Rubber Tree Recognition Based on UAV RGB Multi-Angle Imagery and Deep Learning

被引:4
作者
Liang, Yuying [1 ]
Sun, Yongke [1 ]
Kou, Weili [1 ,2 ]
Xu, Weiheng [1 ,2 ]
Wang, Juan [3 ]
Wang, Qiuhua [4 ]
Wang, Huan [1 ]
Lu, Ning [1 ,2 ]
机构
[1] Southwest Forestry Univ, Coll Big Data & Intelligence Engn, Kunming 650223, Peoples R China
[2] Key Lab Natl Forestry & Grassland Adm Forestry & E, Kunming 650223, Peoples R China
[3] Southwest Forestry Univ, Ecodev Acad, Kunming 650223, Peoples R China
[4] Southwest Forestry Univ, Coll Civil Engn, Kunming 650223, Peoples R China
关键词
rubber plantation; UAV; deep learning; defoliation period; multi-angle images; recognition; NETWORK; XISHUANGBANNA; PLANTATIONS; CROWN;
D O I
10.3390/drones7090547
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
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 & DEG;, -60 & DEG;, 45 & DEG;) 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 & DEG; 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.
引用
收藏
页数:20
相关论文
共 60 条
[1]   Estimation of spinach (Spinacia oleracea) seed yield with 2D UAV data and deep learning [J].
Ariza-Sentis, Mar ;
Valente, Joao ;
Kooistra, Lammert ;
Kramer, Henk ;
Mucher, Sander .
SMART AGRICULTURAL TECHNOLOGY, 2023, 3
[2]   Application of Optical Remote Sensing in Rubber Plantations: A Systematic Review [J].
Azizan, Fathin Ayuni ;
Kiloes, Adhitya Marendra ;
Astuti, Ike Sari ;
Abdul Aziz, Ammar .
REMOTE SENSING, 2021, 13 (03) :1-36
[3]   A fast and robust method for plant count in sunflower and maize at different seedling stages using high-resolution UAV RGB imagery [J].
Bai, Yi ;
Nie, Chenwei ;
Wang, Hongwu ;
Cheng, Minghan ;
Liu, Shuaibing ;
Yu, Xun ;
Shao, Mingchao ;
Wang, Zixu ;
Wang, Siyu ;
Tuohuti, Nuremanguli ;
Shi, Lei ;
Ming, Bo ;
Jin, Xiuliang .
PRECISION AGRICULTURE, 2022, 23 (05) :1720-1742
[4]   Automatic Delineation and Height Measurement of Regenerating Conifer Crowns under Leaf-Off Conditions Using UAV Imagery [J].
Chadwick, Andrew J. ;
Goodbody, Tristan R. H. ;
Coops, Nicholas C. ;
Hervieux, Anne ;
Bater, Christopher W. ;
Martens, Lee A. ;
White, Barry ;
Roeser, Dominik .
REMOTE SENSING, 2020, 12 (24) :1-26
[5]   High-Precision Stand Age Data Facilitate the Estimation of Rubber Plantation Biomass: A Case Study of Hainan Island, China [J].
Chen, Bangqian ;
Yun, Tin ;
Ma, Jun ;
Kou, Weili ;
Li, Hailiang ;
Yang, Chuan ;
Xiao, Xiangming ;
Zhang, Xian ;
Sun, Rui ;
Xie, Guishui ;
Wu, Zhixiang .
REMOTE SENSING, 2020, 12 (23) :1-20
[6]   Transformer for Tree Counting in Aerial Images [J].
Chen, Guang ;
Shang, Yi .
REMOTE SENSING, 2022, 14 (03)
[7]  
[陈优良 Chen Youliang], 2022, [测绘科学, Science of Surveying and Mapping], V47, P135
[8]  
Chen Zi Yan, 2020, International Journal of Machine Learning and Computing, V10, P122, DOI 10.18178/ijmlc.2020.10.1.908
[9]   Identification of Citrus Trees from Unmanned Aerial Vehicle Imagery Using Convolutional Neural Networks [J].
Csillik, Ovidiu ;
Cherbini, John ;
Johnson, Robert ;
Lyons, Andy ;
Kelly, Maggi .
DRONES, 2018, 2 (04) :1-16
[10]  
Djerriri K, 2018, INT GEOSCI REMOTE SE, P2627, DOI 10.1109/IGARSS.2018.8519188