Three-dimensional Reconstruction and Phenotype Parameters Acquisition of Seeding Vegetables Based on Neural Radiance Fields

ZHU Lei, JIANG Wei, SUN Boyan, CHAI Mingtang, LI Saiju, DING Yimin


Accurate and efficient reconstruction of seedling crop structures is crucial for obtaining phenotype parameters. The traditional method for 3D reconstruction based on the structure from motion and multi-view stereo (SFM-MVS) algorithm, which had high reconstruction accuracy and high computional cost. It was difficult to meet the demand for rapid acquisition of phenotype parameters. A system for acquiring phenotype parameters and creating 3D models of seedling crops was proposed by using neural radiance fields (NeRF). The system utilized smart phone to capture RGB images of the objects from various viewpoints and constructed the 3D model through the NeRF algorithm. The algorithms of line fitting and region growing in point cloud library (PCL) were used to automatically segment the plants. Additionally, the algorithms of distance-minimum traversal, circle fitting, and triangulation were used to measure phenotype parameters such as plant height, stem diameter, and leaf area. To assess the reconstruction efficiency and accuracy of phenotype parameter measurement, seedling plants of pepper, tomato, strawberry and epipremnum aureum were selected as subjects. The reconstruction results were compared by using the NeRF and the SFM-MVS algorithm. The results indicated that both methods were capable of achieving superior reconstruction outcomes. The root mean square errors of the point-to-point distances of each seedlings were only 0.128cm to 0.359cm. But in terms of speed, this method improved the reconstruction speed by an average of 700% compared with the SFM-MVS method. The method used to extract plant height and stem diameter of chili pepper seedlings had a coefficient of determination (R2) of 0.971 and 0.907, respectively. The root mean square error (RMSE) was 0.86cm and 0.017cm, respectively. The R2 of the leaf area extracted from the plants at seedling stage ranged from 0.909 to 0.935, and the RMSE ranged from 0.75cm2 to 3.22cm2, indicating a high level of accuracy in measurement. The proposed method can significantly speed up 3D reconstruction and acquisition of phenotype parameters. This would provide a more efficient technical means for vegetable breeding and seedling selection.


Keywords:seedling crop;three-dimensional reconstruction;neural radiance fields;phenotype parameters;leaf area

Download Full Text:



WANG Qing, CHE Yingpu, CHAI Honghong, et al. Monitoring of sugar beet growth using canopy spectrum and structural characteristics with UAV images[J]. Transactions of the CSAE, 2021 , 37(20) ; 90 -98. (in Chinese)

YANG S, ZHENG L, GAO W, et al. An efficient processing approach for colored point cloud-based high-throughput seedling phenotyping[ J]. Remote Sensing, 2020, 12(10): 1540.

YUAN Peisen, LI Runlong, REN Shougang, et al. State-of-the-art review for representation learning and its application in plant phenotypes [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(6) ; 1 - 14. (in Chinese)

HE Yong, LI Xiyao, YANG Guofeng, et al. Research progress and prospect of indoor high-throughput germplasm phenotyping platforms[ J ]. Transactions of the CSAE, 2022, 38(17): 127 - 141. ( in Chinese)

HUANG Yiqi, LIU Xianghuan, HUANG Zhenyu, et al. Identification of early wheel spot and rust on sugarcane leaves based on spectral analysis [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(4) : 259 -267. (in Chinese)

XIE Yaping, TONG Xiaogang, WANG Xiaohui. Early monitoring of rice koji disease based on hyperspectroscopy [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(9) ; 288 -296. (in Chinese)

MWINUKA P R, MBILINYI В P, MBUNGU W B, et al. The feasibility of hand-held thermal and UAV-based multispectral imaging for canopy water status assessment and yield prediction of irrigated African eggplant (Solarium aethopicum [ J]. Agricultural Water Management, 2021, 245: 106584.

ZHANG II, GE Y, XIE X, et al. High throughput analysis of leaf chlorophyll content in sorghum using RGB, hyperspectral, and fluorescence imaging and sensor fusion [ J]. Plant Methods, 2022, 18( 1 ) ; 1 - 17.

XU Shengyong, LI Lei, TONG Hui, et al. High-throughput measurement system for ЗD phenotype of cucumber seedlings using RGB — D camera [J] . Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(7 ); 204 - 213, 281. (in Chinese)

CHENG Man, YUAN Hongbo, CAI Zhenjiang, et al. Review of field-based information acquisition and analysis of high- throughput phenotyping [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(Supp. 1 ) ; 314 -324. ( in Chinese)

ZHU Qihing, ZHANG Meng, LIU Zhenfang, et al. Identification and counting method of potted kumquat fruits based on point cloud registration [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(5) ; 209 -216. (in Chinese)

XIAO Zhigang, ZHOU Mengxiang, YUAN Hongbo, et al. Influence analysis of light intensity on Kinect v2 depth measurement accuracy..! • Transactions of the Chinese Society for Agricultural Machinery, 2021 , 52(Supp. ) ; 108 - 117. (in Chinese)

CHEN Ilaiho, LIU Shengho, WANG Lele, et al. Automatic 3D reconstruction and verification of an individual crop using Kinect V3[J]. Transactions of the CSAE, 2022, 38( 16) : 215 -223. ( in Chinese)

SONG P, LI Z, YANG M , et al. Dynamic detection of three-dimensional crop phenotypes based on a consumer-grade RGB — D camera [J ]. Frontiers in Plant Science, 2023, 14: 1097725.

ZHANG Man, MIAO Yanlong, QIU Ruicheng, et al. Maize point cloud data filtering algorithm based on vehicle 3D LiDAR [J] . Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(4) ; 170 - 178. (in Chinese)

HE W, YE Z, LI M, et al. Extraction of soybean plant trait parameters based on SfM — MVS algorithm combined with GRNN [J] . Frontiers in Plant Science, 2023, 14; 1181322.

ZHU Binglin, LIU Fusang, ZHU Jinyu,et al. Three-dimensional quantifications of plant growth dynamics in field-grown plants based on machine vision method [J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(5) ; 256 - 262. (in Chinese)


  • There are currently no refbacks.