基于双目立体相机的室外场景三维重建系统设计

摘要：三维重建是图像处理、计算机视觉、计算机图形学的一个重要研究领域,双目视觉通过模拟人眼处理景物的方式可以获取目标物体的三维信息,具有非接触、速度快、精度高、自动化程度好等诸多优点,可以大大提高工业生产效率,已经成为人们研究的热点。在传统的基于双目立体视觉的三维重建系统基础上进行了方法和算法的改进与创新,并根据具体应用场合拓展了系统功能。硬件选用Stereolabs公司的二代ZED双目立体相机套件,配合该套件提供的软件开发工具包（ZED SDK）,使用NVIDIA推出的通用并行计算架构CUDA,很大程度上优化了三维重建的运行效率;针对立体匹配过程噪声及原有视图引入误差等问题,利用插值法和数学形态学平滑方法进行处理,引入了视差图修复与细化环节;采用更为合理的特征点提取方法,优化了深度值计算环节。在实验室环境下,对整体系统进行了性能测试,结果表明,算法稳定高效,系统重建效果好,性价比高。     

基于深度语义模型的双目位姿估计

位姿估计是现阶段智能和自动化控制领域最热门的研究方向之一,在无人驾驶汽车、智能工业机械臂、民用家政机器人等领域有着诸多应用。但传统方法大多具有计算复杂,实时性困难等问题。提出了一种利用卷积神经网络来做双目相机图像输入端的尺寸压缩和信息提取,并将特征向量通过双向长短时神经网络与激光雷达计算的标准结果进行回归学习的位姿解算方案。训练得到的深度学习方案在精度和速度方面相对于传统方案都有一定的提升。     

基于双目去歧义的偏振三维重建技术研究

对于表面光滑且纹理单一的物体,因其具有纹理信息不足的特征,故利用传统的重建算法无法准确恢复其形状特征,并且会出现大面积数据空洞的现象,而利用偏振信息对目标物进行重建时,则会很好地解决上述的情况。但由于入射面方位角存在模糊性,导致无法获取有效的深度信息,提出用双目估计参数去除歧义角从而三维重建。利用Stokes参数来表示两个视角下目标表面反射光的偏振态信息,由于两个视图的对应点是独立的,即每个方位角都会存在不可避免的歧义性,这种方位模糊导致有两种可能的法向量,故从两幅具有偏振信息的图像中估计相对位姿,在求解相对位姿时,相对旋转与平移是必不可少的,问题即可以转换为最小二乘求优问题。通过求得最优解来估计出旋转矩阵从而消除方位角的歧义问题,实验结果表明,该消除歧义后深度图的图像分辨率更高,重建后形状信息准确,目标物纹理还原性高,易于工程实现。     

基于深度学习的故障检测方法

针对传统故障诊断方法中特征提取技术难度大、故障样本获取困难等问题,在深度学习计算框架下提出了一种半监督训练的故障检测方法,利用深度信念网络中的受限波茨曼机堆栈结构实现了数据高层特征的自动提取,结合支持向量数据描述方法实现了异常数据检测,只需利用正常工况的数据样本进行网络训练和模型拟合,无需故障样本数据,也无需人工干预进行信号特征提取,即能实现对故障数据进行的实时检测和判别。经采用标准轴承实验数据的三组故障数据进行验证,故障识别率达到100%,具有很强的工程应用价值。     

基于Kinect传感器多深度图像融合的物体三维重建

物体的三维重建技术一直是计算机视觉领域研究的热点问题,提出一种利用Kinect传感器获取的深度图像实现多幅深度图像融合完成物体三维重建的方法。在图像空间中对深度图像进行三角化,然后在尺度空间中融合所有三角化的深度图像构建分层有向距离场（hierarchical signed distance field）,对距离场中所有的体素应用整体Delaunay三角剖分算法产生一个涵盖所有体素的凸包,并利用Marching Tetrahedra算法构造等值面,完成物体表面重建。实验结果表明,该方法利用Kinect传感器采集的不同方向37幅分辨率为640480的深度图像完成目标物体的三维重建,仅需要48 s,并且得到非常精细的重建效果。     

杨氏模量的不确定度评定

本文介绍杨氏模量的不确定度计算方法。     

基于深度学习的初中物理实验教学策略

实验是初中物理教学的重要组成部分,也是每一名学生都应具备的基本技能,对理论知识的学习与理解具有不可忽视的作用。基于新课程改革的指引,对初中物理实验教学提出更高的要求,教师应发挥自身的引导作用,带领学生在动手操作中深化知识理解,促进实践能力的提升,从而达到深度学习的教育目的。文章简要分析了深度学习的特征,探析基于深度学习的初中物理实验教学策略,为广大教育工作者提供参考。     

光栅常量实验的数据处理

以测光栅常量实验的数据处理为例，叙述了一元线性不等精度测量的不确定度评定方法，介绍了直接从方差的性质推得斜率b及截距b0的不确定度的公式。     

牛顿环实验等精度测量及其不确定度的评定与表示

讨论了等精度测量牛顿环曲率半径及牛顿环直径测量不确定度的评定与表示。     

双目视觉中基于对偶四元数的三维运动估计

针对现有的三维运动估计算法在精度、效率和稳定性等综合性能上的不足,提出了一种结合双目视觉三维重建和利用对偶四元数表达运动参数的新算法。该算法以双目视觉系统为基础,采用SIFT算法进行图像特征点的提取和匹配;根据匹配关系进行三维特征点重建,以获取三维场景中运动目标的结构参数;利用对偶四元数可同时表示刚体的旋转和平移运动的特点,实现目标对象运动参数的表达和求解。通过实验将提出的算法与现有算法(包括奇异值分解法、正交分解法和单位四元数分解法)进行比较,结果表明,该算法具有更加简洁的表达形式,在保持传统算法精度和稳定性优势的基础上提高了计算效率,具有更优的综合性能。     

3D reconstruction based on spatial vanishing information

An approach for the three-dimensional (3D) reconstruction of architectural scenes from two un-calibrated images is described in this paper. From two views of one architectural structure, three pairs of corresponding vanishing points of three major mutual orthogonal directions can be extracted. The simple but powerful constraints of parallelism and orthogonal lines in architectural scenes can be used to calibrate the cameras and to recover the 3D information of the structure. This approach is applied to the real images of architectural scenes, and a 3D model of a building in virtual reality modelling language (VRML) format is presented which illustrates the method with successful performance.     

Feasibility of high-resolution magnetic resonance imaging of the liver using deep learning reconstruction based on the deep learning denoising technique

PurposeTo evaluate the feasibility of High-resolution (HR) magnetic resonance imaging (MRI) of the liver using deep learning reconstruction (DLR) based on a deep learning denoising technique compared with standard-resolution (SR) imaging.Materials and methodsThis retrospective study included patients who underwent abdominal MRI including both HR imaging using DLR and SR imaging between April 1 and August 31, 2019. DLR was applied to all HR images using 12 different strength levels of noise reduction to determine the optimal denoised level for HR images. The mean signal-to-noise ratio (SNR) was then compared between the original HR images without DLR and the optimal denoised HR images with DLR and SR images. The mean image noise, sharpness and overall image quality were also compared. Statistical analyses were performed with the Friedman and Dunn-Bonferroni post-hoc test.ResultsIn total, 49 patients were analyzed (median age, 71 years; 25 women). In quantitative analysis, the mean SNRs on the original HR images without DLR were significantly lower than those on the SR images in all sequences (p < 0.01). Conversely, the mean SNRs on optimal denoised HR images were significantly higher than those on the SR images in all sequences (p < 0.01). In the qualitative analysis, the mean scores for the image noise and overall image quality were significantly higher on optimal denoised HR images than on the SR images in all sequences (p < 0.01) except for the mean image noise score in in-phase (IP) images.ConclusionsThe use of a deep learning-based noise reduction technique substantially and successfully improved the SNR and image quality in HR imaging of the liver. Denoised HR imaging using the DLR technique appears feasible for use in liver MR examinations compared with SR imaging.     

Transfer learning in deep neural network based under-sampled MR image reconstruction

In Magnetic Resonance Imaging (MRI), the success of deep learning-based under-sampled MR image reconstruction depends on: (i) size of the training dataset, (ii) generalization capabilities of the trained neural network. Whenever there is a mismatch between the training and testing data, there is a need to retrain the neural network from scratch with thousands of MR images obtained using the same protocol. This may not be possible in MRI as it is costly and time consuming to acquire data. In this research, a transfer learning approach i.e. end-to-end fine tuning is proposed for U-Net to address the data scarcity and generalization problems of deep learning-based MR image reconstruction. First the generalization capabilities of a pre-trained U-Net (initially trained on the human brain images of 1.5 T scanner) are assessed for: (a) MR images acquired from MRI scanners of different magnetic field strengths, (b) MR images of different anatomies and (c) MR images under-sampled by different acceleration factors. Later, end-to-end fine tuning of the pre-trained U-Net is proposed for the reconstruction of the above-mentioned MR images (i.e. (a), (b) and (c)). The results show successful reconstructions obtained from the proposed method as reflected by the Structural SIMilarity index, Root Mean Square Error, Peak Signal-to-Noise Ratio and central line profile of the reconstructed images.     

一种基于场景轮廓特征的三维地形重建方法

为了提升双目视觉系统三维重建的准确性和实时性,提出了一种基于区域分割和匹配的方法。针对实际场景中存在大面积灰度相近区域的现象以及稠密三维重建存在实时性差的问题,采用分水岭算法提取区域轮廓进行三维重建;针对轮廓边缘的误匹配问题,建立区域匹配和边缘点匹配的双重约束条件进行优化匹配;根据平行轴双目立体视觉模型进行三维重建。结果表明:采用轮廓特征进行匹配因其匹配点数大为减少,匹配用时提高了90%;由于采用了双重匹配策略,匹配和重建的准确性得到了保证。     

基于计算机视觉的非朗伯表面三维重构

基于计算机视觉的三维重构方法已经广泛应用在各行各业中。目前的三维重构研究主要针对不透明的朗伯表面,且已经比较成熟,但对非朗伯表面仍然面临诸多问题。而实际场景中的物体表面大多是非朗伯表面,因而,随着实际应用的推广,非朗伯表面的三维重构问题在计算机视觉领域越来越受到关注。虽然本现状研究不能完全涵盖针对非朗伯表面三维重构的所有方法,但它包涵了三维重构每个步骤中的各种典型方法。文中按照图像获取过程中的照明方式和重构原理对现有方法进行了分类,并逐类进行了介绍。由于不存在公共测试网络平台和带有标准视差的非朗伯表面立体图像集,因而,很难对各种算法的计算效率和匹配质量进行比较,文中主要对非朗伯表面的现有三维重构方法的原理、特点、适用范围和最新研究方向进行了介绍,对非朗伯表面三维重构的现有问题和发展前景进行了讨论。     

基于阻尼LSQR-LMBC的火焰三维温度场重建

光场相机可以解决辐射测温多相机系统光路复杂、同步触发难等问题,在辐射成像三维温度重建时有其独特优势. LSQR是求解基于大型稀疏矩阵最小二乘问题的经典算法,该算法用于重建三维温度场时对温度初值依赖较大,在信噪比较低的情况下重建精度不理想.本文提出阻尼LSQR-LMBC重建算法,通过在LSQR方法中添加阻尼正则化项,提高火焰三维温度场重建的抗噪性能,并结合LMBC算法,实现吸收系数和三维温度场同时求解.在数值模拟部分,随着信噪比逐渐降低,阻尼LSQR的重建效果比LSQR更加稳定,在信噪比达到13.86 d B时,重建精度大约提高30%.阻尼LSQR-LMBC的平均重建误差为6.63%.用丁烷火焰进行了实验,重建的丁烷火焰三维温度场分布符合辐射火焰燃烧的特征,和热电偶的测温数据结果进行对比,相对误差在6.8%左右.     

Improved 3D reconstruction method based on the Scheimpflug principle

Optical Review - This paper proposes a 3D reconstruction scheme for monocular cameras based on an improved line structure cursor positioning method and the Scheimpflug principle to overcome the...     

基于计算机视觉的非朗伯表面三维重构

基于计算机视觉的三维重构方法已经广泛应用在各行各业中。目前的三维重构研究主要针对不透明的朗伯表面,且已经比较成熟,但对非朗伯表面仍然面临诸多问题。而实际场景中的物体表面大多是非朗伯表面,因而,随着实际应用的推广,非朗伯表面的三维重构问题在计算机视觉领域越来越受到关注。虽然本现状研究不能完全涵盖针对非朗伯表面三维重构的所有方法,但它包涵了三维重构每个步骤中的各种典型方法。文中按照图像获取过程中的照明方式和重构原理对现有方法进行了分类,并逐类进行了介绍。由于不存在公共测试网络平台和带有标准视差的非朗伯表面立体图像集,因而,很难对各种算法的计算效率和匹配质量进行比较,文中主要对非朗伯表面的现有三维重构方法的原理、特点、适用范围和最新研究方向进行了介绍,对非朗伯表面三维重构的现有问题和发展前景进行了讨论。     

Signal area estimation based on deep learning

In many practical application scenarios, radio communication signals are commonly represented as a spectrogram, which represents the signal strength measured at multiple discrete time instants and frequency points within a specific time interval and frequency band, respectively. In the context of spectrum occupancy measurements, the notion of Signal Area (SA) is defined as the rectangular region in the time–frequency domain where a signal is assumed to be present. Signal Area Estimation (SAE) is an important functionality in spectrum-aware wireless systems where spectrum usage monitoring is required. However, the conventional approaches to SAE have a limited estimation accuracy, in particular at low SNR. In this work, a novel technique for SAE is proposed using Deep Learning based on Artificial Neural Network (DL-ANN) for enhanced extraction of SA information from radio spectrograms. The performance of the proposed DL-ANN method is evaluated both with software simulations and hardware experiments, and the results are compared with several conventional methods from the literature, showing significant performance improvements. A key feature of the proposed method is the improvement in the SAE accuracy compared to other existing methods (in particular in the low SNR regime) and the capability to extract the location of the detected SAs automatically. Overall, the proposed technique is a promising solution for the automatic processing of radio spectrograms in spectrum-aware wireless systems.