Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series
Change detection methods are often incapable of accurately detecting changes within time series that are heavily influenced by seasonal variations. Techniques for de-seasoning time series or methods that apply the spatial context have been used to improve the results of change detection. However, fe...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/11/5/570 |
| _version_ | 1819350307786719232 |
|---|---|
| author | Inacio T. Bueno Fausto W. Acerbi Júnior Eduarda M. O. Silveira José M. Mello Luís M. T. Carvalho Lucas R. Gomide Kieran Withey José Roberto S. Scolforo |
| author_facet | Inacio T. Bueno Fausto W. Acerbi Júnior Eduarda M. O. Silveira José M. Mello Luís M. T. Carvalho Lucas R. Gomide Kieran Withey José Roberto S. Scolforo |
| author_sort | Inacio T. Bueno |
| collection | DOAJ |
| description | Change detection methods are often incapable of accurately detecting changes within time series that are heavily influenced by seasonal variations. Techniques for de-seasoning time series or methods that apply the spatial context have been used to improve the results of change detection. However, few studies have explored Landsat’s shortwave infrared channel (SWIR 2) to discriminate between seasonal changes and land use/land cover changes (LULCC). Here, we explored the effectiveness of Operational Land Imager (OLI) spectral bands and vegetation indices for detecting deforestation in highly seasonal areas of Brazilian savannas. We adopted object-based image analysis (OBIA), applying a multidate segmentation to an OLI time series to generate input data for discrimination of deforestation from seasonal changes using the Random Forest (RF) algorithm. We found adequate separability between deforested objects and seasonal changes using SWIR 2. Using spectral indices computed from SWIR 2, the RF algorithm generated a change map with an overall accuracy of 88.3%. For deforestation, the producer’s accuracy was 88.0% and the user’s accuracy was 84.6%. The SWIR 2 channel as well as the mid-infrared burn index presented the highest importance among spectral variables computed by the RF average impurity decrease measure. Our results give support to further change detection studies regarding to suitable spectral channels and provided a useful foundation for savanna change detection using an object-based method applied to Landsat time series. |
| first_indexed | 2024-12-24T19:14:21Z |
| format | Article |
| id | doaj.art-e9d7f47d857f4b9a8011ee3c13ff8b89 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T19:14:21Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e9d7f47d857f4b9a8011ee3c13ff8b892022-12-21T16:42:56ZengMDPI AGRemote Sensing2072-42922019-03-0111557010.3390/rs11050570rs11050570Object-Based Change Detection in the Cerrado Biome Using Landsat Time SeriesInacio T. Bueno0Fausto W. Acerbi Júnior1Eduarda M. O. Silveira2José M. Mello3Luís M. T. Carvalho4Lucas R. Gomide5Kieran Withey6José Roberto S. Scolforo7Forest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilForest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilForest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilForest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilForest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilForest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilLancaster Environment Centre, Lancaster University, Lancaster LA1 4YQ, UKForest Science Department, Federal University of Lavras, Lavras 37200-000, BrazilChange detection methods are often incapable of accurately detecting changes within time series that are heavily influenced by seasonal variations. Techniques for de-seasoning time series or methods that apply the spatial context have been used to improve the results of change detection. However, few studies have explored Landsat’s shortwave infrared channel (SWIR 2) to discriminate between seasonal changes and land use/land cover changes (LULCC). Here, we explored the effectiveness of Operational Land Imager (OLI) spectral bands and vegetation indices for detecting deforestation in highly seasonal areas of Brazilian savannas. We adopted object-based image analysis (OBIA), applying a multidate segmentation to an OLI time series to generate input data for discrimination of deforestation from seasonal changes using the Random Forest (RF) algorithm. We found adequate separability between deforested objects and seasonal changes using SWIR 2. Using spectral indices computed from SWIR 2, the RF algorithm generated a change map with an overall accuracy of 88.3%. For deforestation, the producer’s accuracy was 88.0% and the user’s accuracy was 84.6%. The SWIR 2 channel as well as the mid-infrared burn index presented the highest importance among spectral variables computed by the RF average impurity decrease measure. Our results give support to further change detection studies regarding to suitable spectral channels and provided a useful foundation for savanna change detection using an object-based method applied to Landsat time series.http://www.mdpi.com/2072-4292/11/5/570deforestationsavannavegetation seasonalitymultidate segmentationshortwave infrared |
| spellingShingle | Inacio T. Bueno Fausto W. Acerbi Júnior Eduarda M. O. Silveira José M. Mello Luís M. T. Carvalho Lucas R. Gomide Kieran Withey José Roberto S. Scolforo Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series Remote Sensing deforestation savanna vegetation seasonality multidate segmentation shortwave infrared |
| title | Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series |
| title_full | Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series |
| title_fullStr | Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series |
| title_full_unstemmed | Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series |
| title_short | Object-Based Change Detection in the Cerrado Biome Using Landsat Time Series |
| title_sort | object based change detection in the cerrado biome using landsat time series |
| topic | deforestation savanna vegetation seasonality multidate segmentation shortwave infrared |
| url | http://www.mdpi.com/2072-4292/11/5/570 |
| work_keys_str_mv | AT inaciotbueno objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT faustowacerbijunior objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT eduardamosilveira objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT josemmello objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT luismtcarvalho objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT lucasrgomide objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT kieranwithey objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries AT joserobertosscolforo objectbasedchangedetectioninthecerradobiomeusinglandsattimeseries |