2017
DOI: 10.1080/22797254.2017.1387505
|View full text |Cite
|
Sign up to set email alerts
|

Land use/land cover change detection combining automatic processing and visual interpretation

Abstract: This article presents a hybrid classification method combining image segmentation, GIS analysis, and visual interpretation, and its application to elaborate a multi-date cartographic database with 23 land use/cover (LUC) classes using SPOT 5 imagery for the Mexican state of Michoacan (~60,000 km 2 ). First, the resolution of an existing 1:100,000 LUC map produced through visual interpretation of 2007 SPOT images was improved. 2007 SPOT images were segmented, and each segment received the "majority" LUC categor… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
32
0
4

Year Published

2018
2018
2022
2022

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 56 publications
(36 citation statements)
references
References 34 publications
0
32
0
4
Order By: Relevance
“…The performance was evaluated using a stratified random sampling technique at 300 sites (pixels) and the overall accuracy for the built-up class in the processed scene exceeded 84%. Although the achieved accuracy can still be improved further by optimizing and increasing the number of the training sets, the authors consider the obtained results satisfactory for the conducted analysis, in line with other literature [18]. In Section 5, we draw on our analysis of key planning documents (e.g., the latest coastal protection plans) to present the main adaptation measures currently planned or implemented in the city and its greater metropolitan area.…”
Section: Methodsmentioning
confidence: 48%
“…The performance was evaluated using a stratified random sampling technique at 300 sites (pixels) and the overall accuracy for the built-up class in the processed scene exceeded 84%. Although the achieved accuracy can still be improved further by optimizing and increasing the number of the training sets, the authors consider the obtained results satisfactory for the conducted analysis, in line with other literature [18]. In Section 5, we draw on our analysis of key planning documents (e.g., the latest coastal protection plans) to present the main adaptation measures currently planned or implemented in the city and its greater metropolitan area.…”
Section: Methodsmentioning
confidence: 48%
“…Land-use/cover changes are one of the main causes of climate change through the modification of carbon, water, and energy cycles [7]. As a result, agricultural lands, vegetative lands, forests, water bodies, as well as mineral resource lands are changing continuously throughout the globe [8].…”
Section: Introductionmentioning
confidence: 99%
“…They applied a hybrid semiautomatic classification method that combined image segmentation, digital classification, and visual interpretation to SPOT satellite imagery from 2004 and 2014. These maps, with a global accuracy of 83.3% and a confidence interval of 3.1%, are the most accurate land-cover/use data available for our study area (Mas et al 2017). Nevertheless, the global accuracy of our maps is surely higher because our study area lacks land-cover/use areas subject to high spectral confusion, such as tropical dry forest and shrubland, and because we combined the 19 original classes into only 4, thus reducing omission and commission errors between spectrally similar classes.…”
Section: Spatial Analysismentioning
confidence: 97%
“…We employed the land-cover/use maps developed by Mas et al (2017) for the state of Michoacán to evaluate FCC processes. They applied a hybrid semiautomatic classification method that combined image segmentation, digital classification, and visual interpretation to SPOT satellite imagery from 2004 and 2014.…”
Section: Spatial Analysismentioning
confidence: 99%
See 1 more Smart Citation