A Low Cost Methodology for Multispectral Image Classification

Mangiameli, Michele; Mussumeci, Giuseppe; Candiano, Alessio

doi:10.1007/978-3-319-95174-4_22

Cited by 5 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Como una reciente tendencia, usar OBIA para la clasificación de imágenes capturadas con VANT se ha convertido en una herramienta indispensable en la planificación y gestión del territorio. Esto es debido a que genera información clave, oportuna y precisa para la toma de decisiones en diferentes ámbitos (Farfaglia et al, 2015;Mafanya et al, 2017;Mangiameli et al, 2018). Diversos estudios aplican técnicas de clasificación a imágenes de alta resolución provenientes de VANT.…”

Section: Introductionunclassified

Evaluación de parámetros de segmentación en OBIA para la clasificación de coberturas del suelo a partir de imágenes VANT

et al. 2021

View full text Add to dashboard Cite

<p>Unmanned Aerial Vehicles (UAVs) have given a new boost to remote sensing and image classification techniques due to the high level of detail among other factors. Object-based image analysis (OBIA) could improve classification accuracy unlike to pixel-based, especially in high-resolution images. OBIA application for image classification consists of three stages i.e., segmentation, class definition and training polygons, and classification. However, defining the parameters: spatial radius (SR), range radius (RR) and minimum region size (MR) is necessary during the segmentation stage. Despite their relevance, they are usually visually adjusted, which leads to a subjective interpretation. Therefore, it is of utmost importance to generate knowledge focused on evaluating combinations of these parameters. This study describes the use of the mean-shift segmentation algorithm followed by <em>Random Forest </em>classifier using Orfeo Toolbox software. It was considered a multispectral orthomosaic derived from UAV to generate a suburban map land cover in town of El Pueblito, Durango, Mexico. The main aim was to evaluate efficiency and segmentation quality of nine parameter combinations previously reported in scientific studies.This in terms of number generated polygons, processing time, discrepancy measures for segmentation and classification accuracy metrics. Results evidenced the importance of calibrating the input parameters in the segmentation algorithms. Best combination was RE=5, RR=7 and TMR=250, with a Kappa index of 0.90 and shortest processing time. On the other hand, RR showed a strong and inversely proportional degree of association regarding the classification accuracy metrics.</p>

show abstract

Section: Introductionunclassified

Evaluación de parámetros de segmentación en OBIA para la clasificación de coberturas del suelo a partir de imágenes VANT

et al. 2021

View full text Add to dashboard Cite

show abstract

Multispectral remote sensing for post‐dictive analysis of archaeological remains. A case study from Bronte (Sicily)

Gennaro¹,

Candiano

Fargione

et al. 2019

Archaeological Prospection

View full text Add to dashboard Cite

In recent years, the use of remote sensing in archeology has rapidly grown, having being proven particularly useful for landscape archaeology investigations. The quality of results obtained through remote sensing mainly depends on the number of bands that can be exploited, the spatial and spectral resolution of imagery and the methodology used. In this work, adopting a post‐dictive approach, multispectral remote sensing data from World‐View 2 (WV‐2) were used in order to detect archaeological features in the volcanic area of Bronte (Sicily, Italy), a town 40 km from Catania. The selected area lies in the western slope of Etna, inside the boundary of Etna Park. Here, the archaeological research is affected by specific problems. The geology and the spontaneous vegetation of this fascinating environment represents one of the biggest issues. The entire research was conducted using free and open source software (FOSS) within a low‐cost logic that allows study of landscapes using limited budget. The strategy developed in our study is directed towards a post‐dictive approach to archeological data and remote sensing techniques. We analyzed an area where archeological buildings are now visible, but WV‐2 multispectral images have been deliberately selected prior to the archaeological excavations carried out in 2015. In this way, we can evaluate and test instruments and techniques at our disposal, emphasizing weaknesses and strengths. The final results illustrate the benefits and challenges of performing multispectral imagines for archaeological investigations. The use of some of the most promising vegetation indices, especially Normalized Difference Vegetation Index (NDVI) and Simple Ratio Index (SRI), is analysed and discussed, while the post‐dictive approach suggests that the more useful bands are undoubtedly NIR_1 and RED_EDGE.

show abstract

Multispectral satellite imagery processing to recognize and analyze archaeological sites in the central area of Sicily (Italy)

Calderone

Mangiameli

Mussumeci

et al. 2022

Journal of Archaeological Science: Reports

View full text Add to dashboard Cite

A Low Cost Methodology for Multispectral Image Classification

Cited by 5 publications

References 20 publications

Evaluación de parámetros de segmentación en OBIA para la clasificación de coberturas del suelo a partir de imágenes VANT

Evaluación de parámetros de segmentación en OBIA para la clasificación de coberturas del suelo a partir de imágenes VANT

Multispectral remote sensing for post‐dictive analysis of archaeological remains. A case study from Bronte (Sicily)

Multispectral satellite imagery processing to recognize and analyze archaeological sites in the central area of Sicily (Italy)

Contact Info

Product

Resources

About