.An unsharp masking(USM)based denoising model is established and a local adaptive enhancement algorithm is proposed to achieve feature point compensation by strengthening local features of the dark image in order to increase amount of image information effectively.Fast library for approximate nearest neighbors(FLANN)and random sample consensus(RANSAC)are image matching algorithms.Experimental results show that the number of effective feature points obtained by the proposed algorithm from images in dark light environment is increased,and the accuracy of image matching can be improved obviously.

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.

Temperature Effect on Light Concentration Silicon Solar Cell’s Operating Point and Conversion Efficiency

It is well known that temperature acts negatively on practically all the parameters of photovoltaic solar cells. Also, the solar cells which are subjected to particularly very high temperatures are the light concentration solar cells and are used in light concentration photovoltaic systems (CPV). In fact, the significant heating of these solar cells is due to the concentration of the solar flux which arrives on them. Light concentration solar cells appear as solar cells under strong influences of heating and temperature. It is therefore necessary to take into account temperature effect on light concentration solar cells performances in order to obtain realistic results. This one-dimensional study of a crystalline silicon solar cell under light concentration takes into account electrons concentration gradient electric field in the determination of the continuity equation of minority carriers in the base. To determine excess minority carrier’s density, the effects of temperature on the diffusion and mobility of electrons and holes, on the intrinsic concentration of electrons, on carrier’s generation rate as well as on width of band gap have also been taken into account. The results show that an increase of temperature improves diffusion parameters and leads to an increase of the short-circuit photocurrent density. However, an increase of temperature leads to a significant decrease in open-circuit photovoltage, maximum electric power and conversion efficiency. The results also show that the operating point and the maximum power point (MPP) moves to the open circuit when the cell temperature increases.

Synthesis of Polyfluorene-Polytriarylamine Block Copolymer with Emitting Part at Junction Point for Light Emitting Applications

A block copolymer consisting of polyfluorene (PF) and polytriarylamine (PTAA) functionalized with green emitting phenoxazine moiety at the junction point of two blocks was designed and prepared for electroluminescent application. PF homopolymer was synthesized by Suzuki coupling polymerization, and was reacted with brominated phenoxazine. In the presence of the resulting PF functionalized with phenoxazine, C-N coupling polymerization of 4-(4’-bromophenyl)-4’’-butyldiphenylamine was carried out to afford a triblock copolymer, PTAA-phenoxazine-PF-phenoxazine-PTAA (PF-Ph-PTAA). Two types of random copolymers were also synthesized with fluorene and phenoxazine (PF2) by Suzuki coupling polymerization for comparison. All the polymers were soluble in common organic solvents and readily formed thin films by a solution processing. Prepared polymers exhibited similar UV absorption and PL emission in chloroform solutions. In a film state, the existence of phenoxazine unit drastically changed PL spectra. Although the content of phenoxazine unit in PF-Ph-PTAA was relatively high (13 mol%), it showed similar PL spectrum to that of PF2(phenoxazine content, 0.2 mol%) indicating that phenoxazine unit is isolated in single polymer chain nevertheless the high content. EL device based on PF-Ph-PTAA showed green-emission, suggesting that emission sites predominantly located in the vicinity of phenoxazine moiety because of its shallow HOMO level.

基于线结构光扫描的工件高精度三维测量方法

为了提高工业中对复杂轮廓工件的测量精度和效率,设计了一套高精度非接触三维测量系统,并提出了一种基于线结构光扫描的工件轮廓三维测量方法。首先,利用高精度相机和三轴移动平台采集线结构光图像。然后,通过基于差分区间的灰度质心算法,精确而高效地提取出线结构光中心线,并生成原始点云模型。接着,对采集到的点云数据进行必要的点云滤波和精简预处理。最后,将预处理后的点云数据与CAD模型精确配准,进行工件表面轮廓的测量与误差评定。实验结果表明:测量工件轮廓高度的绝对误差小于0.07 mm,相对误差小于0.5%。所提出的三维测量系统及方法测量误差较低,能够实现工件的高精度三维测量,具有一定的工业应用价值。

松辽盆地白垩系青山口组一段页岩生、排烃组分特征及页岩油相态演化

松辽盆地白垩系青山口组一段(青一段)页岩有机质热演化程度跨度大、烃类流动性差异强。页岩油相态分析预测是页岩油勘探开发的重要难题。用低成熟页岩样品开展封闭体系及半封闭体系有机质热解实验,根据生、排烃组分特征对滞留烃的轻烃散失进行补偿校正,研究了页岩油组分演化特征。结合中央坳陷区主要生油凹陷典型井埋藏史、热演化史,研究了页岩油相态演化规律,提出了轻质页岩油勘探有利区和开发压力保护条件。研究结果表明:地质条件下随着有机质成熟度的升高,页岩油组分中轻质组分比例不断增加、气体逐渐增多,相包络线从高露点温度、低泡点压力依次向低露点温度、高泡点压力演化。齐家-古龙凹陷青一段页岩油在嫩江组中期油藏向挥发油油藏转化,长岭凹陷青一段页岩油从嫩江组末期开始油藏向挥发油油藏转化,三肇凹陷青一段页岩油则始终为黑油油藏。无论是黑油油藏还是挥发油油藏,均为单一液相。松辽盆地中央坳陷区青一段页岩油挥发油油藏主要分布在齐家-古龙凹陷中心和长岭凹陷北部有机质成熟度(镜质体反射率Ro)为1.3%~1.6%、地层压力为12.2~22.4 MPa的区域。

基于多点结构光扫描的工件定位方法

在自动化生产线工业机器人抓取工件作业中,工件定位方法直接影响作业质量、效率及系统成本。传统基于线结构光的工件定位方式通常存在专用性强、成本高等特点,难以在劳动密集型产业中推广应用。针对这一问题,利用KD-tree ICP算法,提出一种基于多点结构光扫描的工业机器人抓取工件定位方法。首先,利用模型点云和多点结构光原始点云进行粗配准;其次,提取待定位工件点云特征点,并拟合出工件边界;最后,利用模型边界点云和拟合出工件边界点云进行精配准。试验结果表明,该方法具有较高的定位精度及识别效率,满足工件抓取要求。

八髎穴齐刺联合红外偏振光治疗急性非特异性下腰痛临床研究

目的:观察八髎穴齐刺联合红外偏振光照射治疗急性非特异性下腰痛的临床疗效。方法:60例急性非特异性下腰痛患者随机分为观察组和对照组,每组各30例。两组患者均使用红外偏振光采用振荡模式照射针刺部位,1次/d;对照组采用常规针刺治疗,观察组采用八髎穴齐刺法针刺治疗,两组均治疗5 d。观察两组的临床疗效,比较两组治疗前后采用视觉模拟评分法(VAS)评价腰腿部疼痛程度,采用Oswestry功能障碍指数(ODI)评价腰椎功能,采用指地距离(FFD)评价腰部主动前屈受限程度,采用健康状况调查问卷SF-36在治疗前后评价患者的生活质量。结果:与治疗前比较,两组VAS评分、ODI评分和FFD评分均明显下降,差异有统计学意义(P<0.05),且观察组评分降低值均显著大于对照组,差异有统计学意义(P<0.05);与治疗前比较,两组SF-36评分明显提高,差异有统计学意义(P<0.05),且观察组评分明显高于对照组,差异有统计学意义(P<0.05)。观察组总有效率为96.67%(29/30),显著高于对照组的80.00%(24/30),两组差异有统计学意义(P<0.05)。两组均未出现明显不良反应。结论:以八髎穴齐刺针刺法联合红外偏振光照射治疗急性非特异性下腰痛疗效显著,在缓解患者疼痛及改善腰部前屈活动方面效果优于常规针刺方式,改善患者生活质量早期疗效明显。

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。

不同物料流对皮带机转载点的振动冲击分析与研究

选煤厂带式输送机转载点处两皮带有一定高度差,受上端面煤块大小、含水量等因素影响,会对皮带机造成不同程度的振动冲击,从而影响皮带机带身及托辊的使用寿命。为探究物料流对转载点振动冲击的影响,结合现场调研及相关理论,推出落料冲击的影响因素主要为物料流粒度级别和含水量。然后利用光纤振动传感器、数据采集卡等器材和Labview测试系统进行现场试验,将落料口下方带式输送机在不同物料流冲击下的振动信号进行采集和处理,试验结果表明,不同粒度物料流对转载点振动冲击不同,小粒度物料流对转载点的振动波形峰值为大粒度物料流的20%,自功率谱波形峰值为0.625%;不同含水量对转载点振动冲击不同,含水量少的物料流对转载点的振动波形峰值为含水量多物料流的60%,自功率谱波形峰值降低为45%。研究结果可为降低皮带机转载点振动冲击提供合理的方法。

光笔视觉测量系统的精确测量研究

光笔视觉测量系统是以光笔为接触式辅助测量工具的一种便携式坐标测量系统,具有便携性好、测量范围大、精度高等优点。但在接触式测量过程中,记录的是测头中心坐标,需要对测头进行半径补偿。结合光笔式测量系统,提出一种针对散乱点云进行半径补偿的可行性方法。利用点云的网格化处理,寻找散乱点云中点的拓扑关系,得到局部点云的矩形拓扑网格。使用拓扑网格点进行NURBS曲面插值拟合,得到网格中心点的法向量。实验表明,该方法求得的法向量误差角度在0.5°左右,测头半径为2.5mm情况下,测量误差在0.030mm以下。

基于结构光的铆钉凹凸量双目视觉检测方法

为了弥补飞机铆钉凹凸量的传统检测方式在精度、效率及稳定性方面的不足,提出了一种基于结构光的铆钉凹凸量双目视觉检测方法。首先通过工业投影仪将结构光投射到铆接表面,由双目相机采集投影图像。然后根据铆钉边缘特征提取出铆接区域,并采用改进的格雷码解相位方法计算铆接区域表面的相位信息。根据相位信息匹配特征点,利用视差原理计算出点云。最后通过点云数据处理,计算出铆钉的凹凸量。制作标准件并完成了凹凸量测量试验,测量误差在±20μm以内,重复测量标准差小于3μm,单个铆钉测量用时约2.2 s,能够满足现场测量精度和效率要求。

混凝土粗糙面几何特征采集的压饼拓模法试验研究

提出适用于粗糙面几何特征采集的压饼拓模法,并介绍了压饼仪构造及使用方法,使用此方法进行了5种不同预置时长的超轻黏土物理性能和拓印精度试验。结果表明:当黏土开封预置2h左右时,可获得最优拓模精度;塑性沉陷值比含水率更适宜作为界面粗糙度拓模精度控制的黏土物理性质评价指标,当黏土塑性沉陷值不小于1.5mm时,对应点平均误差在0.3mm以内;回弹值对拓模精度影响不大。同时采取增大按压压力、二次按揉、附加刚性背板等措施进行拓模精度影响研究。结果表明:按压压力不应小于50N;二次按揉可提高模印精度;采用刚开封黏土时,附加刚性背板措施可实现高精度即时脱模,其对应点平均误差在0.12mm以内。

用分光计测三棱镜折射率光路图的MATLAB动画演示

建立了三棱镜光路图的数学模型,应用MATLAB绘制光路图,检验了模型的正确性.随着三棱镜的旋转,直观地演示了分光计中光路图和偏向角的变化过程,指出了最小偏向角.

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.

脉搏血氧仪校准方法的研究

本方法适用于光电式的脉搏血氧仪(计)、脉搏血氧饱和度监护仪以及多参数监护仪中脉搏血氧监护部分的校准。在脉搏血氧仪质量控制方面,国家并没有专门的计量标准,各地依据当地的实际情况出台了地方标准,但是均没有关于光吸收比率拟合曲线误差的测量。本文主要介绍了脉搏血氧仪的组成和用途,针对目前临床在用设备,研究了脉搏血氧仪的校准方法,增加了光吸收比率拟合曲线示值误差项目,并对该校准方法进行了验证实验。此研究的目的是为开展相应的质量控制工作提供技术依据,希望通过质量控制确保脉搏血氧仪设备良好运行,有效保障医疗安全。

融合视觉信息感知与虚拟现实的康复辅助系统

当前人工智能技术在康复领域大多用于严重运动障碍群体,而中国现阶段人口老龄化加剧,会导致轻型运动障碍人群的大量增加,亟需更加智能化的运动训练与康复系统.针对轻型运动损伤患者以及普通老年群体,本文提出了一种基于视觉的运动信号感知与虚拟现实的康复辅助系统,该系统通过实时推断人体骨骼模型,利用虚拟现实游戏与骨骼点运动进行交互,实现引导康复动作,最终对康复动作进行评价并给出交互界面提示.本文招募受试者参加实验,在闭环训练中受试者通过本文系统在虚拟康复游戏的引导反馈下复现标准康复动作,对比分析受试者实验结果,验证了所提出方法的有效性与可行性.

植物特征光谱测试系统研制及应用

以植物光合作用的基本原理和一种植物特征光谱实验方法的发明专利为依据,介绍以双驼峰光谱光源为基础,研制出能够产生覆盖光合有效辐射范围的多种单色光发生器,采用多种单色光发生器和光合作用测试仪组合构建植物特征光谱测试系统。阐述如何通过植物特征光谱测试系统获取植物单色光光合响应曲线、对应的饱和点曲线和补偿点曲线,并通过具体案例介绍该系统应用,为植物光照提供技术指导。

超低霜点湿度发生器研制

基于双温双压法原理研制了一台超低霜点湿度发生器,发生霜点范围达到-110~-20℃。优化设计了饱和器和恒温设备等核心部件,并采用“蒸发”和“冷凝”两种模式验证了饱和器的饱和效率。在不同饱和温度和饱和压力条件下,分别采用冷镜式精密露点仪和光腔衰荡微量水分仪,与发生器进行了比对测试。试验结果表明:当霜点温度为-90℃时,露点仪与发生器偏差为0.02℃。当饱和压力为1 MPa、饱和温度为-99.60℃时,光腔衰荡微量水分仪与发生器的霜点温度偏差为0.04℃。对影响发生器测量结果的不确定度因素进行了不确定度评定。发生器在霜点温度-110℃、-90℃和-20℃时,扩展不确定度分别为0.40℃、0.20℃和0.19℃,k=2。