<trans-title>Research on Recognition Methods of Elm Sparse Forest based on Object-based Image Analysis and Deep Learning</trans-title>

Ang CHEN; Xiuchun YANG; Bin XU; Yunxiang JIN; Wenbo ZHANG; Jian GUO; Xiaoyu XING; Dong YANG

doi:10.12082/dqxxkx.2019.190598

Journal of Geo-information Science, Volume. 22, Issue 9, 1897(2020)

Research on Recognition Methods of Elm Sparse Forest based on Object-based Image Analysis and Deep Learning

Ang CHEN¹, Xiuchun YANG^1,2、*, Bin XU^1,2, Yunxiang JIN¹, Wenbo ZHANG¹, Jian GUO¹, Xiaoyu XING¹, and Dong YANG¹

¹Key Laboratory of Agri-informatics, Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China

²College of Grassland Science, Beijing Forestry University, Beijing 100083, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(16)

Fig. 1. Location map of study area in Hunshandake sandy land

Download full size

View in Article

Fig. 2. Flow chart of research methods

Download full size

View in Article

Fig. 3. Deep learning training samples

Download full size

View in Article

Fig. 4. LV and LV-ROC Curves of UAV Image

Download full size

View in Article

Fig. 5. Optimum segmentation of elm sparse forest in UAV image

Download full size

View in Article

Fig. 6. LV and LV-ROC Curves of GF-2 Image

Download full size

View in Article

Fig. 7. Optimum segmentation of elm sparse forest in GF-2 image

Download full size

View in Article

Fig. 8. Sequencing of the Importance of UAV image features

Download full size

View in Article

Fig. 9. Sequencing of the Importance of GF-2image features

Download full size

View in Article

Fig. 10. Accuracy comparison of SVM、RF、DNN used in OBIA

Download full size

View in Article

Fig. 11. Accuracy comparison between object-based method and deep learning method

Download full size

View in Article

Fig. 12. Comparison of extraction result between OBIA and deep learning for elm sparse forest

Download full size

View in Article

Table 1. UAV flight parameters
View table
View in Article
Table 1. UAV flight parameters
飞行航高/m 飞行海拔/m 飞行速度/(km/h) 航向重叠度/% 旁向重叠度/% 地面分辨率/m 相片数/张测量面积/km² 外扩面积/km²
610 1919 60 75 65 0.1 2452 47 0.12

Table 2. Feature list in OBIA

View table

View in Article

Table 2. Feature list in OBIA

特征类型	特征指标
特征类型	无人机	GF-2
指数特征	VDVI、NGRDI、NGBDI、RGRI、EXG	NDVI、MSAVI
光谱特征	Mean red、mean green、mean blue、mean H、mean L、mean S、std.dev.red、std.dev.green、std.dev.blue、std.dev.H、sed.dev.S、std.dev.L、brightness、max.diff	Mean red、mean green、mean blue、mean NIR、std.dev.red、std.dev.green、std.dev.blue、std.dev.NIR、brightness、max.diff
冠层高度特征	mean CHM	无
纹理特征	GLCM (Gray-Level Co-occurrence Matrix) homogeneity、GLCM contrast、GLCM dissimilarity、GLCM entropy、GLCM std. dev.、GLCM correlation、GLCM ang. 2nd moment、GLCM mean
形状特征	Area、number of pixels、border index、shape index、roundness、length/width

Table 3. Results of GF-2 image using deep learning method
View table
View in Article
Table 3. Results of GF-2 image using deep learning method
类别背景地物榆树疏林总计
背景地物 292 5 317
榆树疏林 58 325 383
总计 350 350 700
总体精度/% 91.00
Kappa 0.82

Table 4. Results of UAV image using deep learning method
View table
View in Article
Table 4. Results of UAV image using deep learning method
类别背景地物榆树疏林总计
背景地物 348 9 357
榆树疏林 2 341 343
总计 350 350 700
总体精度/% 98.43
Kappa 0.97

Tools

Get Citation

Copy Citation Text

Ang CHEN, Xiuchun YANG, Bin XU, Yunxiang JIN, Wenbo ZHANG, Jian GUO, Xiaoyu XING, Dong YANG. Research on Recognition Methods of Elm Sparse Forest based on Object-based Image Analysis and Deep Learning[J]. Journal of Geo-information Science, 2020, 22(9): 1897

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites