基于特征面片的复杂型面轮廓视觉测量方法

提出一种基于特征面片的复杂型面轮廓三维视觉测量方法。该方法包括多模式局部特征检测与匹配、特征面片集初始化、膨胀、滤波等重构过程，其输入是已标定的立体图像，输出是覆盖表面的可视稠密面片集。该方法不需要目标和场景的任何初始边界信息，能够自动检测和抛弃外部点和缺失部分；不需要对邻域特征进行任何平滑处理，仅需通过局部单演特征一致约束、立体极线约束和表面可视性约束来高效地匹配、膨胀和滤波稀疏表面点集，并生成密集表面点集。采用多项式曲面提取算法重建三维几何网格模型，采用子采样法将彩色、纹理等特征融合进三维几何网格，重建高保真的三维实体形貌。

Abstract

A feature patch-based three-dimensional vision measuring technique for complex surface and silhouette is proposed. There are several procedures for the proposed method including detecting and matching multi-modal local features, initializing, expanding and filtering patch sets. The algorithm outputs a dense set of rectangular patches covering the surfaces visible in the input calibrated images. The first step of the proposed algorithm is implemented as a matching, expanding, and filtering procedure. It starts from a sparse set of matched key points, and repeatedly expands these to nearby pixel correspondences using the monogenic feature congruency and the epipolar geometric constraint before using visibility constraints to filter away false matches. The keys to its performance are effective techniques for enforcing local photometric consistency and global visibility constraints. A simple but effective polygonal surface extraction algorithm is then used to turn the resulting patch model into a mesh appropriate for image-based modeling. According to the multi-modal monogenic features of a patch, the color and texture information is fused into the reconstructed mesh. Thus a three-dimensional high-fidelity solid model can be obtained finally.

参考文献

[1] G. Slabaugh, B. Culbertson, T. Malzbender et al.. Methods for volumetric reconstruction of visual scenes ［J］. International J. Computer Vision, 2004, 57(3): 179～199

[2] G. Vogiatzis, C. Hernandez, P. Torr et al.. Multi-view stereo via volumetric graph-cuts and occlusion robust photo-consistency ［J］. IEEE Trans. Pattern Anal. Machine Intell., 2007, 29(12): 2241～2246

[3] O. Faugeras, R. Keriven. Variational principles, surface evolution, PDEs, level set methods, and the stereo problem [J]. IEEE Trans. Image Processing, 1998, 7(3): 335～344

[4] J. P. Pons, R. Keriven, O. Faugeras. Multi-view stereo reconstruction and scene flow estimation with a global image-based matching score ［J］. Int. J. Computer Vision, 2007, 72(2): 179～193

[5] Y. Furukawa, J. Ponce. Carved visual hulls for image-based modeling [J]. Int. J. Computer Vision, 2009, 81(1):53～67

[6] V. Kolmogorov, R. Zabih. Multi-camera scene reconstruction via graph cuts ［C］. Seventh European Conference on Computer Vision, 2002. 82～96

[7] 周翔, 赵宏. 基于Mexican hat小波变换的三维轮廓术［J］. 光学学报, 2009, 29(1): 197～202

Zhou Xiang, Zhao Hong. Three-dimensional profilometry based on Mexican hat wavelet transform ［J］. Acta Optica Sinica, 2009, 29(1): 197～202

[8] 周翔, 赵宏. 使用离散小波变换的相位轮廓术［J］. 光学学报, 2009, 29(6): 1563～1569

Zhou Xiang, Zhao Hong. Phase profilometry using discrete wavelet transform ［J］. Acta Optica Sinica, 2009, 29(6): 1563～1569

[9] 吴迪, 吕乃光, 欧阳京. 基于无约束系统的结构光三维测量方法 [J]. 光学学报, 2008, 28(3): 482～486

Wu Di, Lü Naiguang, Ouyang Jing. A structured light three-dimensional measurement method based on unconstrained system configuration [J]. Acta Optica Sinica, 2008, 28(3): 482～486

[10] 刘天亮, 罗立民. 一种基于分割的可变权值和视差估计的立体匹配算法 [J]. 光学学报, 2009, 29(4): 1002～1009

Liu Tianliang, Luo Limin. Segmentation-based stereo matching algorithm with variable support and disparity estimation [J]. Acta Optica Sinica, 2009, 29(4): 1002～1009

[11] 张维光, 赵宏, 张琦等. 线结构光三维轮廓测量系统的标定方法［J］. 中国激光, 2009, 36(1): 182～188

Zhang Weiguang, Zhao Hong, Zhang Qi et al.. Calibration method for three-dimensional measurement system based on linear-structure light ［J］. Chinese J. Lasers, 2009, 36(1): 182～188

[12] Y. Furukawa, J. Ponce. Accurate, dense, and robust multi-view stereopsis ［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2007. 2118～2125

[13] C. Harris, M. J. Stephens. A combined corner and edge detector ［C］. Alvey Vision Conference, 1988. 147～152

[14] H. Bay, A. Ess, T. Tuytelaars et al.. Speeded-up robust features ［J］. Computer Vision and Image Understanding, 2008, 110(3): 346～359

[15] Li Jinjun, Zhao Hong, Jiang Kejiang et al.. Multiscale stereo analysis based on local-color-phase congruency in the color monogenic signal framework ［J］. Opt. Lett., 2010, 35(13): 2271～2274

[16] 李进军, 赵宏. 一种基于多模式单演特征检测与匹配的三维视觉测量方法［J］. 光学学报, 2011, 31(7): 0712007

Li Jinjun, Zhao Hong. Three-dimensional vision measuring technique based on multi-modal monogenic features detecting and matching ［J］. Acta Optica Sinica, 2011, 31(7): 0712007

李进军, 赵宏. 基于特征面片的复杂型面轮廓视觉测量方法[J]. 光学学报, 2011, 31(8): 0812003. Li Jinjun, Zhao Hong. Feature Patch-Based Vision Measuring Technique for Complex Surface and Silhouette[J]. Acta Optica Sinica, 2011, 31(8): 0812003.

基于特征面片的复杂型面轮廓视觉测量方法

关于本站 Cookie 的使用提示

全站搜索

基于特征面片的复杂型面轮廓视觉测量方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索