Land Utilization Change Detection of Satellite Remote Sensing Image Based on AlexNet and Support Vector Machine

Qing Fu; Wenlang Luo; Jingxiang Lü

doi:10.3788/LOP57.172802

Laser & Optoelectronics Progress, Volume. 57, Issue 17, 172802(2020)

Land Utilization Change Detection of Satellite Remote Sensing Image Based on AlexNet and Support Vector Machine

Qing Fu^1,2,3, Wenlang Luo^1,2、*, and Jingxiang Lü^1,2

Author Affiliations

¹School of Electronics and Information Engineering, Jinggangshan University, Ji'an, Jiangxi 343009, China

²Jiangxi Engineering Laboratory of IoT Technologies for Crop Growth, Ji'an, Jiangxi 343009, China

³College of Surveying and Geo-Informatics, Tongji University, Shanghai 200092, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(12)

Fig. 1. AlexNet architecture

Download full size

Fig. 2. Flow chart of land use classification based on AlexNet and SVM

Download full size

Fig. 3. Distribution of validation samples

Download full size

Fig. 4. Classification accuracy of the model at different window sizes

Download full size

Fig. 5. Classification results of different algorithms. (a) Maximum likelihood algorithm; (b) SVM algorithm; (c) AlexNet algorithm; (d) our algorithm (AlexNet+SVM)

Download full size

Fig. 6. Classification accuracy of different algorithms

Download full size

Fig. 7. Dynamic change of land use types in Nanchang. (a) From 2013 to 2014; (b) from 2013 to 2015; (c) from 2013 to 2016; (d) from 2013 to 2017

Download full size

Table 1. GF-1 multispectral camera technical parameters
View table
Table 1. GF-1 multispectral camera technical parameters
Bandrange /μm Spatialresolution /m Width /km Revisittime /d
0.45-0.52
0.52-0.59 16 800 2
0.63-0.69
0.77-0.89

Table 2. Land use/cover change classification system

View table

Table 2. Land use/cover change classification system

No.	Name	Detail
1	Vegetation	Including forest land, grassland and other green vegetation covered land
2	Building	Including urban land, residential land and traffic land
3	Water	Including rivers, lakes, reservoirs, ponds and ditches
4	Bare land	Including natural bare land, developing bare land and beach sand

Table 3. Training sample data
View table
Table 3. Training sample data
Sample size /(pixel×pixel) Sample data numbers
Vegetation Water Bare land Building
5×5 900 800 700 650
7×7 900 800 700 650
9×9 900 800 700 650
11×11 900 800 700 650
13×13 900 800 700 650

Table 4. Land use transition matrix in Nanchang from 2013 to 2017km²
View table
Table 4. Land use transition matrix in Nanchang from 2013 to 2017km²
2013 2017
Building Bare land Vegetation Water
Building 149.45 7.56 9.45 8.78
Bare land 7.58 268.21 10.34 5.66
Vegetation 22.69 9.98 3489.12 39.32
Water 10.45 8.59 37.41 634.74

Table 5. Statistics of land use area change in Nanchang from 2013 to 2017

View table

Table 5. Statistics of land use area change in Nanchang from 2013 to 2017

Category	Land use area change /km²
Category	From 2013to 2014	From 2013to 2015	From 2013to 2016	From 2013to 2017
Vegetation	-44.2	-38.40	-45.03	-54.74
Water	28.64	19.56	10.12	22.12
Building	11.46	14.52	17.83	19.45
Bare land	20.1	8.32	7.06	5.17

Tools

Get Citation

Copy Citation Text

Qing Fu, Wenlang Luo, Jingxiang Lü. Land Utilization Change Detection of Satellite Remote Sensing Image Based on AlexNet and Support Vector Machine[J]. Laser & Optoelectronics Progress, 2020, 57(17): 172802

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites