Multi Perspective Point Cloud Reconstruction Method for Sweet Pepper Fruit under Occlusion Conditions
Abstract
The in-situ phenotype of sweet pepper is an important reference indicator for fruit breeding and management. Automated measurement of phenotype in-situ through phenotype collection robots is one of the effective ways for digital breeding and management of sweet pepper. However, fruit occlusion during the measurement process seriously affects the success rate of detection. Therefore, a three-dimensional reconstruction method for multi view sweet pepper fruit point cloud was proposed to address the problem of target occlusion in in-situ fruit phenotype measurement. By using the method of virtual leaves, an enhanced dataset was created, and a sweet pepper fruit recognition model based on YOLO v5 algorithm was established to recognize fruits with different degrees of occlusion. At the same time, a fruit phenotype collection algorithm considering fruit position and occlusion degree was constructed to achieve multi view threedimensional data collection of fruits. Finally, the three-dimensional point cloud of sweet pepper fruit was registered, the phenotype parameters of sweet pepper was extracted, and the effectiveness of the point cloud reconstruction method was validated through the greenhouse sweet pepper fruit phenotype. Compared with manual measurement data, the average relative error of fruit width was 1.72%, and the average relative error of fruit height was 1.60%. The experimental results indicated that the in-situ phenotype point cloud reconstruction method proposed for sweet pepper can provide effective solutions and feasible methods for crop phenotypes under occlusion conditions.
Keywords: sweet pepper; phenotype; data augmentation; occlusion conditions; point cloud three-dimensional reconstruction; YOLO v5
Download Full Text:
PDFReferences
ZOU Xuexiao, MA Yanqing, DAI Xiongze, et al. Spread and industry development of pepper in China [ J]. Acta Horticulturae Sinica, 2020, 47(9): 1715 - 1716. (in Chinese)
BACHI L, LEFEBVRE V, SAGE-PALLOIX A M, et al. QTL analysis of plant development and fruit traits in pepper and performance of selective phenotyping [ J]. Theoretical and Applied Genetics, 2009, 118: 1157 - 1171.
NAEGELE R P, MITCHELL J, HAUSBECK M K. Genetic diversity, population structure, and heritability of fruit traits in Capsicum annuum[J j. Plos One, 2016, 11(7): eOl56969.
HURTADO M, VI LA NO V A S, PLAZAS M, et al. Phenomics of fruit shape in eggplant (Solarium melongena L. ) using tomato analyzer software[ J ]. Scientia Horticulturae, 2013, 164: 625 -632.
BHAKATH S M, C1LAS C, Li MAH ARAN P. Fruit trait variation in a Caribbean germplasm collection of aromatic hot peppers (Capsicum cnense Jacq. ) J . Hortscience, 2013, 48(5) : 531 -538.
MARTINEZ-ISPIZUA E, CALATAYUD, MARSAL J I, et al. Phenotypic divergence among sweet pepper landraces assessed by aro-morphological characterization as a biodiversity source[ J . Agronomy, 2022, 12(3) ; 632.
LIU Chengliang, GONG Liang, YUAN Jin, et al. Current satus and dvelopment tends of aricultural robots [ J]. Transactions of the Chinese Society for Agricultural Machinery,2022,53(7) :1 -22,55. (in Chinese)
WANG Ning, HAN Yuxiao, WANG Yaxuan, et al. Research progress of agricultural robot full coverage oeration planning [J]. Transactions of the Chinese Society for Agricultural Machinery,2022,53(Supp. 1) :1 - 19. (in Chinese)
LI L, ZHANG Q, HUANG D. A review of imaging techniques for plant phenotyping J ]. Sensors, 2014, 14( 11 ) : 2(X)78 - 20111.
SUN G, W ANG X. Three-dimensional point cloud reconstruction and morphology measurement method for greenhouse plants based on the kinect sensor self-calibration[ J ]. Agronomy, 2019, 9(10): 596.
FAN J, ZHANG Y, WEN W, et al. The future of Internet of Things in agriculture: plant high-throughput phenotypic platform [J]. Journal of Cleaner Production, 2021 , 280: 123651.
REN Dongyu, LI Xiaojuan, LIN l'ao, et al. 3D reconstruction method for fruit tree branches based on Kinect 2 sensor [ J]. Transactions of the Chinese Society for Agricultural Machinery, 2022,53 (Supp. 2) ; 197 -203. (in Chinese)
PAULUS S, SCHUMANN H, KUHLMANN H, et al. High-precision laser scanning system for capturing 3D plant architecture and analysing growth of cereal plants [ J ]. Biosystems Engineering, 2014, 121; 1 - 11.
WANG Y, WEN W, WU S, et al. Maize plant phenotyping: comparing 3D laser scanning, multi-view stereo reconstruction, and 3D digitizing estimates[ J] . Remote Sensing, 2018, 11(1) ; 63.
GARR1D0 M, PARAFOROS D S, RRISER D, et al. 3D maize plant reconstruction based on geo referenced overlapping LiDAR point clouds[ J]. Remote Sensing, 2015, 7( 12): 17077 - 17096.
FORERO M G, MURCIA H F, MENDFZ D, et al. LiDAK platform for acquisition of 3D plant phenotyping database [ J]. Plants, 2022, 11(17): 2199.
LI Rui, LIU Ting, DONG Runru, et al. 3D modeling of individual maize based on ground-based LiDAR data [J ]. Journal of China Agricultural University, 2014,19(3) :196 — 201. (in Chinese)
TENG X, ZHOU G, WU Y, et al. Three-dimensional reconstruction method of rapeseed plants in the whole growth period using RGB - D camera [J ]. Sensors, 2021 , 21(14): 4628.
WANG Y, CHEN Y. Fruit morphological measurement based on three-dimensional reconstruction [ J ]. Agronomy, 2020, 10(4) : 455.
SUN Guoxiang, WANG Xiaochan, LIU Jingna, et al. Multi-modal three-dimensional reconstruction of greenhouse tomato plants based on phase-correlation method[ J ]. Transactions of the CSAE, 2019, 35(18): 134 - 142. (in Chinese)
NGUYEN T T, SLAUGHTER D C, MAX N, et al. Structured light-based 3D reconstruction system for plants[ [J ]. Sensors, 2015, 15(8): 18587 - 18612.
ZHENG Lihua, W ANG Luhan, W ANG Minjuan, et al. Automated 3D reconstruction of leaf lettuce based on Kinect camera [j]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(7) : 159 - 168. (in Chinese)
LI Peng, LAO Cailian, YANG Han, et al. Maize plant 3D information acquisition system based on mobile robot platform[ J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(Supp. ) : 15 —21. (in Chinese)
LIU Xingxing, WANG Shuoshuo, XU Liming, et al. Real time color recognition of moving raisin based on OpenCV [J]. Transactions of the CSAE, 2019, 35(23) : 177 - 184. (in Chinese)
GUO Jianjun, HE Guohuan, XU Longqin, et al. Pigeon behavior detection model based on improved YOLO v4 [ J]. Transactions of the Chinese Society for Agricultural Machinery,2023 ,54(4) ;347 -355. (in Chinese)
HU J, LI G, MO H, et al. Crop node detection and internode length estimation using an improved YOLO 5 model [ J]. Agriculture, 2023, 13(2): 473.
WU W, LAIU H, LI L, et al. Application of local fully convolutional neural network combined with YOLO 5 algorithm in small target detection of remote sensing image J . PloS One, 2021 , 16(10) : e()259283.
Refbacks
- There are currently no refbacks.
