2016
DOI: 10.1016/j.procs.2016.06.025
|View full text |Cite
|
Sign up to set email alerts
|

An Efficient Parallel Block Processing Approach for K -Means Algorithm for High Resolution Orthoimagery Satellite Images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0
1

Year Published

2017
2017
2024
2024

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 8 publications
(5 citation statements)
references
References 1 publication
0
4
0
1
Order By: Relevance
“…Using k-means to categorize blocks of high-resolution satellite photos was suggested by researcher [2]. Authors [3] developed a segmentation and clustering technique with two phases for classifying land cover in satellite pictures.…”
Section: Literature Surveymentioning
confidence: 99%
See 1 more Smart Citation
“…Using k-means to categorize blocks of high-resolution satellite photos was suggested by researcher [2]. Authors [3] developed a segmentation and clustering technique with two phases for classifying land cover in satellite pictures.…”
Section: Literature Surveymentioning
confidence: 99%
“…Many applications, including image classification, object detection in industrial production, medical image analysis, action recognition, and remote sensing, use deep learning and computer vision [1]. There are several uses for satellite image analysis, which is regarded as the primary method of acquiring geographic information [2]. Design, construction, urban planning, and water resource management are all examples of civil engineering.…”
Section: Introductionmentioning
confidence: 99%
“…Se realizó una clasificación supervisada, a partir de la generación de tres ortomosaicos, compuestos por 27 ortofotos (año 2000; Figura 3A), 578 imágenes de Birdseye (año 2010; Figura 3B), 144 de Airbus Defence and Space (año 2018; Figura 3C); las cuales se compararon con imágenes Landsat (año 2018; Figura 3D) y Sentinel (2018). La corrección atmosférica a las imágenes de cada periodo se hizo recortándolas y sometiéndolas a un proceso de clasificación no supervisada con el módulo K-means analysis, que agrupa los valores de celda en clases con el método de análisis de conglomerados de datos multivariados (Jumb et al, 2014;Rashmi et al, 2016); posteriormente, se transformaron los archivos de formato raster a vectorial, para una clasificación supervisada (Figura 4). La clasificación supervisada se llevó a cabo mediante puntos de control, que consistieron en 148 sitios distribuidos de manera sistemática en áreas con alto grado de confusión por la reflectancia de las imágenes, la exposición, ruido y nubosidad.…”
Section: Clasificación Supervisadaunclassified
“…And the non-graceful shutdown time will result in loss of computing time. If it is a graceful shutdown time, it will know what it has to save or current progress to the remote server or database or so on [13][14][15]. In our previous work, we illustrate block processing method which need regular monitoring and provide an uninterrupted service for which process migration is very much required.…”
Section: Motivationmentioning
confidence: 99%