欢迎访问林草资源研究
Practice Discussion

Single-Tree Crown Delineation in Plain Afforestation Areas Based on Mask R-CNN

  • Yuanjun XING ,
  • Kunjian WEN ,
  • Xiaoni GUO ,
  • Yabin SONG ,
  • Zhongyue HU ,
  • Tengyu JIANG ,
  • Zijing HE
Expand
  • Central South Academy of Inventory and Planning of National Forestry and Grassland Administration,Changsha 410000,China

Received date: 2023-04-19

  Revised date: 2023-05-17

  Online published: 2023-08-09

Abstract

This paper aims to investigate an automated approach for extracting spatial distribution and quantities of planted trees in plain areas by using of visible light imagery obtained from unmanned aerial vehicles.Specifically,the study focuses on analyzing afforestation patches located in Huailai,Zhangjiakou,Hebei Province.To achieve this,a manually constructed single-tree crown dataset was utilized to train and predict Mask R-CNN models with varying backbone networks(R50-FPN-1x,R50-FPN-3x,R101-FPN-3x),and their accuracies were compared on an independent test set.Results indicate that all backbone models were able to segment tree crowns in the afforested areas,with the R101-FPN-3x model achieving the highest accuracy of 75.33% and a recall rate of 73.23%.The results showed that the single tree segmentation method based on Mask R-CNN from UAV images could quickly and accurately detect single tree targets in afforestation areas automatically,and effectively segment single tree crown to map the crown contour,which could meet the needs of efficient investigation and monitoring in small and medium-sized plain afforestation areas.

Cite this article

Yuanjun XING , Kunjian WEN , Xiaoni GUO , Yabin SONG , Zhongyue HU , Tengyu JIANG , Zijing HE . Single-Tree Crown Delineation in Plain Afforestation Areas Based on Mask R-CNN[J]. Forest and Grassland Resources Research, 2023 , 0(3) : 115 -120 . DOI: 10.13466/j.cnki.lyzygl.2023.03.015

References

[1] 国务院办公厅关于科学绿化的指导意见[J]. 中华人民共和国国务院公报, 2021(17):178-182.
[2] 刘晓双, 李才文, 龚直文. 营造林成效遥感监测方法适用性研究[J]. 西北林学院学报, 2021, 36(3):203-209.
[3] 梅浩. 基于造林综合核查的营造林质量问题研究[D]. 长沙: 中南林业科技大学, 2018.
[4] 于晓光, 王小昆, 蒋爱军, 等. 中高分辨率遥感影像在营造林成效监测应用中的探讨[J]. 林业资源管理, 2012(5):59-63.
[5] 桂来庭, 张万林, 洪加凤, 等. 全国营造林综合核查技术体系与抽样方法[J]. 中南林业调查规划, 2011, 30(4):1-4.
[6] 王小昆, 王耀, 于世勇, 等. 基于遥感技术的全国营造林监测体系建设构想[J]. 林业资源管理, 2020(5):52-57.
[7] Jurado J M, López A, Pádua L, et al. Remote sensing image fusion on 3D scenarios:A review of applications for agriculture and forestry[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112:102856.
[8] 封晓然, 尚丽晨, 李小龙, 等. 基于无人机影像的营造林核查应用研究[J]. 林业科技, 2020, 45(3):43-47.
[9] 王黎. 航测技术在营造林综合核查中的应用[J]. 山西林业科技, 2017, 46(2):58-60.
[10] 徐伟萌, 杨浩, 李振洪, 等. 利用无人机数码影像进行密植型果园单木分割[J]. 武汉大学学报:信息科学版, 2022, 47(11):1906-1916.
[11] 罗盛万, 蓝晓丹, 兰必赛. 无人机低空摄影测量在国家储备林基地检查验收中的应用试验研究[J]. 林业调查规划, 2020, 45(4):9-13.
[12] 杜澄举, 李赛楠, 孙思, 等. 无人机低空遥感技术辅助高精度造林[J]. 林业与环境科学, 2019, 35(1):49-53.
[13] 王丽文, 朱正礼, 云挺. 基于改进YOLOv3的单木树冠检测算法[J]. 计算机仿真, 2023, 40(1):510-516.
[14] 马永康, 刘华, 凌成星, 等. 基于改进YOLOv5的红树林单木目标检测研究[J]. 激光与光电子学进展, 2022, 59(18):436-446.
[15] Gil-Docampo M L, Ortiz-Sanz J, Martínez-Rodríguez S, et al. Plant survival monitoring with UAVs and multispectral data in difficult access afforested areas[J]. Geocarto International, 2020, 35(2):128-140.
[16] 谢运鸿, 荆雪慧, 孙钊, 等. 基于实例分割的高郁闭度林分单木树冠无人机遥感提取[J]. 林业科学研究, 2022, 35(5):14-21.
[17] Yu Kunyong, Hao Zhenbang, Post C J, et al. Comparison of classical methods and Mask R-CNN for automatic tree detection and mapping using UAV imagery[J]. Remote Sensing, 2022, 14(2):295.
[18] He Kaiming, Gkioxari G, Piotr Dollár, et al. Mask R-CNN[C]// Proceedings of the IEEE international conference on computer vision.Venice:IEEE, 2017:2980-2988.
Outlines

/