偏振多光谱机器视觉的高反光无纹理目标三维重构方法

doi:10.11947/j.AGCS.2018.20170624

测绘学报 ›› 2018, Vol. 47 ›› Issue (6): 816-824.doi: 10.11947/j.AGCS.2018.20170624

• 计算机视觉与三维重建 • 上一篇下一篇

偏振多光谱机器视觉的高反光无纹理目标三维重构方法

郝婧蕾¹, 赵永强², 赵海盟³, Peter BREZANY⁴, 孙嘉玉³

1. 西北工业大学自动化学院, 陕西西安 710071;
2. 西北工业大学深圳研究院, 广东深圳 518057;
3. 北京大学空间地球与空间科学学院, 北京 100871;
4. 维也纳大学, 奥地利维也纳 1090

收稿日期:2017-12-03 修回日期:2018-04-13 出版日期:2018-06-20 发布日期:2018-06-21
通讯作者: 赵永强 E-mail:zhaoyq@nwpu.edu.cn
作者简介:郝婧蕾(1991-),女,博士生,研究方向为偏振和光谱图像三维重构、超分辨、去噪等。
基金资助:
国家自然科学基金（61771391），深圳市科技创新委员会基础研究（学科布局）项目（JCYJ20170815162956949）

3D Reconstruction of High-reflective and Textureless Targets Based on Multispectral Polarization and Machine Vision

HAO Jinglei¹, ZHAO Yongqiang², ZHAO Haimeng³, Peter BREZANY⁴, SUN Jiayu³

1. College of Automation, Northwestern Polytechnical University, Xi'an 710071, China;
2. Research and Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen 518057, China;
3. School of Earth and Space Sciences, Peking University, Beijing 100871, China;
4. University of Vienna, Vienna 1090, Austria

Received:2017-12-03 Revised:2018-04-13 Online:2018-06-20 Published:2018-06-21
Supported by:
The National Natural Science Foundation of China (No.61771391);Shenzhen Science and Technology Innovation Committee Foundational Research (Discipline Distribution) Project (No.JCYJ20170815162956949)

摘要/Abstract

摘要： 随着摄影测量及机器视觉技术的迅速发展，对三维重构的普适性有了更高的要求。对于表面光滑、纹理单一甚至缺失的高反光非金属目标，传统的三维重构方法由于对纹理及反光特性的依赖使得此类目标的重构表面出现大面积的数据空洞。针对这一问题，本文提出了基于多光谱偏振的三维重构方法，将摄影测量与机器视觉进行融合，通过获取目标精确的偏振光谱特征实现准确的三维重构。该方法不依赖于物体表面的纹理信息，并且可以解决仅依靠菲涅尔理论无法实现天顶角和折射率同时估计的问题，最终实现天顶角和折射率的联合估计。由于杂散光和漫反射光在不同波段具有不同的偏振特性以及光谱特性，可完成对目标进行耀光去除的预处理，使得后期的三维重构的精度有较大的提高。基于偏振多光谱的目标三维重构方法是摄影测量与机器视觉融合后三维重构的引导性进展，具有更广泛的应用范围。

关键词: 三维重构, 多光谱偏振, 无纹理目标

Abstract: With the rapid development of photogrammetry and machine vision technology,a higher universality of three-dimensional reconstruction is required.For high-reflective and non-metal targets with smooth surface or extreme simple texture,a large area of data void may appear on the reconstruction surface since the traditional 3D reconstruction methods depend on texture and reflective characteristics.To solve this problem,a 3D reconstruction method based on multispectral polarization imaging is proposed in this paper,which integrates photogrammetry and machine vision and achieves accurate reconstruction by obtaining accurate multispectral polarization characteristics of targets.The proposed method does not rely on the texture information on the surface,and it can solve the problem of joint estimating refractive index and zenith angle simultaneously,which cannot be achieved only by Fresnel theory.Due to straylights and diffuse reflection light have different polarization and spectral characteristics at different wavelengths,we can remove the highlight to improve the reconstruction accuracy.The 3D reconstruction method based on multiband polarization imaging is the guiding progress of 3D reconstruction after the fusion of photogrammetry and machine vision,which has a wider application range.

Key words: 3D reconstruction, multispectral polarization, textureless targets

中图分类号:

TP391

郝婧蕾, 赵永强, 赵海盟, Peter BREZANY, 孙嘉玉. 偏振多光谱机器视觉的高反光无纹理目标三维重构方法[J]. 测绘学报, 2018, 47(6): 816-824.

HAO Jinglei, ZHAO Yongqiang, ZHAO Haimeng, Peter BREZANY, SUN Jiayu. 3D Reconstruction of High-reflective and Textureless Targets Based on Multispectral Polarization and Machine Vision[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 816-824.

参考文献

[1] SONG Weitao, WENG Dongdong, LIU Yue, et al. Three-dimensional Reconstruction for Photon Counting Imaging Using a Planar Catadioptric Method[C]//Proceedings of 2017 Conference on Lasers and Electro-optics Pacific Rim. Singapore:IEEE, 2017:1-2.
[2] WANG Binquan, KONG Lingcheng, ZHAO Jianghai, et al. Design of Three-dimensional Reconstruction and Robot Path Planning Based on Kinect System[C]//Proceedings of the 29th Chinese Control and Decision Conference. Chongqing, China:IEEE, 2017:3829-3834.
[3] ZHANG Junning, PAN Wei, SHI Haobin, et al. Three-Dimensional Reconstruction Method Based on Target Recognition for Binocular Humanoid Robot[C]//Proceedings of 2016 International Conference on Progress in Informatics and Computing. Shanghai, China:IEEE, 2017:355-359.
[4] HONDA J, YOKOYAMA H, TAJIMA H, et al. Influences of 3D Aircraft Model to ILS Localizer[C]//Proceedings of the 201610th International Conference on Complex, Intelligent, and Software Intensive Systems. Fukuoka, Japan:IEEE, 2016:180-185.
[5] SUN Huabo, LUO Boren, YU Liling, et al. Mosaic Research with 3D LiDar Point Cloud of Civil Aircraft[C]//Proceedings of the 20132nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation. Toronto, ON, Canada:IEEE, 2013:683-686.
[6] GODARD C, HEDMAN P, LI Wenbin, et al. Multi-View Reconstruction of Highly Specular Surfaces in Uncontrolled Environments[C]//Proceedings of 2015 International Conference on 3D Vision. Lyon, France:IEEE, 2015:19-27.
[7] ZHAO Yongqiang, YI Chen, KONG S G, et al. Multi-band Polarization Imaging and Applications[M]. Berlin, Heidelberg:Springer, 2016.
[8] RAGHEB H, HANCOCK E R. A Probabilistic Framework for Specular Shape-from-shading[J]. Pattern Recognition, 2003, 36(2):407-427.
[9] KOSHIKAWA K. A Polarimetric Approach to Shape Understanding of Glossy Objects[C]//Proceedings of the 6th International Joint Conference on Artificial Intelligence. Tokyo, Japan:Morgan Kaufmann Publishers Inc., 1979.
[10] GHOSH A, CHEN Tongbo, PEERS P, et al. Circularly Polarized Spherical Illumination Reflectometry[J]. ACM Transactions on Graphics, 2010, 29(6):162.
[11] MIYAZAKI D, KAGESAWA M, IKEUCHI K. Transparent Surface Modeling from a Pair of Polarization Images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):73-82.
[12] ATKINSON G A, HANCOCK E R. Multi-view Surface Reconstruction Using Polarization[C]//Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China:IEEE, 2005:309-316.
[13] MIYAZAKI D, SAITO M, SATO Y, et al. Determining Surface Orientations of Transparent Objects Based on Polarization Degrees in Visible and Infrared Wavelengths[J]. Journal of the Optical Society of America A, 2002, 19(4):687-694.
[14] MOREL O, GORRIA P. Polarization Imaging for 3D Inspection of Highly Reflective Metallic Objects[J]. Optics and Spectroscopy, 2006, 101(1):11-17.
[15] STOLZ C, FERRATON M, MÉRIAUDEAU F. Shape from Polarization:A Method for Solving Zenithal Angle Ambiguity[J]. Optics Letters, 2012, 37(20):4218-4220.
[16] ZHAO Yongqiang, WANG Miaomiao, YANG Guang, et al. FOV Expansion of Bioinspired Multiband Polarimetric Imagers with Convolutional Neural Networks[J]. IEEE Photonics Journal, 2018, 10(1):1-14.
[17] MIYAZAKI D, SHIGETOMI T, BABA M, et al. Polarization-Based Surface Normal Estimation of Black Specular Objects from Multiple Viewpoints[C]//Proceedings of the 2nd International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. Zurich, Switzerland:IEEE, 2012:104-111.
[18] DROUET F, STOLZ C, LALIGANT O, et al. 3D Reconstruction of External and Internal Surfaces of Transparent Objects from Polarization State of Highlights[J]. Optics Letters, 2014, 39(10):2955-2958.
[19] ATKINSON G A, HANCOCK E R. Surface Reconstruction Using Polarization and Photometric Stereo[C]//Proceedings of the 12th International Conference on Computer Analysis of Images and Patterns. Vienna, Austria:Springer, 2007:466-473.
[20] SAMAN G, HANCOCK E. Refractive Index Estimation Using Photometric Stereo[C]//Proceedings of the 18th IEEE International Conference on Image Processing. Brussels, Belgium:IEEE, 2011:1925-1928.
[21] HUYNH C P, ROBLES-KELLY A, HANCOCK E R. Shape and Refractive Index from Single-View Spectro-Polarimetric Images[M]. Hingham:Kluwer Academic Publishers, 2013.
[22] KADAMBI A, TAAMAZYAN V, SHI Boxin, et al. Polarized 3D:High-quality Depth Sensing with Polarization Cues[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile:IEEE, 2015:3370-3378.
[23] NGO T T, NAGAHARA H, TANIGUCHI R I. Shape and Light Directions from Shading and Polarization[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA:IEEE, 2015:2310-2318.
[24] 平茜茜, 刘勇, 董欣明, 等. 基于偏振双目视觉的无纹理高反光目标三维重构[J]. 红外与毫米波学报, 2017, 36(4):432-438. Ping Xixi, LIU Yong, DONG Xinming, et al. 3-D Reconstruction of Textureless and high-Reflective target by Polarization and Binocular Stereo Vision[J]. Journal of Infrared and Millimeter Waves, 2017, 36(4):432-438.
[25] AHMAD J E, TAKAKURA Y. Stereo-polarimetric Measurement of Pair of Mueller Images for Three Dimensional Partial Reconstruction[C]//Proceedings of the 200614th European Signal Processing Conference. Florence, Italy:IEEE, 2006:1-4.
[26] BORN M, WOLF E. Principles of Optics:Electromagnetic Theory of Propagation, Interference and Diffraction of Light[M]. 7th ed. Oxford:Cambridge University Press, 1999.
[27] ZHAO Yongqiang, PENG Qunnie, YI Chen, et al. Multiband Polarization Imaging[J/OL]. Journal of Sensors,(2016)[2016-04-15].http://dx.doi.org/10.1155/2016/5985673.
[28] ZHAO Yongqiang, PENG Qunnie, XUE Jize, et al. Specular Reflection Removal Using Local Structural Similarity and Chromaticity Consistency[C]//Proceedings of 2015 IEEE International Conference on Image Processing. Quebec City, QC, Canada:IEEE, 2015:3397-3401.

偏振多光谱机器视觉的高反光无纹理目标三维重构方法

3D Reconstruction of High-reflective and Textureless Targets Based on Multispectral Polarization and Machine Vision

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	徐君, 王彩玲, 王丽. 采用PPI算法改进的一种数学形态学端元提取方法[J]. 测绘学报, 2019, 48(8): 996-1003.
[2]	尚洋, 孙晓亮, 张跃强, 李由, 于起峰. 三维目标位姿跟踪与模型修正[J]. 测绘学报, 2018, 47(6): 799-808.
[3]	张良培, 张云, 陈震中, 肖佩珮, 罗斌. 基于分裂合并的多模型拟合方法在点云分割中的应用[J]. 测绘学报, 2018, 47(6): 833-843.
[4]	吴佳奇, 张过, 汪韬阳, 蒋永华. 结合运动平滑约束与灰度特征的卫星视频点目标跟踪[J]. 测绘学报, 2017, 46(9): 1135-1146.
[5]	马小龙李成名赵占杰. 道路交叉口自动检测与基于OSG的三维自动建模方法[J]. 测绘学报, 2014, 43(10): 1083-1091.
[6]	胡根生陈长春梁栋. 联合云量自动评估和加权支持向量机的Landsat图像云检测[J]. 测绘学报, 2014, 43(8): 848-854.
[7]	付仲良周凡俞志强. 综合多种特征的后方交会法[J]. 测绘学报, 2014, 43(8): 827-834.
[8]	陶超邹峥嵘丁晓利. 利用角点进行高分辨率遥感影像居民地检测方法[J]. 测绘学报, 2014, 43(2): 164-169.
[9]	刘繁明张迎发荆心. 基于压缩感知的地磁数据分频压缩与重构方法研究[J]. , 2013, 42(4): 0-0.
[10]	李景文, 韦晶闪, 姜建武, 陆妍玲, 刘垒, 唐一飞, 李旭. 多视角监控视频中动态目标的时空信息提取方法[J]. 测绘学报, 2022, 51(3): 388-400.