AUTHOR=He Wei , Ye Zhihao , Li Mingshuang , Yan Yulu , Lu Wei , Xing Guangnan 

TITLE=Extraction of soybean plant trait parameters based on SfM-MVS algorithm combined with GRNN

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1181322

DOI=10.3389/fpls.2023.1181322

ISSN=1664-462X

ABSTRACT=To address the problems of strong subjectivity, high labor intensity, and plant damage in the measurement methods of soybean leaves, a three-dimensional (3D) reconstruction method for soybean plants based on structure from motion (SFM) was proposed. First, based on the SFM algorithm, the 3D point cloud of a soybean plant was reconstructed from multi-view images obtained by a smartphone. Subsequently, low-pass filtering, Gaussian filtering, Ordinary Least Square (OLS) plane fitting, and Laplacian smoothing were used to automatically segment point cloud data, such as individual plants, stems, and leaves. Finally, Eleven morphological traits, such as plant height, minimum bounding box volume per plant, leaf projection area, leaf projection length and width, and leaf tilt information, were accurately and nondestructively measured by the proposed an algorithm for leaf phenotype measurement (LPM). Moreover, Support Vector Machine (SVM), Back Propagation Neural Network (BP), and Back Propagation Neural Network (GRNN) prediction models were established to predict and identify soybean plant varieties. The results indicated that, compared with the manual measurement, the root mean square error (RMSE) of plant height, leaf Running Title length, and leaf width were 0.9997, 0.2357, and 0.2666 cm, respectively, and the mean absolute percentage error (MAPE) were 2.7013%, 1.4706%, and 1.8669%, respectively, and the coefficients of determination (R 2 ) were 0.9775, 0.9785, and 0.9487, respectively. The accuracy of predicting plant species according to the six leaf parameters was high when using GRNN, reaching 0.9211, and the RMSE was 18.3263. The results show that the proposed method can effectively extract the 3D phenotypic structure information of soybean plants and leaves without loss and can be extended to other plants with dense leaves.