Extracting Jinggang pomelo tree information and estimating yield based on Unmanned Aerial Vehicle (UAV) imageries

doi:10.13733/j.jcam.issn.2095-5553.2024.05.025

Abstract

Abstract: In order to realize the rapid and accurate extraction of tree shape information (crown width and tree height) and yield prediction of Jinggang pomelo fruit tree based on the Unmanned Aerial Vehicle (UAV) imageries. By generating Digital Orthophoto map (DOM) based on the UAV imageries, four vegetation indexes were calculated and the accuracy of crown width extraction by threshold segmentation of four vegetation index was analyzed. The sensitive vegetation index and its best classification threshold was determined to complete the extraction of vegetation area and realize the crown width extraction. Then, based on the digital elevation model (DEM) generated by UAV imageries, the tree height of fruit trees was extracted. Finally, three models of crown width, tree height and crown width + tree height were used to predict yield. The results showed that the normalized difference index (NDI) had the highest accuracy in extracting crown width. The coefficients of determination R2 between the extracted EastWest crown width and the measured value was 0.917 2, the R2 between the NorthSouth crown width and the measured value was 0.823 6, and the R2 between the mean of crown width and the measured value was 0.892 8. When extracting tree height based on DEM, it also had a good effect. The R2 between the extracted tree height and the measured value is 0.863 3, and the root mean square error (RMSE) is 0.148 m. The yield prediction results showed that the R2 of using crown width + tree height to predict the number of fruits was 0.676, and the adjusted R2 was 0.638, which had the best prediction effect.

Key words: Jinggang pomelo, fruit trees detection, UAV remote sensing, vegetation index, yield estimation model

摘要： 为实现基于无人机影像的井冈蜜柚果树树形信息(冠幅、树高)快速、准确提取及产量预测，通过基于无人机影像生成数字正射影像(DOM)，计算4个植被指数，分析4个植被指数阈值分割提取冠幅的精度，确定敏感植被指数及其最佳分类阈值完成植被区域的提取，实现冠幅提取；再基于无人机影像生成的数字高程模型(DEM)，提取果树树高；运用“冠幅、树高及冠幅+树高”三种模式对产量进行预测。结果表明，利用归一化差值指数(Normalized Difference Index，NDI)提取冠幅时精度最高，提取的东西冠幅与实测值之间决定系数R2达0.917 2，南北冠幅与实测值之间的R2达0.823 6，冠幅均值与实测值均值之间的R2达0.892 8；基于DEM提取树高时，也具有较好的效果，提取的树高与实测值之间的R2达0.863 3，均方根误差RMSE为0.148 m。进一步运用“冠幅、树高及冠幅+树高”三种模式对挂果数进行预测，运用“冠幅+树高”预测挂果数的R2为0.676，调整R2为0.638，预测效果最好。

关键词: 井冈蜜柚, 果树识别, 无人机遥感, 植被指数, 估产模型

CLC Number:

S252+.9

Luo Xiang, Cao Xiaolin, Yao Lintao, Wu Luofa, Cao Zhongsheng, Shu Shifu. Extracting Jinggang pomelo tree information and estimating yield based on Unmanned Aerial Vehicle (UAV) imageries[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(5): 161-167.

罗翔, 曹晓林, 药林桃, 吴罗发, 曹中盛, 舒时富. 基于无人机影像的井冈蜜柚果树树形信息提取及产量估测[J]. 中国农机化学报, 2024, 45(5): 161-167.

References

［1］　宋彩英, 覃志豪. 吉安市井冈蜜柚产业发展研究［J］. 中国农业资源与区划, 2014, 35(5): 113-116, 122.
Song Caiying, Qin Zhihao. Study on the development of Jinggang candied pomelo industry of Jian City ［J］. Chinese Journal of Agricultural Resources and Regional Planning, 2014, 35(5): 113-116, 122.
［2］　江西省统计局. 江西统计年鉴［M］. 北京: 中国统计出版社, 2021.
［3］　Liang L, Luo X, Liu Z, et al. Habitat selection and prediction of the spatial distribution of the Chinese horseshoe bat (R. sinicus) in the Wuling Mountains ［J］. Environmental Monitoring and Assessment, 2019, 191: 1-15.
［4］　王浩淼, 宋苗语, 李翔, 等. 无人机高光谱遥感监测葡萄长势与缺株定位［J］. 园艺学报, 2021, 48(8): 1626-1634.
Wang Haomiao, Song Miaoyu, Li Xiang, et al. High efficient grapevine growth monitor and inlane deficiency localization by UAV hyperspectral remote sensing ［J］. Acta Horticulturae Sinica, 2021, 48(8): 1626-1634.
［5］　孙逸飞, 柳平增, 张艳, 等. 基于Sentinel-2A遥感影像的潍坊市冬小麦种植面积提取研究［J］. 中国农机化学报, 2022, 43(7): 98-105.
Sun Yifei, Liu Pingzeng, Zhang Yan, et al. Research on extraction of winter wheat planting area in Weifang City based on Sentinel-2A remote sensing image ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(7): 98-105.
［6］　Fletcher R S. Using vegetation indices as input into random forest for soybean and weed classification ［J］. American Journal of Plant Sciences, 2016, 7(15): 2186-2198.
［7］　Luo X, Liang L, Liu Z, et al. Habitat suitability evaluation of the Chinese Horseshoe Bat (R. sinicus) in the Wuling mountain area based on MAXENT Modelling ［J］. Polish Journal of Environmental Studies, 2020, 29(2).
［8］　李福根, 段玉林, 史云, 等. 利用单次无人机影像的果树精准识别方法［J］. 中国农业信息, 2019, 31(4): 10-22.
Li Fugen, Duan Yulin, Shi Yun, et al. Accurate detection of fruit trees using a set of unmanned aerial vehicle(UAV)imageries ［J］. China Agricultural Informatics, 2019, 31(4): 10-22.
［9］　Wan L, Li Y, Cen H, et al. Combining UAV-based vegetation indices and image classification to estimate flower number in oilseed rape ［J］. Remote Sensing, 2018, 10(9): 1484.
［10］　汪沛, 罗锡文, 周志艳, 等. 基于微小型无人机的遥感信息获取关键技术综述［J］. 农业工程学报, 2014, 30(18): 1-12.
Wang Pei, Luo Xiwen, Zhou Zhiyan, et al. Key technology for remote sensing information acquisition based on micro UAV ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(18): 1-12.
［11］　Wu J T, Yang G J, Han L, et al. Automatic counting of in situ rice seedlings from UAV images based on a deep fully convolutional neural network ［J］. Remote Sensing, 2019, 11(6): 691.
［12］　束美艳, 李世林, 魏家玺, 等. 基于无人机平台的柑橘树冠信息提取［J］. 农业工程学报, 2021, 37(1): 68-76.
Shu Meiyan, Li Shilin, Wei Jiaxi, et al. Extraction of citrus crown parameters using UAV platform ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(1): 68-76.
［13］　Panu S, Preesan R. Oil palm tree detection with high resolution multispectral satellite imagery ［J］. Remote Sensing, 2014, 6(10): 9749-9774.
［14］　江洪, 汪小钦, 吴波, 等. 地形调节植被指数构建及在植被覆盖度遥感监测中的应用［J］. 福州大学学报(自然科学版), 2010, 38(4): 527-532.
Jiang Hong, Wang Xiaoqin, Wu Bo, et al. A topographyadjusted vegetation index (TAVI) and its application in vegetation fraction monitoring ［J］. Journal of Fuzhou University (Natural Science), 2010, 38(4): 527-532.
［15］　Victoria G D, Pilar H, Ignacio S, et al. Using highresolution hyperspectral and thermal airborne imagery to assess physiological condition in the context of wheat phenotyping ［J］. Remote Sensing, 2015, 7(10): 13586-13605.
［16］　Shah S H, Angel Y, Houborg R, et al. A random forest machine learning approach for the retrieval of leaf chlorophyll content in wheat ［J］. Remote Sensing, 2019, 11(8): 920.
［17］　Woebbecke D M, Meyer G E, Von Bargen K, et al. Plant species identification, size, and enumeration using machine vision techniques on nearbinary images ［C］. Optics in Agriculture and Forestry, SPIE, 1993, 1836: 208-219.
［18］　Louhaichi M, Borman M M, Johnson D E. Spatially located platform and aerial photography for documentation of grazing impacts on wheat ［J］. Geocarto International, 2001, 16(1): 65-70.
［19］　Gitelson A A, Zur Y, Chivkunova O B, et al. Assessing carotenoid content in plant leaves with reflectance spectroscopy ［J］. Photochemistry and Photobiology, 2002, 75(3): 272-281.
［20］　谭文学, 赵春江, 吴华瑞, 等. 基于弹性动量深度学习神经网络的果体病理图像识别［J］. 农业机械学报, 2015, 46(1): 20-25.
Tan Wenxue, Zhao Chunjiang, Wu Huarui, et al. A deep learning network for recognizing fruit pathologic images based on flexible momentum ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(1): 20-25.
［21］　孙钰, 周焱, 袁明帅, 等. 基于深度学习的森林虫害无人机实时监测方法［J］. 农业工程学报, 2018, 34(21):74-81.
Sun Yu, Zhou Yan, Yuan Mingshuai, et al. UAV realtime monitoring for forest pest based on deep learning ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(21): 74-81.
［22］　沈萍, 赵备. 基于深度学习模型的花卉种类识别［J］. 科技通报, 2017, 33(3): 115-119.Shen Ping, Zhao Bei. Automatic classification of flowers based on deep learning model ［J］. Bulletin of Science and Technology, 2017, 33(3): 115-119.
［23］　王术波, 韩宇, 陈建, 等. 基于深度学习的无人机遥感生态灌区杂草分类［J］. 排灌机械工程学报, 2018, 36(11): 1137-1141.
Wang Shubo, Han Yu, Chen Jian, et al. Weed classification of remote sensing by UAV in ecological irrigation areas based on deep learning ［J］. Journal of Drainage and Irrigation Machinery Engineering, 2018, 36(11): 1137-1141.
［24］　Houborg R, McCabe M F. A hybrid training approach for leaf area index estimation via Cubist and random forests machinelearning ［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 135: 173-188.
［25］　Liang L, Sun Q, Luo X, et al. Longterm spatial and temporal variations of vegetative drought based on vegetation condition index in China ［J］. Ecosphere, 2020, 8(8): e01919.
［26］　Shao G, Tang L, Liao J. Overselling overall map accuracy misinforms about research reliability ［J］. Landscape Ecology, 2019, 34: 2487-2492.
［27］　刘云萌, 刘云霞, 曾广旭, 等. 基于GIS的吉安地区井冈蜜柚特色果业种植气候区划［J］. 江西农业学报, 2015, 27(6): 130-133.
Liu Yunmeng, Liu Yunxia, Zeng Guangxu, et al. Climatic regionalization of Jinggang pomelo planting in Jian area based on GIS ［J］. Acta Agriculturae Jiangxi, 2015, 27(6): 130-133.
［28］　万祖毅. 基于无人机遥感的柑橘果树信息提取及应用研究［D］. 重庆: 西南大学, 2020.Wan Zuyi. Extraction and application of citrus fruit tree information based on UAV remote sensing ［D］. Chongqing: Southwest University, 2020.
［29］　吴强建, 肖委明, 赵晓东, 等. 江西井冈蜜柚种植区果园土壤肥力现状及区域分布特征［J］. 农业资源与环境学报, 2022(5): 1025-1032.
Wu Qiangjian, Xiao Weiming, Zhao Xiaodong, et al. Status, spatial distribution, and fertility of soil in pomelo orchards in Jinggang, Jiangxi Province ［J］. Journal of Agricultural Resources and Environment, 2022(5): 1025-1032.

[1]	Zhao Shengli, , , Wang Guobin, , , Hu Lianbin, , , Xu Haiyu, , , Gong Daocai, , , Lan Yubin, , . Estimation of cotton growth parameters and yield based on UAV multi-spectral remote sensing [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 227-234.
[2]	Li Yanzhou, He Yanzhou, , Qin Feng, , Qian Wanqiang, Wu Mei, Qiao Xi, . Identification of Spartina alterniflora based on convolutional neural network [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(4): 159-166.
[3]	Li Zhibo, Li Yaqin, Zhao Huanmin, Wang Junfa, Ge Yiyuan, Qiu Xinwei.. Study on the decisionmaking scheme of soilrice canopy variable nitrogen application based on GNDVI index [J]. Journal of Chinese Agricultural Mechanization, 2022, 43(4): 160-165.