检索结果-南通市图书馆

在线全文

学校读者我要写书评

暂无评论

低重叠率人体点云拼接方法研究

应用激光 2024年第3期44卷 204-213页

作者：翟漪璇宋丽梅贺瑾胜朱新军天津工业大学天津市电气装备智能控制重点实验室天津300387

为解决点云重叠率低、特征缺失等造成的拼接错位严重的问题,提出一种基于点云复合特征的法向约束点到面ICP拼接方法。首先采集被测物的多视角激光点云并预处理;结合待拼接点云数据的特点,分别提取内部形状描述子和法线对齐径向特征点,... 详细信息

为解决点云重叠率低、特征缺失等造成的拼接错位严重的问题,提出一种基于点云复合特征的法向约束点到面ICP拼接方法。首先采集被测物的多视角激光点云并预处理;结合待拼接点云数据的特点,分别提取内部形状描述子和法线对齐径向特征点,并补充提取显著性约束特征点;将提取的特征融合,得到各视角点云的复合特征点集,以Kd-Tree搜索待拼接点云的邻域内公共复合特征为拼接步骤的输入;基于公共复合特征,使用改进的法向约束点到面ICP方法实现低重叠点云的拼接。试验表明,本文所提出的特征提取方法能有效选取特征点,简化点云约为原数据量的0.25%;法向约束点到面ICP方法能有效拼接低重叠的激光点云,与ICP、FPFH等方法相比具有更高的精度,人体点云拼接误差仅0.073 m,综合表现更好。

关键词：点云拼接特征提取低重叠率多视角

3D velocity field reconstruction of gas-liquid two-phase flow based on space-time multi-scale binocular-PIV technology

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2022年第10期18卷 613-617页

作者： WANG Hongyi DOU Gongcheng ZHANG Hao zhu xinjun SONG Limei Tianjin Key Laboratory of Intelligent Control of Electrical Equipment School of Artificial IntelligenceTiangong UniversityTianjin300387China Tianjin Key Laboratory of Intelligent Control of Electrical Equipment School of Control Science and EngineeringTiangong UniversityTianjin300387China

For particle image velocimetry(PIV) technique, the two-dimensional(2D) PIV by one camera can only obtain 2D velocity field, while three-dimensional(3D) PIV based on tomography by three or four cameras is always complex and expensive. In this work, a binocular-PIV technology based on two cameras was proposed to reconstruct the 3D velocity field of gas-liquid two-phase flow, which is a combination of the binocular stereo vision and cross-correlation based on fast Fourier transform(CC-FFT). The depth of particle was calculated by binocular stereo vision on space scale, and the plane displacement of particles was acquired by CC-FFT on time scale. Experimental results have proved the effectiveness of the proposed method in 3D reconstruction of velocity field for gas-liquid two-phase flow.

关键词： flow flow phase

在线全文

学校读者我要写书评

暂无评论

基于区域立体匹配的单频条纹结构光三维测量

激光与光电子学进展 2024年第10期61卷 137-145页

作者：朱新军孙瑞群侯林鹏赵海川宋丽梅王红一天津工业大学人工智能学院天津300387 天津工业大学控制科学与工程学院天津300387

为克服传统质量导向相位展开方法无法正确展开多孤立物体的局限性,提出一种基于区域分割的立体质量导向相位展开方法。该方法将包裹相位分割为多个区域,并为每个孤立区域通过立体匹配算法确立左右相机多视图相位展开初始点,通过质量导... 详细信息

为克服传统质量导向相位展开方法无法正确展开多孤立物体的局限性,提出一种基于区域分割的立体质量导向相位展开方法。该方法将包裹相位分割为多个区域,并为每个孤立区域通过立体匹配算法确立左右相机多视图相位展开初始点,通过质量导向相位展开算法实现多视图孤立物体相位展开。进一步提出了基于区域双目立体展开相位匹配的单频条纹结构光三维(3D)测量,实现了单个频率包裹相位下的多孤立物体3D重建。实验结果表明,所提方法可以实现多孤立物体运动状态的3D重建,在四步相移和单幅条纹图条件下重建标准球的直径平均绝对值偏差分别为0.0135 mm和0.0347 mm。

关键词：三维重建质量导向结构光立体匹配相位展开

Wavelet based deep learning for depth estimation from single fringe pattern of fringe projection profilometry

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2022年第11期18卷 699-704页

作者： zhu xinjun HAN Zhiqiang SONG Limei WANG Hongyi WU Zhichao School of Artificial Intelligence Tiangong UniversityTianjin 300387China

Depth estimation from single fringe pattern is a fundamental task in the field of fringe projection three-dimensional(3D) measurement. Deep learning based on a convolutional neural network(CNN) has attracted more and more attention in fringe projection profilometry(FPP). However, most of the studies focus on complex network architecture to improve the accuracy of depth estimation with deeper and wider network architecture, which takes greater computational and lower speed. In this letter, we propose a simple method to combine wavelet transform and deep learning method for depth estimation from the single fringe pattern. Specially, the fringe pattern is decomposed into low-frequency and high-frequency details by the two-dimensional(2D) wavelet transform, which are used in the CNN network. Experiment results demonstrate that the wavelet-based deep learning method can reduce the computational complexity of the model by 4 times and improve the accuracy of depth estimation. The proposed wavelet-based deep learning models(UNet-Wavelet and hNet-Wavelet) are efficient for depth estimation of single fringe pattern, achieving better performance than the original UNet and hNet models in both qualitative and quantitative evaluation.

关键词： measurement network estimation

Phase unwrapping based on deep learning in light field fringe projection 3D measurement

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2023年第9期19卷 556-562页

作者： zhu xinjun ZHAO Haichuan YUAN Mengkai ZHANG Zhizhi WANG Hongyi SONG Limei School of Artificial Intelligence Tiangong UniversityTianjin 300387China Tianjin Key Laboratory of Intelligent Control of Electrical Equipment Tiangong UniversityTianjin 300387China School of Control Science and Engineering Tiangong UniversityTianjin 300387China

Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.

关键词： Phase unwrapping based on deep learning in light field fringe projection 3D measurement

有机硅树脂对不烧铝碳滑板中温性能的影响研究

在线全文

学校读者我要写书评

暂无评论

耐火与石灰 2024年第1期49卷 20-24页

作者：黄晨朱新军曾立民曾昆吕建江湖南湘钢瑞泰科技有限公司湘潭411102

通过在酚醛树脂中添加有机硅树脂作为复合结合剂,利用X射线衍射仪、扫描电子显微镜和能谱仪对不烧铝碳滑板的物相、形貌和微区成分进行分析,研究了有机硅树脂的加入对不烧铝碳滑板中温性能的影响。研究结果表明:有机硅树脂能有效减小不... 详细信息

通过在酚醛树脂中添加有机硅树脂作为复合结合剂,利用X射线衍射仪、扫描电子显微镜和能谱仪对不烧铝碳滑板的物相、形貌和微区成分进行分析,研究了有机硅树脂的加入对不烧铝碳滑板中温性能的影响。研究结果表明:有机硅树脂能有效减小不烧铝碳滑板的体积密度与显气孔率波动,添加1%有机硅树脂时不烧铝碳滑板具有较好的综合性能;酚醛树脂在600℃时已基本脱氢碳化,有机硅树脂在600℃下仍具有较高的结合强度,可以有效防止不烧铝碳滑板中温强度低谷的出现;有机硅树脂可以促进不烧铝碳滑板在中温条件下晶须的生成,对不烧铝碳滑板的中温性能起积极作用。

关键词：不烧铝碳滑板有机硅树脂酚醛树脂中温性能

Poly(PEGMA) magnetic nanogels:Preparation via photochemical method,characterization and application as drug carrier

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2009年第1期52卷 69-75页

作者： SUN HanWen ZHANG LianYing zhu xinjun KONG ChunYan ZHANG CunLan YAO SiDe Department of Chemistry Dezhou UniversityDezhou 253023China Shanghai Institute of Applied Physics Chinese Academy of SciencesShanghai 201800China

One-pot synthesis of magnetic nanogels with excellent biocompatibility via the photochemical method is reported in this paper.Poly(PEGMA) modified superparamagnetic nanogels(poly(PEGMA) magnetic nanogels) were synthesized by in-situ polymerization using poly(ethylene glycol) methacrylate(PEGMA) as the monomer and N,N'-methylene-bis-(acrylamide)(MBA) as the cross-linking agent in magnetite aqueous suspension under UV irradiation.The surface functional groups and components of magnetic nanogels were analyzed by Fourier transform infrared spectroscopy(FTIR) and a thermogra-vimetric analyzer(TGA).The results indicated that the poly(PEGMA) magnetic nanogels were synthe-sized successfully by coating poly(PEGMA) on the Fe3O4 nanoparticles under UV irradiation,and the Fe3O4 nanoparticles content in this nanogels was above 50 wt%.The morphology,size,zeta-potential and magnetic property were also characterized.The magnetic nanogels had a nearly spherical shape and core-shell structure,the average size in aqueous system measured by photon correlation spec-troscopy(PCS) was 68.4 nm,which was much bigger than that in the dry state,the nanogels behaved superparamagnetically with saturated magnetization of 58.6 emu/g,and the zeta-potential was-16.3-_17.3 mV at physiological pH(6.8-7.4) which could help to maintain stability in blood.The preliminary application as drug carrier was made and the doxorubicin-loaded magnetic nanogels had an excellent property in slow-release.The experiment indicated that the magnetic nanogel was an ideal candidate carrier in target drug delivery systems and other biomedical application.

关键词： magnetic nanogels photochemical polymerization poly(ethylene glycol) methacrylate drug carrier doxorubicin

基于R2U-Net的单帧投影条纹图深度估计

在线全文

学校读者我要写书评

暂无评论

激光与光电子学进展 2022年第16期59卷 83-94页

作者：袁梦凯朱新军侯林鹏天津工业大学控制科学与工程学院天津300387 天津工业大学人工智能学院天津300387

从条纹图快速、准确获取被测物体准确深度信息是条纹投影三维测量技术关键环节之一。为解决单帧条纹图深度估计准确性问题,基于U-Net的递归残差卷积神经网络(R2U-Net),提出了一种条纹图深度估计方法,并在模拟数据和实验数据上进行了验... 详细信息

从条纹图快速、准确获取被测物体准确深度信息是条纹投影三维测量技术关键环节之一。为解决单帧条纹图深度估计准确性问题,基于U-Net的递归残差卷积神经网络(R2U-Net),提出了一种条纹图深度估计方法,并在模拟数据和实验数据上进行了验证。对于模拟数据,所提方法的预测结果误差为1.71×10^(-6),小于U-Net方法对应的误差7.98×10^(-6);对于实验数据,该方法预测的深度图误差比U-Net方法对应的误差降低了13%。实验结果表明,与已有的U-Net深度图预测方法相比,所提方法所得深度图的高度分布曲线与标签拟合程度更高,提高了单帧条纹图三维测量结果的准确性。

关键词：图像处理条纹投影 R2U-Net 深度三维测量

在线全文

学校读者我要写书评

暂无评论

面向集成制造的改进ORB图像匹配方法

计算机集成制造系统 2022年第7期28卷 2242-2249页

作者：杨倩兰宋丽梅黄浩珍朱新军天津工业大学控制科学与工程学院天津市电气装备智能控制重点实验室天津300387

图像匹配是计算机视觉应用研究的主要内容。针对ORB(Oriented FAST and Rotated BRIEF)图像匹配方法不具备尺度不变性和匹配精度低的问题,提出一种基于改进ORB算法的图像匹配方法。在特征点检测阶段,ORB和SURF(Speeded Up Robust Featu... 详细信息

图像匹配是计算机视觉应用研究的主要内容。针对ORB(Oriented FAST and Rotated BRIEF)图像匹配方法不具备尺度不变性和匹配精度低的问题,提出一种基于改进ORB算法的图像匹配方法。在特征点检测阶段,ORB和SURF(Speeded Up Robust Feature)同时检测特征点,首先采用oFAST(oriented-FAST)与SURF算法检测左右图像特征点,然后使用rBRIEF(rotation-aware BRIEF)描述子描述特征点;在立体匹配阶段,采用Hamming距离对特征点进行粗匹配的基础上,引入极线约束筛选特征点并进行精匹配,减小匹配搜索范围,加快匹配速度,提高匹配准确率。实验结果表明,所提改进ORB算法点对数平均值是SURF算法的1.5倍左右,匹配速度平均值比SURF算法提高了22%,准确率比SURF算法提高了2倍,比ORB算法提高1.7倍,从而证明所提改进ORB算法,具有匹配点数多、速度快、准确率高的特点,且具有尺度不变性。所提方法可应用于目标识别、目标跟踪、三维重建、缺陷检测等领域。

关键词：改进ORB算法特征点检测特征点描述外极线约束图像匹配