scholarly journals Thresholding Algorithm Optimization for Change Detection to Satellite Imagery

2018 ◽  
Author(s):  
René Vázquez-Jiménez ◽  
Rocío N. Ramos-Bernal ◽  
Raúl Romero-Calcerrada ◽  
Patricia Arrogante-Funes ◽  
Sulpicio Sanchez Tizapa ◽  
...  
Keyword(s):  
Change Detection ◽  
Satellite Imagery ◽  
Algorithm Optimization ◽  
Thresholding Algorithm

LambdaNet: A Fully Convolutional Architecture for Directional Change Detection

2020 ◽  
Vol 2020 (8) ◽  
pp. 114-1-114-7
Author(s):  
Bryan Blakeslee ◽  
Andreas Savakis
Keyword(s):  
Change Detection ◽  
Satellite Imagery ◽  
Classification Scheme ◽  
Deep Architecture ◽  
Binary Process ◽  
Directional Change ◽  
Class Labels ◽  
Image Pairs

Change detection in image pairs has traditionally been a binary process, reporting either “Change” or “No Change.” In this paper, we present LambdaNet, a novel deep architecture for performing pixel-level directional change detection based on a four class classification scheme. LambdaNet successfully incorporates the notion of “directional change” and identifies differences between two images as “Additive Change” when a new object appears, “Subtractive Change” when an object is removed, “Exchange” when different objects are present in the same location, and “No Change.” To obtain pixel annotated change maps for training, we generated directional change class labels for the Change Detection 2014 dataset. Our tests illustrate that LambdaNet would be suitable for situations where the type of change is unstructured, such as change detection scenarios in satellite imagery.

Change detection in Arctic satellite imagery using clustering of sparse approximations (CoSA) over learned feature dictionaries

2015 ◽  
Author(s):  
Daniela I. Moody ◽  
Cathy J. Wilson ◽  
Joel C. Rowland ◽  
Garrett L. Altmann
Keyword(s):  
Change Detection ◽  
Satellite Imagery ◽  
Sparse Approximations

scholarly journals Change Detection of Lake Chad Water Surface Area Using Remote Sensing and Satellite Imagery

2021 ◽  
Vol 13 (05) ◽  
pp. 561-577
Author(s):  
Abdel-Aziz Adam Mahamat ◽  
Adeeba Al-Hurban ◽  
Nehaya Saied
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
Surface Area ◽  
Satellite Imagery ◽  
Water Surface ◽  
Lake Chad ◽  
Water Surface Area

scholarly journals High-Resolution Satellite Imagery to Assess Sargassum Inundation Impacts to Coastal Areas

2020 ◽  
Author(s):  
William J. Hernandez ◽  
Julio M. Morell ◽  
Roy A. Armstrong
Keyword(s):  
High Resolution ◽  
Change Detection ◽  
Satellite Imagery ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Unconsolidated Sediments ◽  
Coastal Vegetation ◽  
Atmospheric Effects ◽  
True Color ◽  
Benthic Composition

AbstractA change detection analysis utilizing Very High-resolution (VHR) satellite imagery was performed to evaluate the changes in benthic composition and coastal vegetation in La Parguera, southwestern Puerto Rico, attributable to the increased influx of pelagic Sargassum spp and its accumulations in cays, bays, inlets and near-shore environments. Satellite imagery was co-registered, corrected for atmospheric effects, and masked for water and land. A Normalized Difference Vegetation Index (NDVI) and an unsupervised classification scheme were applied to the imagery to evaluate the changes in coastal vegetation and benthic composition. These products were used to calculate the differences from 2010 baseline imagery, to potential hurricane impacts (2018 image), and potential Sargassum impacts (2020 image). Results show a negative trend in Normalized Difference Vegetation Index (NDVI) from 2010 to 2020 for the total pixel area of 24%, or 546,446 m2. These changes were also observed in true color images from 2010 to 2020. Changes in the NDVI negative values from 2018 to 2020 were higher, especially for the Isla Cueva site (97%) and were consistent with the field observations and drone surveys conducted since 2018 in the area. The major changes from 2018 and 2020 occurred mainly in unconsolidated sediments (e.g. sand, mud) and submerged aquatic vegetation (e.g. seagrass, algae), which can have similar spectra limiting the differentiation from multi-spectral imagery. Areas prone to Sargassum accumulation were identified using a combination of 2018 and 2020 true color VHR imagery and drone observations. This approach provides a quantifiable method to evaluate Sargassum impacts to the coastal vegetation and benthic composition using change detection of VHR images, and to separate these effects from other extreme events.

Sign in / Sign up

Export Citation Format

Share Document