Object-based land-cover change detection applied to Brazilian seasonal savannahs using geostatistical features

Silveira, Eduarda Martiniano de Oliveira; Mello, José Márcio de; Júnior, Fausto Weimar Acerbi; Carvalho, Luís Marcelo Tavares de

doi:10.1080/01431161.2018.1430397

Cited by 30 publications

(20 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The state of Minas Gerais (MG) is located in south-eastern Brazil (Figure 1a), and has Savanna, Atlantic Forest and Semi-arid woodland biomes (Figure 1b). The Brazilian Savanna is a heterogeneous biome, comprising vegetation types ranging from grasslands to woodlands (Ribeiro & Ferraz, 2013;Silveira et al, , 2018c, located between latitudes -14.25° and -21.50° 51.52 S and longitudes -41.80° and -50.91° W. The climate is seasonal Tropical, presenting dry winter and rainy summer (AW by Koppen classification). The average annual temperature is between 22 and 23 C. The average monthly rainfall shows a clear seasonality, occurring more concentrated between October and March, with annual average between 1.200 and 1.800 mm (Scolforo et al, 2015).…”

Section: Field Data and Study Areamentioning

confidence: 99%

Anthropogenic Disturbances Affect the Relationship Between Spectral Indices and the Biometric Variables of Brazilian Savannas

et al. 2019

Self Cite

View full text Add to dashboard Cite

According to previous studies involving biometric variables modeling using remote sensing (RS), data did not consider the effects of anthropogenic disturbance as relevant factor. The main objective of this study was to model aboveground biomass (AGB) and total wood volume (TWV) of Brazilian Savanna biome using vegetation indices (VI) from LANDSAT 5 TM. Multiple linear regression (MLR) and random forest (RF) algorithm were applied across 641 field plots of cerrado sensu stricto of the state of Minas Gerais, Brazil, comparing two models: non-stratified, and stratified according to plot's anthropization degree. AGB and TWV obtained from non-anthropized plots presented linear relation with VIs (R 2 = 0.82 and 0.74, respectively) and, on the other hand, presented nonlinear relation when plots were affected by anthropogenic disturbances or were not stratified. This finding helps improving estimates by stratifying plots into their anthropization degree, mainly in the Brazilian Savanna biome undergoing anthropogenic disturbances.

show abstract

Section: Field Data and Study Areamentioning

confidence: 99%

Anthropogenic Disturbances Affect the Relationship Between Spectral Indices and the Biometric Variables of Brazilian Savannas

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dessa forma, requer-se melhores métodos de gerenciamento de fogo considerando o conhecimento da extensão de áreas queimadas, da gravidade da queimadura e dos processos de recuperação após o fogo (Rozario et al, 2018). Uma das formas de detectar e mapear áreas de vegetação queimadas consiste na utilização de técnicas de sensoriamento remoto que permitem extrair séries temporais e obter informações sobre as áreas afetadas (Pereira, 2016;Hislop et al, 2018), uma vez que a severidade de uma queimada influencia na composição das espécies após a queima (Schepers et al, 2014) e altera as assinaturas espectrais entre a vegetação saudável e a vegetação que foi danificada pelo fogo (Henry et al, 2019) Atualmente, tem-se uma grande quantidade de dados de sensoriamento remoto disponíveis para diversos usos, incluindo a obtenção de séries temporais e a detecção e quantificação de mudanças na superfície terrestre (Doxani et al, 2018;White et al, 2014;Fornacca et al, 2018;Silveira et al, 2018;Pickell et al, 2015). Pode-se citar como exemplo os arquivos do satélite Landsat que disponibilizam diversos registros que contribuem com a realização de pesquisas relacionadas à mudanças da cobertura da terra e mudanças climáticas (Mishra et al, 2014).…”

Section: Introductionunclassified

Determinação das Áreas Atingidas por Queimadas em Bacias Hidrográficas por meio do Índice De Queimada (NBR), Estudo de Caso da Bacia do Rio Piracicaba-MG

Pio

Vieira

2020

Rev. Bras. Geog. Fis.

View full text Add to dashboard Cite

O desenvolvimento da humanidade e consequente alteração no uso do solo vem tornando áreas cada vez mais susceptíveis à incêndios florestais, fato agravado pela prática de queimadas. Eventos de queima são considerados preocupantes devido a abrangência dos impactos que influenciam, inclusive nas mudanças climáticas. Assim, técnicas de sensoriamento remoto podem ser empregadas para identificação e espacialização de áreas queimadas. A gravidade dos impactos gerados torna visível a importância de estudos capazes de detectar cicatrizes de queimadas a fim contribuir com o desenvolvimento de técnicas de monitoramento, conscientização, prevenção e recuperação de áreas afetadas. Assim, o presente estudo objetivou gerar o índice de queimada (NBR) bem como sua variação (NBR) e o Índice Normalizado de Diferença de Água (NDWI) para distinção entre áreas queimadas e áreas úmidas para a região da bacia hidrográfica do rio Piracicaba, Minas Gerais, utilizando cenas Landsat 8 órbita/ponto 217/074 e 218/074 dos meses de agosto e setembro de 2016. A eficiência do método para detecção de áreas queimadas foi analisada a partir da comparação com polígonos de queimadas do banco de dados do INPE e pontos de ocorrência de incêndio fornecidos pelo 4º Pelotão de Bombeiros Militar de Itabira. Os resultados da NBR foram classificados em níveis de severidade e mostraram-se eficientes para a detecção de áreas queimadas quando comparados com polígonos de registro de queimadas do INPE. Com o cálculo do índice para toda a bacia pôde-se perceber regiões com maior ocorrência das classes moderada e alta severidade nas porções noroeste e nordeste da bacia. Determination of Areas Affected by Burns in Watersheds by the Queimada Index (Nbr), Case Study of the Piracicaba-MG River Basin ABSTRACTThe development of mankind and consequent alteration in land use has made areas increasingly susceptible to forest fires, a fact aggravated by the practice of burning. Burning events are considered worrisome due to the extent of the impacts that influence, including climate change. Thus, remote sensing techniques can be used to identify and spatialize burned areas. The severity of the impacts generated makes visible the importance of studies capable of detecting burn scars in order to contribute to the development of monitoring techniques, awareness, prevention and recovery of affected areas. Thus, the present study aimed to generate the burn rate (NBR) as well as its variation (ΔNBR) and the Normalized Water Difference Index (NDWI) to distinguish between burned areas and wetlands for the Piracicaba river basin region, Minas Gerais, using Landsat 8 scenes orbit / point 217/074 and 218/074 from the months of August and September 2016. The efficiency of the method for the detection of burned areas was analyzed from the comparison with burned polygons of the INPE and fire occurrence points provided by the 4th Itabira Military Fire Squad. The results of ΔNBR were classified in severity levels and were efficient for the detection of burned areas when compared to INPE burn logs. With the calculation of the index for the whole basin it was possible to perceive regions with higher occurrence of the moderate and high severity classes in the northwest and northeast portions of the basin.Keywords: burned, sevirity of fire, remote sensing, burn rate

show abstract

“…The designation for detecting land-cover change is based on the candidate segments. For example, Silveira et al applied an object-based LCCD approach to detect Brazilian seasonal savannahs through a geostatistical object feature [30], and Dronova et al presented an object-based LCCD method for monitoring wetland-cover type changes in Poyang Lake region, China [31]. Despite the advantages of OBCD in the smoothing noise of change detection map, these approaches still have limitations, including the fact that OBCD performance is determined by multi-scale segmentation algorithms.…”

mentioning

confidence: 99%

“…Cai et al, for example, developed a fusion strategy for utilising the advantages of different methods (AMC-OBCD) [32]. Further comparisons between pixel-and object-based LCCD approaches are available [17,30,33,34].A multi-scale object histogram distance (MOHD) for LCCD using bi-temporal VHR images is proposed in this study. Firstly, multi-scale objects of the post-event image are extracted through the fractional net evaluation approach (FNEA) multi-resolution segmentation algorithm [35,36].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Multi-Scale Object Histogram Distance for LCCD Using Bi-Temporal Very-High-Resolution Remote Sensing Images

Liu²,

Benediktsson

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

To improve the performance of land-cover change detection (LCCD) using remote sensing images, this study utilises spatial information in an adaptive and multi-scale manner. It proposes a novel multi-scale object histogram distance (MOHD) to measure the change magnitude between bi-temporal remote sensing images. Three major steps are related to the proposed MOHD. Firstly, multi-scale objects for the post-event image are extracted through a widely used algorithm called the fractional net evaluation approach. The pixels within a segmental object are taken to construct the pairwise frequency distribution histograms. An arithmetic frequency-mean feature is then defined from the red, green and blue band histogram. Secondly, bin-to-bin distance is adapted to measure the change magnitude between the pairwise objects of bi-temporal images. The change magnitude image (CMI) of the bi-temporal images can be generated through object-by-object. Finally, the classical binary method Otsu is used to divide the CMI to a binary change detection map. Experimental results based on two real datasets with different land-cover change scenes demonstrate the effectiveness of the proposed MOHD approach in detecting land-cover change compared with three widely used existing approaches. divide the CMI into a binary change detection map (BCDM). Numerous methods can be used to generate the CMI, such as difference and ratios [22,23], change vector analysis [19] and spectral gradient difference [18]. In addition, a binary threshold is necessary for distinguishing whether a pixel in CMI is changed or unchanged, such as the most commonly used Otsu [20,24] and expectation maximisation [25]. Despite the many traditional PBCD approaches applied in practice, numerous existing PBCD approaches cannot provide satisfactory detection results with the use of VHR remote sensing images because, although superior in visual performance, these images are usually insufficient in the spectra [26][27][28]. Contextual information around a pixel is usually considered to solve this problem; for example, Lv et al. proposed an LCCD approach for VHR images based on adaptive contextual information [20], Zhang et al. promoted a level set evolution with local uncertainty constraints (LSELUC) [4] for unsupervised change detection [4] and Celik developed a principal component analysis and k-means clustering (PCA-Kmeans) approach [29].Apart from the aforementioned PBCD methods, OBCD is widely used for LCCD while employing remote sensing images with high spatial resolution. In general, a pre-step for the OBCD method is multi-scale segmentation, which generates a group of multi-scale segments. The designation for detecting land-cover change is based on the candidate segments. For example, Silveira et al. applied an object-based LCCD approach to detect Brazilian seasonal savannahs through a geostatistical object feature [30], and Dronova et al. presented an object-based LCCD method for monitoring wetland-cover type changes in Poyang Lake region, China [31]. Despite the advantages...

show abstract

Object-based land-cover change detection applied to Brazilian seasonal savannahs using geostatistical features

Cited by 30 publications

References 59 publications

Anthropogenic Disturbances Affect the Relationship Between Spectral Indices and the Biometric Variables of Brazilian Savannas

Anthropogenic Disturbances Affect the Relationship Between Spectral Indices and the Biometric Variables of Brazilian Savannas

Determinação das Áreas Atingidas por Queimadas em Bacias Hidrográficas por meio do Índice De Queimada (NBR), Estudo de Caso da Bacia do Rio Piracicaba-MG

Multi-Scale Object Histogram Distance for LCCD Using Bi-Temporal Very-High-Resolution Remote Sensing Images

Contact Info

Product

Resources

About