下面截取部分内容加以阐述:
摘要:随着人工智能技术、智慧农业和虚拟现实技术等信息技术的快速发展和摄像器材的广泛普及,三维模型重建工作越来越普遍,如何开发面向植物的简易三维模型重建流程已受到普遍关注。本研究通过文献研究法和实证研究法,实现了摄像机的自标定过程,基于机器学习和SVM理论,实现了交互式彩色图像分割模式并与原有的颜色阈值分割法进行了对比,构建了针对植物三维模型的基于单目视觉的运动恢复结构流程,并以兰花为例进行了重建。结果表明:(1)SVM图像分割理论更适合背景复杂的植物图形和批量处理,颜色阈值分割法在背景单一的情况下能取得良好效果;(2)BRISK立体匹配算法的匹配效率更高且更具有鲁棒性;(3)基于单目视觉的SfM法能较好地还原植物三维信息。
关键词:三维重建;植物;SVM图像分割;单目视觉
废话不多说,这个项目说到底其实就是一个针对激光建模方案的替代方案,由于手持式激光建模仪器太过于昂贵,除非实验必要,大部分有真正需求的人,反而无法接受其高昂的价格。所以在结合我的导师的建议和我自身兴趣的前提下,我查阅了大量资料,文献,设计出了这一款,能够实现植物三维模型快速重建的小程序,分享出来,以便提供大家参考。
上图所示就是这个程序的一个小功能,主要是利用支持向量机原理,将图像精准分割。
下图所示,是这个项目的流程设计图。
下图是,项目所做的一些成果
参考文献
[1] 章毓晋.图像工程,第三版(合订本).北京:清华大学出版社,2013
[2] Witkin A P. Recovering surface shape and orientation from texture[J]. Artificial intelligence, 1981, 17(1-3): 17-45.
[3] Wiley W C, McLaren I H. Time‐of‐flight mass spectrometer with improved resolution[J]. Review of Scientific Instruments, 1955, 26(12): 1150-1157.
[4] Woodham R J. Photometric method for determining surface orientation from multiple images[J]. Optical engineering, 1980, 19(1): 191139-191139-.
[5] Wiese D R. Laser Triangulation Sensors[J]. Quality, 1989, 28(1): 46.
[6] Aloimonos J. Shape from texture[J]. Biological cybernetics, 1988, 58(5): 345-360.
[7] Horn B K P. Shape from shading: A method for obtaining the shape of a smooth opaque object from one view[J]. 1970.
[8] Barnard S T, Thompson W B. Disparity analysis of images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1980 (4): 333-340.
[9] Marr D, Poggio T. A computational theory of human stereo vision[J]. Proceedings of the Royal Society of London B: Biological Sciences, 1979, 204(1156): 301-328.
[10] Barrow H G, Tenenbaum J M. Computer vision systems[J]. Computer vision systems, 1978, 2.
[11] Barnard S T, Fischler M A. Computational stereo[J]. ACM Computing Surveys (CSUR), 1982, 14(4): 553-572.
[12] Dhond U R, Aggarwal J K. Structure from stereo-a review[J]. IEEE transactions on systems, man, and cybernetics, 1989, 19(6): 1489-1510.
[13] ladys law Skarbek W, Koschan A. Colour image segmentation a survey[J]. IEEE Transaction son circuits and systems for Video Tecknology, 1994, 14(7).
[14] Seitz S M, Curless B, Diebel J, et al. A comparison and evaluation of multi-view stereo reconstruction algorithms[C]. IEEE, 2006, Vol 1: 519-528.
[15] 雷成, 胡占义, 吴福朝. 一种新的基于 Kruppa 方程的摄像机自标定方法[J]. 计算机学报, 2003, 26(5): 587-597.
[16] Zhong Y, Zhang H. Control points based semi-dense matching[C]//Proceedings of the 5th Asian Conference on Computer Vision. Melbourne, Australia, 2002, 144.
[17] 谢路生, 王磊, 出晓岚, 等. 基于 SfS 的 3D 视觉测量研究[J]. 2009.
[18] 李秀智, 张广军. 一种基于边缘线的三目立体匹配方法[J]. 光電工程, 2007, 34(3): 22-26.
[19] Hartley R, Zisserman A. Multiple view geometry in computer vision[M]. Cambridge university press, 2003.
[20] Bouguet, J. Y. "Camera Calibration Toolbox for Matlab."Computational Vision at the California Institute of Technology.
[21] Zhang, Z. "A Flexible New Technique for Camera Calibration."IEEE Transactions on Pattern Analysis and Machine Intelligence.Vol. 22, No. 11, 2000, pp. 1330–1334.
[22] Heikkila, J., and O. Silven."A Four-step Camera Calibration Procedure with Implicit Image Correction."IEEE International Conference on Computer Vision and Pattern Recognition.1997.
[23] 杨丹, 赵海滨, 龙哲. MATLAB 图像处理实例详解[J]. 2013.
[24] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.
[25] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 1440-1448.
[26] He K, Gkioxari G, Dollár P, et al. Mask r-cnn[J]. arXiv preprint arXiv:1703.06870, 2017.
[27] Cortes C, Vapnik V. Support vector machine [J][J]. Machine learning, 1995, 20(3): 273-297.
[28] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3): 27.
[29] 白明, 庄严, 王伟. 双目立体匹配算法的研究与进展[J]. 控制与决策, 2008, 23(7):721-729. DOI:doi:10.3321/j.issn:1001-0920.2008.07.001.
[30] 张令涛, 曲道奎, 徐方. 一种基于图割的改进立体匹配算法[J]. 机器人, 2010, 32(1):104-108.
[31] Leutenegger, S., M. Chli and R. Siegwart. "BRISK: Binary Robust Invariant Scalable Keypoints", Proceedings of the IEEE International Conference, ICCV, 2011.
[32] Rosten, E., and T. Drummond. "Fusing Points and Lines for High Performance Tracking," Proceedings of the IEEE International Conference on Computer Vision, Vol. 2 (October 2005): pp. 1508–1511.
[33] Harris, C., and M. Stephens, "A Combined Corner and Edge Detector," Proceedings of the 4th Alvey Vision Conference, August 1988, pp. 147-151.
[34] Shi, J., and C. Tomasi, "Good Features to Track," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 1994, pp. 593–600.
[35] Von Noorden G K. Binocular vision & ocular motility [J]. 1990.
[36] Howard I P, Rogers B J. Binocular vision and stereopsis [M]. Oxford University Press, USA, 1995.
[37] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91-110.
[38] Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal