Object-oriented classification of very high resolution airborne imagery for the extraction of hedgerows and field margin cover in agricultural areas

Tansey, Kevin; Chambers, Ian; Anstee, Andrew; Denniss, Anthony; Lamb, Alistair

doi:10.1016/j.apgeog.2008.08.004

Cited by 79 publications

(40 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The accuracy of the classification we applied to SPOT-5 and TerraSAR-X images using an object-oriented approach is high (percentage of correctly detected pixels = 92% for the optical image and 90% for the SAR image). These results are comparable to those from similar studies that aim to develop methods to automatically extract linear landscape features such as hedgerows from VHSR (Very High Spatial Resolution) optical data (Wiseman et al 2009;Czerepowicz et al 2012;Tansey et al 2009) or VHSR radar data (Bargiel et al 2013;Betbeder et al 2014b). Therefore, the landscape metrics defined in order to characterize hedgerow network structure can be derived from classifications based on either image.…”

Section: Discussionsupporting

confidence: 67%

Assessing ecological habitat structure from local to landscape scales using synthetic aperture radar

Betbeder

Hubert‐Moy

Burel

et al. 2015

Ecological Indicators

View full text Add to dashboard Cite

Ecological studies need accurate environmental data such as vegetation characterization, landscape structure and organization, to predict and explain the spatial distribution of biodiversity. Few ecological studies use remote sensing data to assess the biophysical or structural properties of vegetation to understand species distribution. To date, Synthetic Aperture Radar (SAR) data have seldom been used for ecological applications. However, these sensors provide data allowing access to the inner structure of vegetation which is a key information in ecology. The objective of this article is to compare the predictive power of ecological habitat structure variables derived from a TerraSAR-X image, an aerial photograph and a SPOT-5 image for species distribution. The test was run with a hedgerow network in Brittany and assessed the spatial distribution of the forest ground carabid beetles which inhabit these hedgerows. The results confirmed that radar and optical images can be indifferently used to extract hedgerow network and derived landscape metrics (hedgerow density, network grain) useful to explain the spatial distribution of forest carabid beetles. In comparison with passive optical remotely sensed data, VHSR SAR images provide new data to characterize vegetation structure and more particularly hedgerow canopy cover, a variable known to explain the spatial distribution of carabid beetles in an agricultural landscape, but not yet quantified at a fine scale. The hedgerow canopy cover derived from the SAR image is 2 a strong predictor of the abundance of forest carabid beetles at two scales i.e. a local scale and a landscape scale. Keywordsbiodiversity, remote sensing, forest carabid beetles, hedgerow canopy cover, landscape scale, quantitative maps

show abstract

Section: Discussionsupporting

confidence: 67%

Assessing ecological habitat structure from local to landscape scales using synthetic aperture radar

Betbeder

Hubert‐Moy

Burel

et al. 2015

Ecological Indicators

View full text Add to dashboard Cite

show abstract

“…Accurate mapping of linear hedgerows can be problematic due to their small areal extent and fragmented nature [15]. Due to the appearance of very high spatial resolution (VHSR) sensors, remotely sensed data can now be used to automatically map hedgerows in agricultural landscapes [16][17][18]. Lausch and Herzog (2002) [19] suggested that the spatial resolution should be below 5 m to capture linear features in a landscape.…”

Section: Introductionmentioning

confidence: 99%

Detection and Characterization of Hedgerows Using TerraSAR-X Imagery

et al. 2014

View full text Add to dashboard Cite

Whilst most hedgerow functions depend upon hedgerow structure and hedgerow network patterns, in many ecological studies information on the fragmentation of hedgerows network and canopy structure is often retrieved in the field in small areas using accurate ground surveys and estimated over landscapes in a semi-quantitative manner. This paper explores the use of radar SAR imagery to (i) detect hedgerow networks; and (ii) describe the hedgerow canopy heterogeneity using TerraSAR-X imagery. The extraction of hedgerow networks was achieved using an object-oriented method using two polarimetric parameters: the Single Bounce and the Shannon Entropy derived from one TerraSAR-X image. The hedgerow canopy heterogeneity estimated from field measurements was compared with two backscattering coefficients and three polarimetric parameters derived from the same image. The results show that the hedgerow network and its fragmentation can be identified with a very good accuracy (Kappa index: 0.92). This study also reveals the high correlation between one polarimetric parameter, the Shannon entropy, and the canopy fragmentation measured in the field. Therefore, VHSR radar images can OPEN ACCESSRemote Sens. 2014, 6 3753 both precisely detect the presence of wooded hedgerow networks and characterize their structure, which cannot be achieved with optical images.

show abstract

“…Embora a classificação orientada a objetos seja mais amplamente aplicada em imagens de alta resolução espacial (Mallinis et al, 2008;Tansey et al, 2009;Zhou et al, 2009;Machado et al, 2014), os resultados obtidos no presente trabalho mostram a robustez do método também para imagens de média resolução espacial. Essa adequação também decorre da resolução radiométrica de 16 bits das imagens, da correção atmosférica realizada e da fusão entre bandas multiespectrais, de 30 m de resolução espacial, e a banda pancromática, de 15 m. Assim, além da informação de reflectância, foram obtidos detalhes de cor, forma, textura e nitidez.…”

Section: Resultsunclassified

Análise comparativa de classificadores digitais em imagens do Landsat-8 aplicados ao mapeamento temático

Liempt

Messias

Liesenberg

et al. 2015

Pesq. agropec. bras.

View full text Add to dashboard Cite

Resumo -O objetivo deste trabalho foi avaliar o desempenho dos classificadores digitais SVM e K-NN para a classificação orientada a objeto em imagens Landsat-8, aplicados ao mapeamento de uso e cobertura do solo da Alta Bacia do Rio Piracicaba-Jaguari, MG. A etapa de pré-processamento contou com a conversão radiométrica e a minimização dos efeitos atmosféricos. Em seguida, foi feita a fusão das bandas multiespectrais (30 m) com a banda pancromática (15 m). Com base em composições RGB e inspeções de campo, definiramse 15 classes de uso e cobertura do solo. Para a segmentação de bordas, aplicaram-se os limiares 10 e 60 para as configurações de segmentação e união no aplicativo ENVI. A classificação foi feita usando SVM e K-NN. Ambos os classificadores apresentaram elevados valores de índice Kappa (k): 0,92 para SVM e 0,86 para K-NN, significativamente diferentes entre si a 95% de probabilidade. Uma significativa melhoria foi observada para SVM, na classificação correta de diferentes tipologias florestais. A classificação orientada a objetos é amplamente aplicada em imagens de alta resolução espacial; no entanto, os resultados obtidos no presente trabalho mostram a robustez do método também para imagens de média resolução espacial.Termos para indexação: classificação orientada a objetos, gestão territorial, sensoriamento remoto, resolução espacial, uso e cobertura do solo. Comparative analysis of digital classifiers of Landsat-8 images for thematic mapping proceduresAbstract -The objective of this work was to evaluate the performance of SVM and K-NN digital classifiers for the object-based classification on Landsat-8 images, applied to mapping of land use and land cover of Alta Bacia do Rio Piracicaba-Jaguari, in the state of Minas Gerais, Brazil. The pre-processing step consisted of using radiometric conversion and atmospheric correction. Then the multispectral bands (30 m) were merged with the panchromatic band (15 m). Based on RGP compositions and field inspection, 15 land-use and land-cover classes were defined. For edge segmentation, the bounds were set to 10 and 60 for segmentation configuring and merging in the ENVI software. Classification was done using SVM and K-NN. Both classifiers showed high values for the Kappa index (k): 0.92 for SVM and 0.86 for K-NN, significantly different from each other at 95% probability. A major improvement was observed for SVM by the correct classification of different forest types. The object-based classification is largely applied on high-resolution spatial images; however, the results of the present work show the robustness of the method also for medium-resolution spatial images.Index terms: object-based classification, territorial management, remote sensing, spatial resolution, land use and land cover. IntroduçãoA gestão territorial demanda uma constante caracterização dos recursos naturais, além de seu monitoramento contínuo, com o objetivo de sua utilização de forma racional. A execução de projetos de levantamento e mapeamento da superfície terrestre têm-se beneficiado ...

show abstract

Object-oriented classification of very high resolution airborne imagery for the extraction of hedgerows and field margin cover in agricultural areas

Cited by 79 publications

References 14 publications

Assessing ecological habitat structure from local to landscape scales using synthetic aperture radar

Assessing ecological habitat structure from local to landscape scales using synthetic aperture radar

Detection and Characterization of Hedgerows Using TerraSAR-X Imagery

Análise comparativa de classificadores digitais em imagens do Landsat-8 aplicados ao mapeamento temático

Contact Info

Product

Resources

About