A Novel Approach for Change Detection Analysis of Land Cover from Multispectral FCC Optical Image using Machine Learning

2021 ◽  
Author(s):  
Khyat Patel ◽  
Manan Jain ◽  
Manish I. Patel ◽  
Ruchi Gajjar
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Change Detection ◽  
Optical Image ◽  
Change Detection Analysis ◽  
Detection Analysis ◽  
Novel Approach

scholarly journals Change detection analysis of reservoirs and lakes in Multi-Temporal Landsat-7 (ETM+) data over the Indian sub-continent during 2008-2018

2018 ◽  
Vol 7 (4.6) ◽  
pp. 122
Author(s):  
B. Chandrababu Naik ◽  
Prof. B. Anuradha ◽  
. .
Keyword(s):  
Land Cover ◽  
Change Detection ◽  
Accuracy Assessment ◽  
Kappa Statistics ◽  
Detection Techniques ◽  
Change Detection Analysis ◽  
Detection Analysis ◽  
Landsat 7 ◽  
Multi Temporal ◽  
Lakes And Reservoirs

Remote sensing change detection techniques are extensively used in numerous applications such as land cover monitoring, disaster monitoring, and urban sprawl. The main motive of this paper study the change detection analysis of Land Use / Land Cover (LULC) in different lakes and Reservoirs, such as Chilika Lake, Pulicat Lake, Vembanad Lake, Penna Reservoir, and Nagarjuna Sagar Reservoir located in the Indian subcontinent region.  The analyses and changes are evaluated during period of 2008 - 2018 in multi-temporal Landsat-7 (ETM+) data. The major disadvantage in Landsat-7 for data acquired from satellite sensor, is that it includes strips (gaps) in an image. On May 31, 2003 the Scan-Line-Corrector (SLC) failed completely, due to 22% of pixel information lost in the Landsat-7 data. The focal analysis method is applied to the required image for removing all strips (gaps). Change detection using Image Differencing technique, maximum changed area and unchanged area detect the different Lakes and Reservoirs in the period of 2008-2018. The unsupervised classification is used to compute the accuracy assessment analysis. Excellent results are obtained by using accuracy assessment for different Lakes and Reservoirs from 2008 to 2018, with the overall accuracy of 91.59%, and overall kappa statistics of 0.9032. The percentage of a decreased area is more in 2018 as compared to 2008 and it concludes that the percentage of decreased area is more as compared to the percentage of increased area for acquired Landsat-7 data.  

scholarly journals SPATIOTEMPORAL CHANGE DETECTION USING LANDSAT IMAGERY: THE CASE STUDY OF KARACABEY FLOODED FOREST, BURSA, TURKEY

2017 ◽  
Vol IV-4/W4 ◽  
pp. 31-35 ◽  
Author(s):  
A. E. Akay ◽  
B. Gencal ◽  
İ. Taş
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Change Detection ◽  
Short Paper ◽  
Landsat 8 ◽  
Land Use Land Cover ◽  
Spatiotemporal Change ◽  
Change Detection Analysis ◽  
Flooded Forest ◽  
Detection Analysis

This short paper aims to detect spatiotemporal detection of land use/land cover change within Karacabey Flooded Forest region. Change detection analysis applied to Landsat 5 TM images representing July 2000 and a Landsat 8 OLI representing June 2017. Various image processing tools were implemented using ERDAS 9.2, ArcGIS 10.4.1, and ENVI programs to conduct spatiotemporal change detection over these two images such as band selection, corrections, subset, classification, recoding, accuracy assessment, and change detection analysis. Image classification revealed that there are five significant land use/land cover types, including forest, flooded forest, swamp, water, and other lands (i.e. agriculture, sand, roads, settlement, and open areas). The results indicated that there was increase in flooded forest, water, and other lands, while the cover of forest and swamp decreased.

Sign in / Sign up

Export Citation Format

Share Document