Journal of Geo-information Science >
The Research on the Method of Combining Images of GF-1 and OLI for FuzzyClassification of Land use
Received date: 2016-04-25
Request revised date: 2016-08-25
Online published: 2017-01-13
Copyright
In order to improve the phenomenon that different objects perform the same spectral characteristics in land use mapping of high spatial resolution data and the “mixed pixel” problem caused by lower spatial resolution in land use mapping of medium spatial resolution data, this study took GF-1 and OLI as a case and proposed a method of combining high spatial resolution data and medium spatial resolution data for fuzzy classification of land use. Firstly, texture information of GF-1 and spectral information of OLI were compressed and strengthened by principal component analysis (PCA), respectively. Compressed texture information of GF-1 and compressed spectral information of OLI were layer stacked. The combined data of three bands feature was received. Then, the feature combined data was segmented into three different levels of 60, 80, 100 based on texture and spectral characteristics of the different land use types in feature combined data. Finally, the fuzzy logic membership functions of the land use types were built based on texture and spectral difference of the different land use types. In this way, the fuzzy land use classification of the study area was carried out. Results shows that the PCA method compressed and strengthened GF-1 and OLI of study area effectively and the proposed method classified the land use of study area successfully receiving a high total accuracy of 93.52%. The method proposed in this paper offered a new idea for classification feature selecting in object-oriented classification and had some significance for other classification research of combining high spatial resolution data and high spectral resolution data.
Key words: GF-1; OLI; Combined use; Land use; Fuzzy classification
ZHANG Cuifen , SHUAI Shuang , HAO Lina , LIU Xi . The Research on the Method of Combining Images of GF-1 and OLI for FuzzyClassification of Land use[J]. Journal of Geo-information Science, 2017 , 19(1) : 1 -9 . DOI: 10.3724/SP.J.1047.2017.00002
Fig. 1 GF-1 and OLI images of the study area图1 研究区GF-1影像和OLI影像 |
Fig. 2 Feature combined flow of GF-1 and OLI data图2 GF-1数据与OLI数据特征协同流程 |
Fig. 3 The texture information fusion image of GF-1 data in the study area图3 研究区GF-1数据纹理信息融合图像 |
Tab. 1 The correlation coefficient and spectraltwist of fusion images表1 融合结果相关系数与光谱扭曲度对比表 |
融合方法 | 相关系数 | 光谱扭曲度 |
---|---|---|
主成分变换 | 0.2242 | 145.2364 |
Gram-Schmidt变换 | 0.2337 | 128.3545 |
Pan-sharpen变换 | 0.2289 | 136.4752 |
Tab. 2 The standard deviation of the maximumarea of multi-scales表2 各尺度最大面积标准差 |
尺度 | 水体 | 林地 | 建设用地 | 农田 | 铁路 |
---|---|---|---|---|---|
50 | 5.07 | 4.57 | 10.38 | 4.23 | 16.68 |
60 | 5.07 | 4.57 | 10.38 | 9.83 | 16.68 |
70 | 5.07 | 4.57 | 10.38 | 9.83 | 20.35 |
80 | 5.07 | 6.56 | 16.24 | 9.83 | 42.36 |
90 | 6.58 | 8.15 | 16.24 | 18.60 | 42.36 |
100 | 6.58 | 8.15 | 18.71 | 18.60 | 42.36 |
110 | 6.58 | 18.97 | 18.71 | 27.58 | 48.26 |
120 | 27.07 | 18.97 | 25.97 | 27.58 | 48.26 |
130 | 27.07 | 20.00 | 25.97 | 33.26 | 48.26 |
140 | 27.07 | 20.00 | 25.97 | 33.26 | 48.26 |
Tab. 3 Multi-scale segmentation levels andparameter settings表3 多尺度分割层次和参数设置 |
分割层次 | 尺度 | 波动权重(PC1:PC2:T) | 形状 | 紧密度 |
---|---|---|---|---|
Level 1 | 100 | 1:2:1 | 0.1 | 0.6 |
Level 2 | 80 | 2:2:1 | 0.1 | 0.6 |
Level 3 | 60 | 1:1:2 | 0.2 | 0.6 |
Fig. 4 The land use classification results of the study area图4 研究区土地利用类型分类效果图 |
Tab. 4 Confusion matrices of the classification results表4 研究区特征协同影像模糊分类结果精度评价 |
土地利用类型 | 耕地 | 建设用地 | 林地 | 水体 | 铁路 | 未利用地 | 总计/行 | 用户精度/% |
---|---|---|---|---|---|---|---|---|
耕地 | 14 047 | 225 | 0 | 5 | 0 | 255 | 14 532 | 96.67 |
建设用地 | 38 | 1777 | 0 | 0 | 8 | 110 | 1933 | 91.88 |
林地 | 225 | 188 | 5351 | 37 | 0 | 315 | 6116 | 87.49 |
水体 | 0 | 0 | 0 | 276 | 0 | 0 | 276 | 100.00 |
铁路 | 13 | 0 | 17 | 6 | 208 | 0 | 244 | 85.25 |
未利用地 | 69 | 61 | 0 | 25 | 0 | 1408 | 1563 | 90.08 |
总计/列 | 14 392 | 2251 | 5368 | 349 | 216 | 2088 | ||
生产者精度/% | 97.60 | 78.94 | 99.68 | 79.08 | 96.30 | 67.43 |
The authors have declared that no competing interests exist.
[1] |
[
|
[2] |
[
|
[3] |
[
|
[4] |
[
|
[5] |
[
|
[6] |
[
|
[7] |
[
|
[8] |
[
|
[9] |
[
|
[10] |
|
[11] |
[
|
[12] |
[ Bai M, Liu H P, Qiao Y, et al. New Progress in the Classification of High Spatial Resolution satellite Images for LUCC[J]. Remote Sensing for Land & Resources, 2010,1:19-23. ]
|
[13] |
|
[14] |
|
[15] |
|
[16] |
|
[17] |
[
|
[18] |
[
|
[19] |
[
|
[20] |
[
|
[21] |
[
|
[22] |
[
|
/
〈 | 〉 |