ASTER/Terra Imagery and a Multilevel Semantic Network for Semi-automated Classification of Landforms in a Subtropical Area

Camargo, Pedro H. C.; Almeida, Cláudia Maria de; Florenzano, Teresa Gallotti; Heipke, Christian; Feitosa, Raul Queiroz; Costa, G. A. O. P.

doi:10.14358/pers.77.6.619

Cited by 8 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…with P = {p i } I i=1 denoting a non-representational point set containing I points, i k is the index of the kth neighbor of the ith point, K is the number of neighbors, and η ik is the weight of LGS defined by Equation (9). The partial derivative of Equation (27) with respect to the parameter W is obtained by:…”

Section: Implementation Detailsmentioning

confidence: 99%

A Small UAV Based Multi-Temporal Image Registration for Dynamic Agricultural Terrace Monitoring

Wei

Han

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Terraces are the major land-use type of agriculture and support the main agricultural production in southeast and southwest China. However, due to smallholder farming, complex terrains, natural disasters and illegal land occupations, a light-weight and low cost dynamic monitoring of agricultural terraces has become a serious concern for smallholder production systems in the above area. In this work, we propose a small unmanned aerial vehicle (UAV) based multi-temporal image registration method that plays an important role in transforming multi-temporal images into one coordinate system and determines the effectiveness of the subsequent change detection for dynamic agricultural terrace monitoring. The proposed method consists of four steps: (i) guided image filtering based agricultural terrace image preprocessing, (ii) texture and geometric structure features extraction and combination, (iii) multi-feature guided point set registration, and (iv) feature points based image registration. We evaluated the performance of the proposed method by 20 pairs of aerial images captured from Longji and Yunhe terraces, China using a small UAV (the DJI Phantom 4 Pro), and also compared against four state-of-the-art methods where our method shows the best alignments in most cases.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

A Small UAV Based Multi-Temporal Image Registration for Dynamic Agricultural Terrace Monitoring

Wei

Han

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The extended algorithm to reduce the uniform segments from the image segmentation result is explored through multi resolutions segmentation (MRS). The newest usage of OBIA for combined land-cover and landform mapping has just been applied for mapping the vegetation, canal, and mud flats using very high spatial resolution imageries [7,8,9]. Therefore, in this paper, the aims of the study are to examine the ability of radar interferometry imagery in mapping landforms using segmentation method, and to identify the topographic elements composition of each landform mapping unit derived from "toposhape" analysis.…”

Section: Introductionmentioning

confidence: 99%

Identification of topographic elements composition based on landform boundaries from radar interferometry segmentation (preliminary study on digital landform mapping)

Widyatmanti

Wicaksono

Syam

2016

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Abstract. Dense vegetation that covers most landscapes in Indonesia becomes a common limitation in mapping the landforms in tropical region. This paper aims to examine the use of radar interferometry for landform mapping in tropical region; to examine the application of segmentation method to develop landform type boundaries; and to identify the topographic elements composition for each type of landform. Using Idrisi® and "eCognition ®" softwares, toposhape analysis, segmentation and multi-spectral classification were applied to identify the composition of topographic elements i.e. the types of land-cover from Landsat 8, elevation, slope, relief intensity and curvatures from SRTM (DEM). Visual interpretation on DEM and land-cover fusion imagery was conducted to derive basic control maps of landform and land-cover. The result shows that in segmentation method, shape and compactness levels are essential in obtaining land-cover, elevation, and slope class units to determine the most accurate class borders of each element. Despite a complex procedure applied in determining landform classification, the combination of topographic elements segmentation result presents a distinct border of each landform class. The comparison between landform maps derived from segmentation process and visual interpretation method demonstrates slight dissimilarities, meaning that multi-stage segmentation approach can improve and provide more effective digital landform mapping method in tropical region. Topographic elements on each type of landforms show distinctive composition key containing the percentage of each curvature elements per area unit. Supported by GIS programming and modeling in the future, this finding is significant in reducing effort in landform mapping using visual interpretation method for a very large coverage but in detail scale level. IntroductionThe application of remote sensing in geomorphic mapping has been developing vastly, coinciding with the launching of radar interferometry and its ability to provide digital surface/elevation model (DSM/DEM) [1]. One of the important parameters in geomorphic mapping is land physical characteristics information derived from landform classification and mapping, both in regional or global level. Landform, as the main element in geomorphic mapping, is a natural object feature that divides the earth surface into one main spatial unit [2]. It comprises the information of relief, elevation and the common land activities that dominating the landscape processes. DEM provides more promising data to the researchers in increasing the quality of landform mapping, because it consists of elevation information with 3-dimentional relief features. Nowadays, landform classification using DSM/DEM is one of basic research domain in digital terrain analysis, including GIS landscape integrated studies. The common free access and reliable 3-dimentional relief data used in many mapping applications is Shuttle Radar Topography Mission (SRTM) (Figure 1). This imagery has horizontal and vertical spatial ...

show abstract

“…Bispo et al (2009) avaliam o potencial das VG SRTM para identifi car classes de vegetação na Amazônia. Para o caso específi co da Geomorfologia, os trabalhos utilizam VG com o objetivo de desenvolver metodologias para automatizar o mapeamento geomorfológico (DRAGUT; EISANK, 2012;ANDERS et al, 2011;CAMARGO et al, 2011;BLASCHKE, 2006).…”

Section: Introductionunclassified

Relações Entre Dados SRTM E Classes Geomorfológicas Do Projeto Radambrasil

Fernandes

Valeriano

2014

Rev. Bras. Geomorfol.

View full text Add to dashboard Cite

ResumoO objetivo do presente trabalho é mostrar a relação entre dados geomorfométricos SRTM com as classes geomorfológicas mapeadas pelo projeto RADAMBRASIL até o terceiro nível taxonômico. Especifi camente, busca-se caracterizar por meio de análise visual e estatística descritiva as classes apresentadas em torno da geomorfometria extraída dos dados SRTM, e indicar, a partir das análises feitas, as VG diferenciadoras dessas classes. Os dados SRTM provenientes do projeto TOPODATA foram preparados e tratados em ambiente SIG, o que permitiu a análise visual e quantitativa das classes RADAMBRASIL, e a indicação de variáveis geomorfométricas separadoras de classes para uma área de estudo localizada no Estado do Rio de Janeiro, no entorno da Baía de Guanabara. A análise quantitativa foi feita com base em estatísticas descritivas extraídas no SIG, e em histogramas e gráfi cos boxplots. Os dados SRTM permitiram, no geral, a caracterização geomorfométrica regional, tanto visual quanto quantitativa, de classes de relevo RADAMBRASIL para cada nível taxonômico. As classes que mais se diferenciaram por uma maior quantidade de VG foram as classes do primeiro nível taxonômico, em que a altimetria, declividade e curvatura vertical mostraram potencial na separação dos Domínios Morfoestruturais. Nos demais táxons, menos variáveis geomorfométricas foram indicadas, e houve maior grau de confusão entre classes. As análises empregadas serviram para recuperar um modelo de conhecimento implícito no mapa RADAMBRASIL a partir das variáveis geomorfométricas, que permitiram o entendimento do comportamento geomorfométrico das classes, e assim, fazer algumas relações com seus processos formadores.

show abstract

ASTER/Terra Imagery and a Multilevel Semantic Network for Semi-automated Classification of Landforms in a Subtropical Area

Cited by 8 publications

References 25 publications

A Small UAV Based Multi-Temporal Image Registration for Dynamic Agricultural Terrace Monitoring

A Small UAV Based Multi-Temporal Image Registration for Dynamic Agricultural Terrace Monitoring

Identification of topographic elements composition based on landform boundaries from radar interferometry segmentation (preliminary study on digital landform mapping)

Relações Entre Dados SRTM E Classes Geomorfológicas Do Projeto Radambrasil

Contact Info

Product

Resources

About