High quality 3D reconstruction based on fusion of polarization imaging and binocular stereo vision

Polarization imaging can retrieve inaccurate objects’ 3D shapes with fine textures, whereas coarse but accurate depths can be provided by binocular stereo vision. To take full advantage of these two complementary techniques, we investigate a novel 3D reconstruction method based on the fusion of polarization imaging and binocular stereo vision for high quality 3D reconstruction. We first generate the polarization surface by correcting the azimuth angle errors on the basis of registered binocular depth, to solve the azimuthal ambiguity in the polarization imaging. Then we propose a joint 3D reconstruction model for depth fusion, including a data fitting term and a robust low-rank matrix factorization constraint. The former is to transfer textures from the polarization surface to the fused depth by assuming their relationship linear, whereas the latter is to utilize the low-frequency part of binocular depth to improve the accuracy of the fused depth considering the influences of missing-entries and outliers. To solve the optimization problem in the proposed model, we adopt an efficient solution based on the alternating direction method of multipliers. Extensive experiments have been conducted to demonstrate the efficiency of the proposed method in comparison with state-of-the-art methods and to exhibit its wide application prospects in 3D reconstruction.     

“两步法”求取双目视觉传感器中摄象机位置关系

根据平行线“消隐点”理论，提出了用于双目视觉传感器自标定的“两步法”。该方法仅需４对消隐点象面坐标便可线性求解出旋转矩阵，再用２个空间点坐标便可线性求解出平移矢量。     

带钢端部形状双目视觉检测系统的建模仿真

为了实现热轧带钢端部形状检测,利用Matlab中视觉图像处理工具箱,建立了由CCD线阵相机构成的双目立体视觉系统模型和实际带钢生产线上的运动过程模型。热轧带钢在生产过程中会受到粗轧辊的不平均压力的影响,从而造成带钢头尾变形。针对这种情况.提出了一种新的带钢末端形状视觉检测和宽度计算方法。该方法不但可以在带钢发生平移、倾斜等位置和姿态变化情况下仍能够准确测量出带钢宽度,并且可以精确还原出带钢头尾形状。仿真试验结果证实了所提出的视觉模型和算法的有效性.取得的结果令人满意。     

基于主动形状模型的双目识别系统的设计与实现

给出了一种基于统计形状模型的双目识别系统实现方法.该系统根据识别目标在场景中的姿态有一定规律性的特点,用先验的样本信息指导识别的过程,并采用径向对齐约束的方法对摄像头内外参数进行标定,利用图像识别结果中特征点的顺序性完成特征匹配,进而获得目标的三维信息.     

Cognitive processes in complex tasks: introduction and discussion

This paper points out that the fusional limits of binocular stereoscopic viewing are an important factor, not only determining the reproduction range of stereoscopic images, but also the conformity between the stereoscopic display and stereoscopic vision. Experimental results showed that fusional limits increase in proportion to the field of view angle, and that they are affected not only by the size of the viewing target, but also by the effects that the environment has on the target. These findings explain the differences between binocular vision in real space and binocular vision in a stereoscopic display. Finally, the conditions under which observers arc able to view images of stereoscopic displays without excessive visual strain are discussed.     

靶标成像双目视觉坐标测量建模

提出了一种利用手持式靶标实现双目视觉三维坐标测量建模的新方法。利用空间透视变换建立了非线性测量模型．介绍了基于牛顿非线性迭代的测量方程的求解方法。以矩阵分析理论为基础，讨论了影响测量方程求解的因素，并提出了方法中重要部件手持式靶标上特征点分布的基本约束条件，为这一方法在实际应用中获得较高的测量精度提供了较为完善的理论分析依据。通过数值分析与计算，验证了理论分析的正确性和这一方法应用的可行性。     

双眼立体感知几何模型的研究

利用普通针孔成象的双摄像模型对双眼立体感知几何模型进行了研究，详细讨论了体视象空间的视觉重构，最后通过实验分析了影响体视的因素。     

Disparity-based just-noticeable-difference model for perceptual stereoscopic video coding using depth of focus blur effect

Human 3D perception provides an important clue to the removal of redundancy in stereoscopic 3D (S3D) videos. Because objects outside the binocular fusion limit cannot be fused on retina, the human visual system (HVS) makes them blur according to the depth-of-focus (DOF) effect to increase the binocular fusion limit and suppress diplopia, i.e. double vision. Based on human depth perception, we propose a disparity-based just-noticeable-difference model (DJND) to save bit-rate and improve visual comfort in S3D videos. We combine the DOF blur effect with conventional JND models in the pixel domain into DJND. Firstly, we use disparity information to get the average disparity value of each block. Then, we integrate the DOF blur effect into luminance JND (LJND) by a selective low pass Gaussian filter to minimize the visual stimulus in S3D videos. Finally, we incorporate disparity information into the filtered JND models to obtain DJND. Experimental results demonstrate that the proposed method successfully improves both image quality and visual comfort in viewing S3D videos without increasing the bit-rate.     

基于PatchMatch的半全局高效双目立体匹配算法

近年来双目立体匹配技术发展迅速,高精度、高分辨率、大视差的应用需求无疑对该技术的计算效率提出了更高的要求.由于传统立体匹配算法固有的计算复杂度正比于视差范围,已经难以满足高分辨率、大视差的应用场景.因此,从计算复杂度、匹配精度、匹配原理等多方面综合考虑,提出了一种基于PatchMatch的半全局双目立体匹配算法,在路径...     

Modeling of binocular vision system for 3D reconstruction with improved genetic algorithms

This paper models the binocular vision system focused on 3D reconstruction and describes an improved genetic algorithm (GA) for estimating camera system parameters. The two-camera system model that takes into account camera radial distortion includes a total of 24 parameters. The proposed improved GA is used to solve this nonlinear optimization problem with high dimension. In our improved GA, the adaptive control of camera parameter search interval and the catastrophe strategy with elitist preservation are employed. The experimental results indicate that our improved GA is effective to solve the multi-peak function optimization problem and the 3D reconstruction accuracy of the binocular vision system is promising.