Rapeseed Stand Count Estimation at Leaf Development Stages With UAV Imagery and Convolutional Neural Networks

Authors

Biquan Zhao, Huazhong Agricultural University, Wuhan & Ministry of Agriculture, Wuhan
Chenghai Yang, USDA-Agricultural Research Service, College Station
Yeyin Shi, University of Nebraska-LincolnFollow
Qingxi Liao, Huazhong Agricultural University, Wuhan
Guangsheng Zhou, Huazhong Agricultural University, Wuhan
Chufeng Wang, Huazhong Agricultural University, Wuhan & Ministry of Agriculture, Wuhan
Tianjin Xie, Huazhong Agricultural University, Wuhan & Ministry of Agriculture, Wuhan
Zhao Jiang, Huazhong Agricultural University, Wuhan & Ministry of Agriculture, Wuhan
Dongyan Zhang, Anhui University, Hefei
Wanneng Yang, Huazhong Agricultural University, Wuhan
Chenglong Huang, Huazhong Agricultural University, WuhanFollow
Jing Xie, Huazhong Agricultural UniversityFollow
Jian Zhang, Huazhong Agricultural University, Wuhan & Ministry of Agriculture, Wuhan

Document Type

Article

Date of this Version

2020

Citation

Zhang J, Zhao B, Yang C, Shi Y, Liao Q, Zhou G, Wang C, Xie T, Jiang Z, Zhang D, Yang W, Huang C and Xie J (2020) Rapeseed Stand Count Estimation at Leaf Development Stages With UAV Imagery and Convolutional Neural Networks. Front. Plant Sci. 11:617. doi: 10.3389/fpls.2020.00617

Comments

2020 Zhang, Zhao, Yang, Shi, Liao, Zhou, Wang, Xie, Jiang, Zhang, Yang, Huang and Xie.

Abstract

Rapeseed is an important oil crop in China. Timely estimation of rapeseed stand count at early growth stages provides useful information for precision fertilization, irrigation, and yield prediction. Based on the nature of rapeseed, the number of tillering leaves is strongly related to its growth stages. However, no field study has been reported on estimating rapeseed stand count by the number of leaves recognized with convolutional neural networks (CNNs) in unmanned aerial vehicle (UAV) imagery. The objectives of this study were to provide a case for rapeseed stand counting with reference to the existing knowledge of the number of leaves per plant and to determine the optimal timing for counting after rapeseed emergence at leaf development stages with one to seven leaves. A CNN model was developed to recognize leaves in UAV-based imagery, and rapeseed stand count was estimated with the number of recognized leaves. The performance of leaf detection was compared using sample sizes of 16, 24, 32, 40, and 48 pixels. Leaf overcounting occurred when a leaf was much bigger than others as this bigger leaf was recognized as several smaller leaves. Results showed CNN-based leaf count achieved the best performance at the four- to six-leaf stage with F-scores greater than 90% after calibration with overcounting rate. On average, 806 out of 812 plants were correctly estimated on 53 days after planting (DAP) at the four- to sixleaf stage, which was considered as the optimal observation timing. For the 32-pixel patch size, root mean square error (RMSE) was 9 plants with relative RMSE (rRMSE) of 2.22% on 53 DAP, while the mean RMSE was 12 with mean rRMSE of 2.89% for all patch sizes. A sample size of 32 pixels was suggested to be optimal accounting for balancing performance and efficiency. The results of this study confirmed that it was feasible to estimate rapeseed stand count in field automatically, rapidly, and accurately. This study provided a special perspective in phenotyping and cultivation management for estimating seedling count for crops that have recognizable leaves at their early growth stage, such as soybean and potato.