3D Point Cloud Registration for Apple Tree Based on Kinect Camera

Zheng Lihua, Mai Chunyan, Liao We, Wen Yao, Liu Gang

Abstract

Aiming at establishing a 3D point cloud model of fruit tree with true color to provide scientific guidance for the production management of orchard, a research on the registration method for two pieces of 3D original point clouds of fruit tree obtained from different perspectives was carried out. The 3D raw point clouds of apple tree in two perspectives were obtained based on Kinect camera and information fusion technology. Firstly, the background removal and noise filtering approaches were used to implement a data pretreatment for each piece of raw point cloud, and every relative exact point cloud of single apple tree was acquired in each specific angle. Secondly, by using depth information of fruit tree’s point cloud image and object boundary characteristics, the key points were extracted based on NARF (Normal aligned radial feature) algorithm. Meanwhile, the FPFH (Fast point feature histograms) descriptor was developed to obtain the characteristic vector for each key point. Thirdly, according to the characteristic vectors, the pairs of corresponding key points between two pieces of point cloud were estimated and extracted. And the spatial mapping relationships between two pieces of point cloud were calculated by validating and refining all pairs of corresponding key points based on the RANSAC (Random sample consensus) algorithm. Then the rotation matrix and translation vector between the two neighboring point clouds were computed, by which, the initial registration of two adjacent pieces of point cloud was achieved further. Finally, on the basis of the initial registration, two pieces of point cloud were fused into the same space coordinate system to complete their precise registration through applying the ICP(Iterative closest point) algorithm. This paper carried out the experiments based on the above algorithms, and the results showed that the improved point cloud registration method could be used to match two pieces of point cloud at any original positions in space, and its mean registration error reached 0.7cm.

Keywords: apple tree, Kinect camera, 3D point cloud, initial registration, iterative closest point algorithm

Download Full Text:

PDF


References


ZHANG Yu,WANG Xiaochan,SUN Guoxiang,et al. Leaves and stems measurement of plants based on laser vision in greenhouses [J]. Transactions of the Chinese Society for Agricultural Machinery ,2014 ,45 ( 9) :254 -259. (in Chinese)

LIU Gang,SI Yongsheng, FENG Juan. 3D reconstruction of agriculture and forestry crops[ J ]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(6) ; 39 -46. (in Chinese) 2012,43(3): 152 -156.

CAI Jianrong,SUN Haibo,LI Yongping. 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. (in Chinese)

ADHIKARI B,KARKEE M. 3D reconstruction of apple trees for mechanical pruning[ С] //2011 ASABE Annual Meeting, ASABE Paper 1111613,2011.

IIAN S II, BALKS T F. 3D reconstruction of a citrus canopy[ С]/ /2009 ASABE Annual Meeting,ASABE Paper 097398 .2009.

MA Xiaodan,GLO Cailing,ZHANG Xue,et al. Calculation of light distribution of apple tree canopy based on color characteristics of 3D point cloud[ J]. Transactions of the Chinese Society for Agricultural Machinery ,2015 ,46 ( 6 ) ;263 -268. ( in Chinese)

LIN Y ,HYYPPA J. Multiecho-recording mobile laser scanning for enhancing individual tree crown reconstruction [J]. Geoscience and Remote Sensing,2012 ,50( 11 ) : 4323 -4332.

RAUMONEN P, KAASALAINEN S, KAASALAINEN M,et al. Approximation of volume and branch size distribution of trees from laser scanner data[J]. International Archives of Photogrammetrv, Remote Sensing and Spatial Information Sciences,2011 ,38( 12) ; 79 -84.

YANG Weivvei ,CIIEN Xilong,LIU Hangkong,et al. Three-dimensional simulation of canopy structure and light interception for tall spindle shape of spur Fuji apple with dwarf interstock [ J ]. Scientia Agricultura Sinica ,2014 ,47 (23 ) : 4680 -4694. (in Chinese)

ZHANG Lanfen,LI Bingzhi,ZHANG Sheqi,et al. Light interception measurement of apple trees trained to tall spindle shape based on three-dimensional digitizer [J]. Northern Horticulture ,2012 (7) ; 9 - 12. (in Chinese)

WANG Fei, ZHANG Sheqi, LI Bingzhi, et al. Three-dimensional reconstruction of trees trained to tall spindle shape and assessment of light characteristics [ J ]. Northern Horticulture ,2012 ( 6 ) ; 10-13. (in Chinese)

TRIPICCHIO P, SATLER M , DABISIAS G,et al. Towards smart farming and sustainable agriculture with drones [ С ] // 2015 International Conference on Intelligent Environments,2015 : 140 - 143. Kinect 2015(11): 216 -221.

YU Xiuli,WANG Dandan,NIU Leilei,et al. The applications and research progress of Kinect in the information field of modern agriculture [ J ]. Journal of Agricultural Mechanization Research ,2015 ( 11): 216 — 22 1. (in Chinese)

Microbes B. Using depth cameras for biomass estimation-a multi-angle approach[J]. Precision Agriculture .2015,15( 1 ) : 97 — 101.

GAI J,TANG L, STEWARD В L. Plant recognition through the fusion of 2D and 3D images for robotic weeding[C] // ASABE Annual International Meeting,ASABE Paper 152181371,2015.

BESL P J, MCKAY N D. A method for registration of 3-D shapes [ J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992,14(2) :239 -256.

SHARP G C,LEE S W , W EHE D K. ICP registration using invariant features[ J]. Pattern Analysis and Machine Intelligence, 2002,24( 1 ) : 90 - 102.

STEDER В,RUSU R B,K0N0LIGE K,et al. Point feature extraction on 3D range scans taking into account object boundaries[ С] // 2011 IEEE International Conference on Robotics and Automation,2011 ; 2601 -2608.

RUSU R В, BLODOW N,BEETZ M. Fast point feature histograms (FPFH) for 3D registration [ С ] // 2009 IEEE International Conference on Robotics and Automation ,2009: 3212 -3217.

FISCHLER M A,BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography [ J ]. Communications of the ACM, 1981 ,24(6) ; 381 -395.

ZHOU Wei,MA Xiaodan, ZHANG Lijiao,et al. Three dimensional point cloud splicing of tree canopy based on multi-source camera [ J ]. Acta Optical Sinica ,2014,34 ( 12 ) ; 185 -192. (in Chinese)


Refbacks

  • There are currently no refbacks.