Dataset List

Vol.|Area

Data Details

Experimental Dataset of Identifying Road Material Using GF-6 Images


CUI Yuping1
1 China Highway Engineering Consulting Corporation,Beijing 100097,China

DOI:10.3974/geodb.2022.08.10.V1

Published:Aug. 2022

Visitors:6517       Data Files Downloaded:179      
Data Downloaded:82310.49 MB      Citations:

Key Words:

road material,machine learning,GF-6,Langfang

Abstract:

Based on the GF-6 images, the spectral characteristic indexes - spectral difference index, spectral ratio index, spectral variance index and spectral normalization index - were calculated in the experimental area in Langfang, Hebei Province of China. The sample data of road material was obtained based on Google Earth images and Baidu Maps. The machine learning technology was used to develop the experimental dataset of identifying road material from GF-6 images. Compared with the samples, the road material identification accuracy is 80.07%, and the Kappa coefficient is 0.70. The dataset consists of: (1) spectral characteristic index data; (2) road material sample data; (3) road material identification result. The dataset is archived in .dat, .shp. and .xlsx formats, and consists of 16 data files with data size of 3.69 GB (compressed into 4 files, 1.62 GB).Browse

Foundation Item:

GF-6 (07-Y30B03-9001-19/21, 87-Y50G28-9001-22/23);

Data Citation:

CUI Yuping. Experimental Dataset of Identifying Road Material Using GF-6 Images[J/DB/OL]. Digital Journal of Global Change Data Repository, 2022. https://doi.org/10.3974/geodb.2022.08.10.V1.

CUI Yuping. Methods and results of identifying a road material dataset from GF-6 remote sensing data in the Langfang area [J]. Journal of Global Change Data & Discovery, 2022, 6(4): 607–618.

References:

[1] Zhang, L. Modern Traffic Information Network and Communication Technology [M]. Shanghai: Tongji University Press, 2007.
     [2] Manzo, C., Mei, A., Salvatori, R., et al. Spectral modelling used to identify the aggregates index of asphalted surfaces and sensitivity analysis [J]. Construction & Building Materials, 2014, 61: 147-155.
     [3] Fu, C. Opportunities and challenges for highway survey and design in the era of big data [D]. Xi’an: Changan University, 2016.
     [4] Estes, J. E., Thorley, G. A. Manual of Remote Sensing-Volume II: Interpretation and Applications [M]. Virginia: American Society of Photogrammetry, 1983: 1955-2109.
     [5] Gardner, M., Roberts, D. A., Funk, C., et al. Road extraction from AVIRIS using spectral mixture and Q-tree filter techniques [C]. Technical Report, May 2001. University of California, Santa Barbara, National Consortium on Remote Sensing and Transportation: Infrastructure, 2001.
     [6] Grote, A., Heipke, C. Road extraction for update of road databases in suburban areas [J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2008, 37(B3b): 563-568.
     [7] Suchandt, S., Runge, H., Breit, H., et al. Automatic extraction of traffic flows using TerraSAR-X along-track interferometry [J]. IEEE Transactions on Geoscience & Remote Sensing, 2010, 48(2): 807-819.
     [8] Buslaev, A., Seferbekov, S., Iglovikov, V., et al. Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery [C]. Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2018.
     [9] She, Y. C., Lin, H., Sun, H. Analysis of hyperspectral characteristics of main road pavement materials [J]. Journal of Central South University of Forestry and Technology, 2014, 34(11): 120-139.
     [10] Jin, X., Zhang, X. F., Luo, L., et al. Analysis of spectral characteristics of highway pavement and preliminary exploration of remote sensing monitoring method for asphalt pavement aging [J]. Journal of Geo-Information Science, 2017, 19(5): 672-681.
     [11] Gao, L. P. Research on road extraction based on airborne LiDAR and high-resolution remote sensing images [D]. Xuzhou: China University of Mining and Technology, 2014.
     [12] Zhang, Y. X., Xu, W., Wang, Y., et al. Discrimination analysis of pavement materials based on spectral characteristics [J]. Journal of Changsha University of Science and Technology (Natural Science Edition), 2017, 14(4): 1-9.
     [13] Lu, P. P., Dai, J. G., Shi, X, Z. Analysis of four typical road spectral characteristics based on hyperspectral remote sensing [J]. Surveying and Mapping and Spatial Geographic Information, 2019, 42(5): 141-144.
     [14] Zhang, X. B., Cheng, R. S., Wang, L. J. Investigation and analysis of the thickness of asphalt pavement on expressways in my country [J]. Henan Communications Science and Technology, 1999(1): 3-5.
     [15] Li, X. P. Make up for the shortcomings and build the "Four Good Rural Roads" [J]. China Highway, 2017(17): 20-25.
     

Data Product:

ID Data Name Data Size Operation
0Datapaper_GF_RoadMaterial.pdf18000.00kbDownLoad
1 1_SpectralCharacteristicIndex_SDI_SVI.rar 210870.80KB
2 1_SpectralCharacteristicIndex_SNI.rar 757602.06KB
3 1_SpectralCharacteristicIndex_SRI.rar 730480.19KB
4 2&3_SampleData_RoadMaterial.rar 1705.59KB
Co-Sponsors
Superintend