Measurement of the Angle between stems and leaves of rice based on key point detection

Xiaoyue Seng; Tonghai Liu; Xue Yang; Rui Zhang; Chuangchuang Yuan; Tiantian Guo; Wenzheng Liu

doi:10.54097/bev3vbbn

Authors

Xiaoyue Seng
Tonghai Liu
Xue Yang
Rui Zhang
Chuangchuang Yuan
Tiantian Guo
Wenzheng Liu

DOI:

https://doi.org/10.54097/bev3vbbn

Keywords:

Rice, Stem-leaf angle, Deep learning, Key points, Phenotypic characteristics

Abstract

Stem-leaf angle is an important phenotypic parameter of rice, which is crucial for the growth and development of rice plants and scientific breeding. However, the traditional method is inefficient and subjective. In order to quickly and accurately calculate the stem-leaf pinch angle of rice, this paper proposes a key point-based stem-leaf pinch angle detection method. Experimentally, four periods of rice (Jointing stage, Booting stage, Heading stage and Mature stage) are selected as research objects, image data are collected, key points are extracted by YOLOv7-pose network model, and a lightweight convolution method GSConv is introduced, which is able to reduce the complexity of the model and improve the accuracy of the key point detection, the average accuracy of key point detection was improved from 93.7% to 98.7%, an improvement of 5%. Finally, the angular size of the pinch angle was determined based on the coordinates of the key points located by the model, and the R2 of the pinch angle calculation results to the actual manual measurements was the highest of 0.84, the errors for the four periods were 1.543°, 1.716°, 1.213°, and 0.998°. So the method ensures the accuracy of identification while the model size is reduced, and can effectively measure the angle of rice stem and leaf pinch, and the investigated method can better help farmers to understand the growth and development of plants and provide support for the selection of excellent crop traits.

References

Li, L., Hassan, M. A., Song, J., Xie, Y., Rasheed, A., Yang, S., Li, H., Liu, P., Xia, X., He, Z., & Xiao, Y. (2023). UAV-based RGB imagery and ground measurements for high-throughput phenotyping of senescence and QTL mapping in bread wheat. Crop Science, 63(6), 3292–3309. doi: 10.1002/csc2.21086

Qu, Y., Gao, Z., Shang, J., Liu, J., & Casa, R. (2021). Simultaneous measurements of corn leaf area index and mean tilt angle from multi-directional sunlit and shaded fractions using downward-looking photography. Computers and Electronics in Agriculture, 180, 105881. doi: 10.1016/j.compag.2020.105881

Elli, E. F., Edwards, J., Yu, J., Trifunovic, S., Eudy, D. M., Kosola, K. R., Schnable, P. S., Lamkey, K. R., & Archontoulis, S. V. (2023). Maize leaf angle genetic gain is slowing down in the last decades. Crop Science, 63(6), 3520–3533. doi: 10.1002/csc2.21111

Li, Z., Guo, R., Li, M., Chen, Y., & Li, G. (2020). A review of computer vision technologies for plant phenotyping. Computers and Electronics in Agriculture, 176, 105672. doi: 10.1016/j.compag.2020.105672

Zhao Q, Zang H, Li G, Wang J, & Hu F. (2019). Research on data acquisition system of crop phenotypic traits based on Android. Henan Agricultural Science, 48(8), 175–180. doi: 10.15933/j.cnki.1004-3268.2019.08.026

Yang H, Sun A, Hu Ch, & He H. (2015). Research on the measurement of rice stem-leaf angle based on image vision. Bulletin of science and technology, 31(5), 81-85. doi: 10.13774/j.cnki.kjtb.2015.05.018

Lu W, Zhao Y, Luo B, Pan D, & Wang C. (2015). Rice flag leaf angle measurement system based on Android mobile phone. Journal of Agricultural Machinery, 46(11), 296-301. doi: 10.6041/j.issn.1000-1298.2015.11.040

Zhuang Z., Lu Z., Huang Z., Liu C., Qin W., & School of Mechanical Engineering, Shanghai Jiao Tong University, 200240, Shanghai, China. (2019). School of Mechanical Engineering, Shanghai Jiao Tong University, 200240, Shanghai, China. Mathematical Biosciences and Engineering, 16(5), 4491–4505. doi: 10.3934/mbe.2019224

Kenchanmane Raju, S. K., Adkins, M., Enersen, A., Santana De Carvalho, D., Studer, A. J., Ganapathysubramanian, B., Schnable, P. S., & Schnable, J. C. (2020). Leaf Angle eXtractor: A high‐throughput image processing framework for leaf angle measurements in maize and sorghum. Applications in Plant Sciences, 8(8), e11385. doi: 10.1002/aps3.11385

Zhao P, & Wu Y. (2023). Improved detection of human key points of KAPAO. Journal of Electronic Measurement and Instrumentation, 37(7), 177-185.

doi: 10.13382/j.jemi.B2306196

Chen H, Song Q, Chang T, Zheng L, Zhu X, Zhang M, & Wang M. (2023). Phenotypic parameters extraction of single-tiller rice based on YOLOv5m and CBAM-CPN. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 1-8. doi: 10.11975/j.issn.1002-6819.202304126.

Wu, Z., Xia, F., Zhou, S., & Xu, D. (2023). A method for identifying grape stems using keypoints. Computers and Electronics in Agriculture, 209, 107825.

doi: 10.1016/j.compag.2023.107825.

Periyasamy, A. S., Amini, A., Tsaturyan, V., & Behnke, S. (2023). YOLOPose V2: Understanding and improving transformer-based 6D pose estimation. Robotics and Autonomous Systems, 168, 104490.

doi: 10.1016/j.robot.2023.104490.

Ma M, Ma H, & Song H. (2023). Pedestrian pose estimation algorithm of small target in urban street scene based on YOLO-Pose. Computer Engineering, 1–11.

doi: 10.19678/j.issn.1000-3428.0067733.

Zhang L & Yu S. (2023). CornerNet-Ghost : Lightweight object detection model based on Hourglass-Ghost. Computer applications and software, 40(9), 236-241.

doi: 10.3969/j.issn.1000-386x.2023.09.037.

Kong Y, Qin Y, & Zhang K. (2023). Deep learning based two-dimension human pose estimation: a critical analysis. Journal of Image and Graphics, 28(07): 1965-1989.

doi: 10. 11834/jig. 220436

Cheng, Y., Li, Y., Zhang, R., Gui, Z., Dong, C., & Ma, R. (2023). Locating Tea Bud Keypoints by Keypoint Detection Method Based on Convolutional Neural Network. Sustainability, 15(8), 6898.

doi: 10.3390/su15086898.

Ren Y, Luo J, & Liang X. (2021). Algorithm for Detecting Occluded Basketball Players Based on Adaptive Keypoint Heatmap. Journal of Computer Aided Design and Graphics, 33(9), 1450-1456.

doi: 10.3724/SP.J.1089.2021.18707

Xu H, Yang H, Li Y, Zhang W, Zhao Y, & Wu Q. (2023). Detecting the key points of tractor drivers under complex environments using improved YOLO-Pose. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(16): 139-149.

doi: 10.11975/j.issn.1002-6819.202305146

Wang, W., Zhang, W., Zhang, H., & Zhang, A. (2024). Research on parking space detection algorithm in complex environments based on improved YOLOv7. Measurement Science and Technology, 35(2), 025403.

doi: 10.1088/1361-6501/ad0b68

Hua C, Sun M, Jiang Y, Yu J, & Chen Y. (2023). Multispectral apple surface defect detection based on improved YOLOv7-tiny. Laser & Optoelectronics Progress, 1-15.

doi: 10.3788/LOP231895

Chen, J., Ma, B., Ji, C., Zhang, J., Feng, Q., Liu, X., & Li, Y. (2023). Apple inflorescence recognition of phenology stage in complex background based on improved YOLOv7. Computers and Electronics in Agriculture, 211, 108048.

doi: 10.1016/j.compag.2023.108048

Liu, P., Wang, Q., Zhang, H., Mi, J., & Liu, Y. (2023). A Lightweight Object Detection Algorithm for Remote Sensing Images Based on Attention Mechanism and YOLOv5s. Remote Sensing, 15(9), 2429.

doi: 10.3390/rs15092429

Liu Q, Yin W, & Li K. (2023). Research on image preprocessing acceleration method based on RISC-V vector extension. Journal of Beijing University of Aeronautics and Astronautics, 1-15.

doi: 10.13700/j.bh.1001-5965.2023.0208

Bao, W., Niu, T., Wang, N., & Yang, X. (2023). Pose estimation and motion analysis of ski jumpers based on ECA-HRNet. Scientific Reports, 13(1), 6132.

doi: 10.1038/s41598-023-32893-x

Zhang, M., Zhang, K., Yu, D., Xie, Q., Liu, B., Chen, D., Xv, D., Li, Z., & Liu, C. (2021). Computerized assisted evaluation system for canine cardiomegaly via key points detection with deep learning. Preventive Veterinary Medicine, 193, 105399. doi: 10.1016/j.prevetmed.2021.105399

Huang, C., Lei, Z., Li, L., Zhong, L., Lei, J., & Wang, S. (2023). A Method for Detecting Key Points of Transferring Barrel Valve by Integrating Keypoint R-CNN and MobileNetV3. Electronics, 12(20), 4306.

doi: 10.3390/electronics12204306

Du, Z., Xu, X., Bai, Z., Liu, X., Hu, Y., Li, W., Wang, C., & Li, D. (2023). Feature fusion strategy and improved GhostNet for accurate recognition of fish feeding behavior. Computers and Electronics in Agriculture, 214, 108310.

doi: 10.1016/j.compag.2023.108310

[29] Lei, Y., Pan, D., Feng, Z., & Qian, J. (2023). Lightweight YOLOv5s Human Ear Recognition Based on MobileNetV3 and Ghostnet. Applied Sciences, 13(11), 6667.

doi: 10.3390/app13116667.