Application of UAV Aerial Photo Data in Forest Information Extraction

doi:10.13466/j.cnki.lyzygl.2021.03.025

Abstract

Abstract:

In this study,the UAV images of pine forest in Shazikou Street,Laoshan District,Qingdao City,Shandong Province were captured in the spring and autumn of 2020.The optimal scale for the segmentation of DOM images was confirmed with ESP auxiliary tools.Decision trees for identifying the changing area were constructed using fuzzy classification.The watershed algorithm was used to rapidly extract the changes in the number of living trees in the pine forest.The results showed that the number of living trees decreased by 205 in 6 locations of the study area.Based on field surveys,217 trees were reduced,and the accuracy for detecting the changes of living trees was 92.3%.These results demonstrated that high-resolution UAV images could facilitate the rapid and accurate monitor of changes of trees in forests,thereby having great potential for forestry resource investigation,pinewood nematode disease monitoring and disaster assessment,especially for areas with high altitude and dangerous road,it can replace manual survey.

Key words: UAV, segmentation scale, decision tree, watershed algorithm, information extraction

CLC Number:

S771.8
TP75

SUN Yujiang, LI Fengtao, CHEN Xiangqin, ZHANG Lei, YANG Ning, ZHENG Da. Application of UAV Aerial Photo Data in Forest Information Extraction[J]. FOREST RESOURCES WANAGEMENT, 2021, 0(3): 160-164.

Figures/Tables 7

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.1

References 17

[1]	汪霖, 李明阳, 方子涵, 等. 基于无人机数据的人工林森林参数估测[J]. 林业资源管理, 2019(5):61-67.
[2]	付凯婷. 无人机遥感技术估算桉树蓄积量的研究[D]. 南宁:广西大学, 2015:48-50.
[3]	陈崇成, 李旭, 黄洪宇. 基于无人机影像匹配点云的苗圃单木冠层三维分割[J]. 农业机械学报, 2018, 49(2):149-155.
[4]	Wang L, Gong P, Biging G S. Individual Tree-Crown Delineation and Treetop Detection in High-Spatial-Resolution Aerial Imagery[J]. Photogrammetric Engineering & Remote Sensing, 2004, 70(3):351-358.
[5]	董天阳, 周棋正. 基于形态Snake模型的遥感影像的单木树冠检测算法[J]. 计算机科学, 2018, 45(S2):269-273.
[6]	Culvenor D S. TIDA:an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery[J]. Computers & Geosciences, 2002, 28(1):33-44. doi: 10.1016/S0098-3004(00)00110-2
[7]	王枚梅, 林家元, 林沂, 等. 基于无人机可见光影像的亚高山针叶林树冠参数信息自动提取[J]. 林业资源管理, 2017(4):82-88.
[8]	仇江啸, 王效科. 基于高分辨率遥感影像的面向对象城市土地覆被分类比较研究[J]. 遥感技术与应用, 2010, 25(5):653-661.
[9]	李秦, 高锡章, 张涛, 等. 最优分割尺度下的多层次遥感地物分类实验分析[J]. 地球信息科学学报, 2011, 13(3):409-417. doi: 10.3724/SP.J.1047.2011.00409
[10]	邓书斌. ENVI 遥感图像处理方法[M]. 北京: 科学出版社, 2014.
[11]	杨帆, 王博. 基于决策树的遥感图像分类方法研究[J]. 测绘与空间地理信息, 2019, 42(7):1-4.
[12]	汪小钦, 王苗苗, 王绍强, 等. 基于可见光波段无人机遥感的植被信息提取[J]. 农业工程学报, 2015, 31(5):152-159.
[13]	Vincent L, Soille P. Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6):583-598. doi: 10.1109/34.87344
[14]	Bieniek A, Moga A. An efficient watershed algorithm based on connected components[J]. Pattern Recognition, 2000, 33(6):907-916. doi: 10.1016/S0031-3203(99)00154-5
[15]	沈夏炯, 吴晓洋, 韩道军. 分水岭分割算法研究综述[J]. 计算机工程, 2015, 41(10):26-30.
[16]	Lucian D, Tiede D, Levick S R. ESP:A tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data[J]. International Journal of Geographical Information Science, 2010, 24(6):859-871. doi: 10.1080/13658810903174803
[17]	鲁恒, 李永树, 何敬, 等. 无人机低空遥感影像数据的获取与处理[J]. 测绘工程, 2011, 20(1):51-54.

区域名称	面积/hm²	数据提取		实际核查		误差率/%
区域名称	面积/hm²	提取数量/株	减少密度/(株/hm²)	砍伐数量/株	减少密度/(株/hm²)	误差率/%
区域1	0.0427	87	2039	90	2109	3.33
区域2	0.0160	33	2063	35	2188	5.71
区域3	0.0080	17	2125	15	1875	6.67
区域4	0.0127	26	2053	30	2368	13.30
区域5	0.0113	23	2029	25	2206	8.00
区域6	0.0140	20	1429	22	1571	9.09
平均值	0.0174	34.33	1956.20	36.17	2052.93	7.68