Rubber Tree Recognition Based on UAV RGB Multi-Angle Imagery and Deep Learning
Author:
Liang Yuying1, Sun Yongke1, Kou Weili12ORCID, Xu Weiheng12ORCID, Wang Juan3, Wang Qiuhua4, Wang Huan1, Lu Ning12ORCID
Affiliation:
1. College of Big Data and Intelligence Engineering, Southwest Forestry University, Kunming 650223, China 2. Key Laboratory of National Forestry and Grassland Administration on Forestry and Ecological Big Data, Kunming 650223, China 3. Eco-Development Academy, Southwest Forestry University, Kunming 650223, China 4. College of Civil Engineering, Southwest Forestry University, Kunming 650223, China
Abstract
The rubber tree (Hevea brasiliensis) is an important tree species for the production of natural latex, which is an essential raw material for varieties of industrial and non-industrial products. Rapid and accurate identification of the number of rubber trees not only plays an important role in predicting biomass and yield but also is beneficial to estimating carbon sinks and promoting the sustainable development of rubber plantations. However, the existing recognition methods based on canopy characteristic segmentation are not suitable for detecting individual rubber trees due to their high canopy coverage and similar crown structure. Fortunately, rubber trees have a defoliation period of about 40 days, which makes their trunks clearly visible in high-resolution RGB images. Therefore, this study employed an unmanned aerial vehicle (UAV) equipped with an RGB camera to acquire high-resolution images of rubber plantations from three observation angles (−90°, −60°, 45°) and two flight directions (SN: perpendicular to the rubber planting row, and WE: parallel to rubber planting rows) during the deciduous period. Four convolutional neural networks (multi-scale attention network, MAnet; Unet++; Unet; pyramid scene parsing network, PSPnet) were utilized to explore observation angles and directions beneficial for rubber tree trunk identification and counting. The results indicate that Unet++ achieved the best recognition accuracy (precision = 0.979, recall = 0.919, F-measure = 94.7%) with an observation angle of −60° and flight mode of SN among the four deep learning algorithms. This research provides a new idea for tree trunk identification by multi-angle observation of forests in specific phenological periods.
Funder
National Natural Science Foundation of China Key Laboratory of National Forestry and Grassland Administration on Forestry and Ecological Big Data, Southwest Forestry University Joint Special Project for Agriculture of Yunnan Province Scientific Research Foundation for Ph.D. of Southwest Forestry University Research Foundation for Basic Research of Yunnan Province Youth Top Talents of Yunnan Ten Thousand Talents Program
Subject
Artificial Intelligence,Computer Science Applications,Aerospace Engineering,Information Systems,Control and Systems Engineering
Reference60 articles.
1. Chen, B., Yun, T., Ma, J., Kou, W., Li, H., Yang, C., Xiao, X., Zhang, X., Sun, R., and Xie, G. (2020). High-precision stand age data facilitate the estimation of rubber plantation biomass: A case study of Hainan Island, China. Remote Sens., 12. 2. Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery;Liang;Ecol. Indic.,2022 3. Biomass and its estimation model of rubber plantations in Xishuangbanna, Southwest China;Tang;Chin. J. Ecol.,2009 4. Expansion dynamics of deciduous rubber plantations in Xishuangbanna, China during 2000–2010;Kou;GISci. Remote Sens.,2018 5. Azizan, F.A., Kiloes, A.M., Astuti, I.S., and Abdul Aziz, A. (2021). Application of optical remote sensing in rubber plantations: A systematic review. Remote Sens., 13.
|
|