基于多源信息融合的果树冠层三维点云拼接方法研究

构建了基于彩色相机和光学混合探测(PMD)相机的多源视觉系统，旨在建立具有真彩色信息的果树冠层三维点云模型，为果树的剪枝、疏花疏果和采摘等果园管理提供技术支持。针对PMD相机获取的目标场景三维点云，结合PMD相机的幅度图像和密度聚类算法提取有效点，利用前期研究的图像配准方法得到多源图像之间的坐标转换关系，完成了果树冠层多源信息融合。通过主成分分析法得到较好的初始位置，再采用最近点迭代算法，实现两组三维点云之间的拼接。对自然场景下的开花期和坐果期的果树冠层三维点云拼接方法进行了实验验证，结果表明多视角三维点云拼接误差为2.62 cm，可以较好地弥补单个角度下拍摄造成的数据缺失，实现了果树冠层完整的三维显示。

Abstract

In order to guide the pruning, flower thinning and harvesting of fruit trees in orchard, a novel vision system which combines a color-camera system with a photo mixing detector (PMD)-camera is constructed. For the three-dimensional coordinate information of target scene acquired by the PMD camera, effective point cloud combining PMD amplitude image with density-based spatial clustering of applications with noise (DBSCAN) algorithm is extracted. Multi-source information fusion is completed with the result of image registration in the previous studies. Primary component analysis algorithm (PCA) is used to get the initial state of the point cloud at different locations, which is called prealignment. Accurate splice between two point clouds is realized by the iterative closest point (ICP) algorithm based on the least square method to get the optimal matching. Coordinate transformations are obtained by singular value decomposition (SVD) after prealigment and accurate splice. Several groups of experiments are used for verification, which show the average error of multi-view point cloud splicing reaches 2.62 cm and can better make up full three dimensional display of apple tree canopy without missing data than a single angle shot.

参考文献

[1] 汪景彦, 李壮, 李敏, 等. 我国苹果业存在问题及其对策与发展趋势[J]. 中国果树, 2011, (2): 62-65.

Wang Jingyan, Li Zhuang, Li Min, et al.. Existing problem, countermeasure and development trend of apple industry in China [J]. China Fruits, 2011, (2): 62-65.

[2] M Nielsen, D C Slaughter, C Gliever. Vision-based 3D peach tree reconstruction for automated blossom thinning [J]. IEEE Transactions on Industrial Informatics, 2012, 8(1): 188-196.

[3] 蔡健荣, 孙海波, 李永平, 等. 基于双目立体视觉的果树三维信息获取与重构[J]. 农业机械学报, 2012, 43(3): 152-156.

Cai Jianrong, Sun Haibo, Li Yongping, et al.. Fruit trees 3-D information perception and reconstruction based on binocular stereo vision [J]. Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(3): 152-156.

[4] 袁晓敏, 赵春江, 温维亮, 等. 番茄植株三维形态精确重构研究 [J]. 农业机械学报, 2012, 43(12): 204-210.

Yuan Xiaomin, Zhao Chunjiang, Wen Weiliang, et al.. Detailed modeling of 3-D configuration of tomato plant [J]. Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(12): 204-210.

[5] Y Lin, J Hyypp. Multiecho-recording mobile laser scanning for enhancing individual tree crown reconstruction [J]. IEEE Transactions on Geoscience and Remote Sening, 2012, 50(11): 4323-4332.

[6] A Bucksch, K Khoshelham. Localized registration of point clouds of botanic trees [J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3): 631-635.

[7] 王剑, 周国民. 基于激光扫描仪的树干三维重建方法研究 [J]. 微计算机信息, 2009, 25(8-3): 227-230.

Wang Jian, Zhou Guomin. Trunk reconstruction method based on Laser scanner [J]. Microcomputer Information, 2009, 25(8-3): 227-230.

[8] P Raumonen, S Kaasalainen, M Kaasalainen, et al.. Approximation of volume and branch size distribution of trees from laser scanner data [J]. Int Archives Photogramm, Remote Sens, Spatial Inf Sci, 2011, 38(5): 1-6.

[9] T Watanabe, J S Hanan, P M Room, et al.. Rice morphogenesis and plant architecture: Measurement. specification and the reconstruction of structural develop by 3D architectural modeling [J]. Annals of Botany, 2005, 95(7): 1131-1143.

[10] 王菲. 高纺锤形富士苹果树分形维数及三维数字化建模和STAR值的研究 [D]. 杨凌: 西北农林大学, 2012.

Wang Fei. Study on Fractal Dimension and Three-Dimensional Digital Modeling and STAR Values of High Spindle Fuji Apple Tree [D]. Yangling: Northwest A&F University, 2012.

[11] 杨亮, 郭新宇, 赵春江, 等. 基于多幅图像的黄瓜叶片形态三维重建 [J]. 农业工程学报, 2009, 25(2): 141-144.

Yang Liang, Guo Xinyu, Zhao Chunjiang, et al.. 3D morphological reconstruction of cucumber leaf based on multiple images [J]. Transactions of the Chinese Society of Agricultural Engineering, 2009, 25(2): 141-144.

[12] M Lindner, I Schiller, A Kolb, et al.. Time-of-flight sensor calibration for accurate range sensing [J]. Computer Vision and Image Understanding, 2010, 114(12S1): 1318-1328.

[13] S F Salmerón, G A Ribas, C T Genís. Exploitation of time-of-flight (ToF) cameras [R]. Technical Report IRI-TR-10-07, Institut de Robòticai Informàtica Industrial, CSIC-UPC, 2010.

[14] 冯娟, 刘刚, 王圣伟, 等. 采摘机器人果实识别的多源图像配准[J]. 农业机械学报, 2013, 44(3): 197-203.

Feng Juan, Liu Gang, Wang Shengwei, et al.. Multi source images registration for harvesting robot to recognize fruits [J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(3): 197-203.

[15] 李嘉, 阿依古丽·阿曼, 郑德华, 等. 复杂场景三维点云中未知球形目标的自动识别方法[J]. 计算机辅助设计与图形学学报, 2013, 25(10): 1489-1495.

Li Jia, Ayiguli Aman, Zheng Dehua, et al.. Automatically identifying uncertain spherical targets in 3D point clouds of complex scenario [J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(10): 1489-1495.

[16] 陈晓霞, 陈孝威. 三维重建中散乱点云的聚类筛选与网格重建[J]. 计算机系统应用, 2011, 20(4): 141-144.

Chen Xiaoxia, Chen Xiaowei. Sieving scattered 3D point clouds using clustering analysis for 3D surface reconstruction [J]. Computer Systems & Applications, 2011, 20(4): 141-144.

[17] 周薇, 冯娟, 刘刚, 等. 苹果采摘机器人中的图像配准技术研究[J]. 农业工程学报, 2013, 29(11): 20-26.

Zhou Wei, Feng Juan, Liu Gang, et al.. Application of image registration technology in apple harvest robot [J]. Transactions of the CSAE, 2013, 29(11): 20-26.

[18] 周薇, 刘刚, 马晓丹, 等. 不同生长时期果树多源图像的配准方法研究[J]. 光学学报, 2014, 34(2): 0215001.

Zhou Wei, Liu Gang, Ma Xiaodan, et al.. A study on multi-image registration of apple tree at different growth stages [J]. Acta Optica Sinica, 2014, 34(2): 0215001.

[19] 刘善勇. 三维激光点云与序列数码影像配准方法的研究[J]. 城市勘测, 2011, (4): 92-95.

Liu Shanyong. Research on laser scanning point cloud data and digital image sequence registration [J]. Urban Geotechnical Investigation & Surveying, 2011, (4): 92-95.

[20] 张贺, 杨金玲, 曹先革, 等. 基于点云数据的主成分分析重构表面算法[J]. 黑龙江工程学院学报（自然科学版）, 2010, 24(1): 39-42.

Zhang He, Yang Jinling, Cao Xiange, et al.. Principal component analysis reconstruction surface algorithm based on points cloud data [J]. J Heilongjiang Institute of Technology, 2010, 24(1): 39-42.

[21] 赵明波, 何峻, 罗小波, 等. 基于改进迭代最近点算法的两视角激光雷达数据配准[J]. 光学学报, 2012, 32(11): 1128007.

Zhao Mingbo, He Jun, Luo Xiaobo, et al.. Two-viewing angle ladar data registration based on improved iterative closest-point algorithm [J]. Acta Optica Sinica, 2012, 32(11): 1128007.

[22] 孙军华, 射萍, 刘震, 等. 基于分层块状全局搜索的三维点云自动配准[J]. 光学精密工程, 2013, 21(1): 174-180.

Sun Junhua, She Ping, Liu Zhen, et al.. Automatic 3D point cloud registration based on hierarchical block global search [J]. Optics and Precision Engineering, 2013, 21(1): 174-180.

[23] 陶海跻, 达飞鹏. 一种基于法向量的点云自动配准方法[J]. 中国激光, 2013, 40(8): 0809001.

Tao Haiji, Da Feipeng. Automatic registration algorithm for the point clouds based on the normal vector [J]. Chinese J Lasers, 2013, 40(8): 0809001.

[24] 左超, 鲁敏, 谭志国, 等. 一种新的点云拼接算法[J]. 中国激光, 2012, 39(12): 1214004.

Zuo Chao, Lu Min, Tan Zhiguo, et al.. A novel algorithm for registration of point clouds [J]. Chinese J Lasers, 2012, 39(12): 1214004.

周薇, 马晓丹, 张丽娇, 郭彩玲, 刘刚. 基于多源信息融合的果树冠层三维点云拼接方法研究[J]. 光学学报, 2014, 34(12): 1215003. Zhou Wei, Ma Xiaodan, Zhang Lijiao, Guo Cailing, Liu Gang. Three Dimensional Point Cloud Splicing of Tree Canopy Based on Multi-Source Camera[J]. Acta Optica Sinica, 2014, 34(12): 1215003.

基于多源信息融合的果树冠层三维点云拼接方法研究

关于本站 Cookie 的使用提示

全站搜索

基于多源信息融合的果树冠层三维点云拼接方法研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索