Segmentation and Classification Using Logistic Regression in Remote Sensing Imagery

This paper presents techniques for segmentation and change classification using logistic regression. The research was conducted on SPOT 5 multispectral multitemporal images covering the 2010 floods in Pakistan. Segmentation was performed to extract the built up area (BUA) from the satellite images and change detection was performed to find the damaged BUA. The damaged area was classified into three categories based on the extent of damage. The segmentation results were validated using statistical measures like precision, recall, and dice coefficient on available ground truth. The results of change classification were compared and found consistent with the manual assessment report produced by UNO experts using Worldview 1 satellite imagery with submeter resolution. The proposed scheme and results give an indication that SPOT 5 imagery can be used for fast automatic damage assessment and classification immediately after a natural calamity. The proposed change detection technique was also applied on Unites States Geographical Survey dataset. We compared our change detection results with established methods like change vector analysis, Principal component analysis using K-means and commercially available software Erdas Imagine on both the above-mentioned datasets. The comparison results suggest that our proposed algorithm performs better than the other methods.

[1]  Paul de Fraipont,et al.  Rapid EO disaster mapping service: added value, feedback and perspectives after 4 years of charter actions , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[2]  Y. F. Tian,et al.  Techniques for seismic damages assessment by using remotely sensed images , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[3]  F. Balcik,et al.  DETERMINATION OF MAGNITUDE AND DIRECTION OF LAND USE/ LAND COVER CHANGES IN TERKOS WATER BASIN, ISTANBUL , 2012 .

[4]  Keiko Saito,et al.  Visual Damage Assessment using High-Resolution Satellite Images following the 2003 Bam, Iran, Earthquake , 2005 .

[5]  G. Andre,et al.  Building destruction and damage assessment after earthquake using high resolution optical sensors. The case of the Gujarat earthquake of January 26, 2001 , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[6]  Turgay Çelik,et al.  Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering , 2009, IEEE Geoscience and Remote Sensing Letters.

[7]  Xiang Liu,et al.  Cognitive model based method for earthquake damage assessment from high-resolution satellite images: A study following the WenChuan earthquake , 2010, 2010 Sixth International Conference on Natural Computation.

[8]  M. Matsuoka,et al.  Building Damage Mapping of the 2003 Bam, Iran, Earthquake Using Envisat/ASAR Intensity Imagery , 2005 .

[9]  Jing-Fa Zhang,et al.  Change detection of earthquake-damaged buildings on remote sensing image and its application in seismic disaster assessment , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[10]  Linlin Lu,et al.  Urbanization analysis by mutual information based change detection between SPOT 5 panchromatic images , 2011, 2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp).

[11]  P. Gamba,et al.  GIs and Image Understanding for Near-Real- Time Earthquake Damage Assessment , 1998 .

[12]  A. X. Dou,et al.  Retrieve seismic damages from remote sensing images by change detection algorithm , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[13]  A. Mahmood,et al.  The International Charter ‘Space and Major Disasters’ , 2015 .

[14]  Alan R. Gillespie,et al.  A New Approach to Change Vector Analysis Using Distance and Similarity Measures , 2011, Remote. Sens..

[15]  Budhendra L. Bhaduri,et al.  Rapid Damage Assessment from High Resolution Imagery , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[16]  M. Matsuoka,et al.  Visual Damage Interpretation of Buildings in Bam City using QuickBird Images following the 2003 Bam, Iran, Earthquake , 2005 .

[17]  Ellen Rathje,et al.  Comparison of Earthquake Damage Evaluation using Change Detection and Thematic Classification , 2005 .

[18]  F. Yamazaki,et al.  Identification of Damaged Areas due to the 2006 Central Java, Indonesia Earthquake Using Satellite Optical Images , 2007, 2007 Urban Remote Sensing Joint Event.

[19]  S. Tanathong,et al.  Object oriented change detection of buildings after the Indian ocean tsunami disaster , 2008, 2008 5th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[20]  W. Malila.  Change Vector Analysis: An Approach for Detecting Forest Changes with Landsat , 1980 .