Automatic Change Detection for High-Resolution Satellite Images of Urban and Suburban Areas

Authors: Antigoni Panagiotopoulou, Lemonia Ragia

Abstract:

High-resolution satellite images can provide detailed information about change detection on the earth. In the present work, QuickBird images of spatial resolution 60 cm/pixel and WorldView images of resolution 30 cm/pixel are utilized to perform automatic change detection in urban and suburban areas of Crete, Greece. There is a relative time difference of 13 years among the satellite images. Multiindex scene representation is applied on the images to classify the scene into buildings, vegetation, water and ground. Then, automatic change detection is made possible by pixel-per-pixel comparison of the classified multi-temporal images. The vegetation index and the water index which have been developed in this study prove effective. Furthermore, the proposed change detection approach not only indicates whether changes have taken place or not but also provides specific information relative to the types of changes. Experimentations with other different scenes in the future could help optimize the proposed spectral indices as well as the entire change detection methodology.

Keywords: Change detection, multiindex scene representation, spectral index, QuickBird, WorldView.

References:

[1] J. Gong, C. Liu, and X. Huang, “Advances in urban information extraction from high-resolution remote sensing imagery”, Sci. China Earth Sci., vol. 63, no. 4, pp. 463-475, Dec. 2020.
[2] C. Marin, F. Bovolo, and L. Bruzzone, “Building change detection in multitemporal very high resolution SAR images”, IEEE Trans. Geosci Remote Sens., vol. 53, no. 5, pp. 2664-2682, May 2015.
[3] L. Bruzzone and F. Bovolo, “A novel framework for the design of change-detection systems for very-high-resolution remote sensing images”, IEEE Proc., vol. 101, no. 3, pp. 609-630, March 2013.
[4] M. Volpi, D. Tuia, F. Bovolo, M. Kanevski, and L. Bruzzone, “Supervised change detection in VHR images using contextual Information and support vector machines”, INT J APPL EARTH OBS, vol. 20, pp. 77-85, Feb. 2013.
[5] F. Pacifici and F. Del Frate, “Automatic change detection in very high resolution images with pulse-coupled neural networks”, IEEE Geosci. Remote Sens. Lett., vol. 7, no. 1, pp. 58-62, Jan. 2010.
[6] N. Falco, M. D. Mura, F. Bovolo, J. A. Benediktsson, and L. Bruzzone, “Change detection in VHR images based on morphological attribute profiles”, IEEE Geosci. .Remote Sens. Lett., vol. 10, no. 3, pp. 636- 640, May 2013.
[7] F. Bovolo, “A multilevel parcel-based approach to change detection in very high resolution multitemporal images”, IEEE Geosci. Remote Sens. Lett., vol. 6, no. 1, pp. 33-37, Jan.2009.
[8] D. Wen, X. Huang, L. Zhang, and J. A. Benediktsson, “A novel automatic change detection method for urban high-resolution remotely sensed imagery based on multiindex scene representation”, IEEE Trans. Geosci Remote Sens., vol. 54, no. 1, pp. 609-625, Jan. 2016.
[9] X. Huang, D. Wen, J. Li, and R. Qin, “Multi-level monitoring of subtle urban changes for the megacities of China using high-resolution multi view satellite imagery”, Remote Sens. Environ., vol. 196, pp. 56- 75, Jul. 2017.
[10] L. Ragia and P. Krassakis, “Monitoring the changes of the coastal areas using remote sensing data and geographic information systems”, in SPIE Proceedings of the Seventh International Conference RSCy2019, Paphos, 2019, 111740X.
[11] E. Bratsolis, A. Panagiotopoulou, M. Stefouli, E. Charou, N. Madamopoulos and S. Perantonis, “Comparison of optimized mathematical methods in the improvement of raster data and map display resolution of Sentinel-2 images”, in IEEE ICIP Proc., Athens, 2018, pp. 2521-2525.
[12] X. Huang, W. Yuan, and L. Zhang, “A new building extraction postprocessing framework for high-spatial-resolution-remote-sensing-Imagery”, IEEE J Sel Top Appl Earth Obs Remote Sen, vol. 10, no. 2, pp. 654-688, Febr. 2017.
[13] X. Huang and L. Zhang, “A multidirectional and multiscale morphological index for automatic building extraction from multispectral GeoEye-1 imagery”, PE&RS, vol. 77, no. 7, pp. 721-732, Jul. 2011.
[14] X. Huang, C. Xie, X. Fang, and L. Zhang, “Combining pixel- and object-based machine learning for identification of water-body types from urban high-resolution remote-sensing imagery”, IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 8, no. 5, pp. 2097-2110, May 2015.
[15] X. Liu, L. Liu, Y. Shao, Q. Zhao, Q. Zhang, and L. Lou, “Water detection in urban areas from GF-3”, Sensors, vol. 18, no. 1299, pp.1-12, Apr. 2018.
[16] F. Chen, X. Chen, T. Van de Voorde, D. Roberts, H. Jiang, and W. Xu, “Open water detection in urban environments using high spatial resolution remote sensing imagery”, Remote Sens. Environ., vol. 242, pp. 1-17, Jun. 2020.
[17] C. Galindo, P. Moreno, J, Gonzalez, and V. Arevalo, “Swimming pools localization in colour high-resolution satellite images”, in IGARSS 2009, CapeTown, pp. IV-510-IV513.
[18] Mst I. Faridatul and B. Wu, “Automatic classification of major urban land covers based on novel spectral indices”, ISPRS Int. J. Geo- Inf., vol. 7, no. 453, pp. 1-25, Nov. 2018.
[19] T. Celik, “Unsupervised change detection in satellite images using principal component analysis and k-means clustering”, IEEE Geosci. Remote Sens. Lett., vol. 6, no. 4, pp. 772-776, Oct. 2009.