Assessing the classification accuracy of multisource remote sensing data

Fitzgerald, Robert; Lees, Brian

doi:10.1016/0034-4257(94)90103-1

Cited by 129 publications

(56 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One potential problem associated with automatically classified maps is the production of omission and commission errors due to spectral similarity among targets or algorithm limitations (Shlien and Smith, 1975;Fitzgerald and Lees, 1994;Stehman, 1997;Salovaara et al, 2005). Thus, in order to generate more clearly differentiated results, we performed a manual edit of the maps to correct for class confusion and to adjust the limits of the land cover classes.…”

Section: Generating the Landscape Mapsmentioning

confidence: 99%

Influence of landscape heterogeneity on spatial patterns of wood productivity, wood specific density and above ground biomass in Amazonia

et al. 2009

View full text Add to dashboard Cite

Abstract. Long-term studies using the RAINFOR network of forest plots have generated significant insights into the spatial and temporal dynamics of forest carbon cycling in Amazonia. In this work, we map and explore the landscape context of several major RAINFOR plot clusters using Landsat ETM+ satellite data. In particular, we explore how representative the plots are of their landscape context, and test whether bias in plot location within landscapes may be influencing the regional mean values obtained for important forest biophysical parameters. Specifically, we evaluate whether the regional variations in wood productivity, wood specific density and above ground biomass derived from the RAINFOR network could be driven by systematic and unintentional biases in plot location. Remote sensing data covering 45 field plots were aggregated to generate landscape maps to identify the specific physiognomy of the plots. In the Landsat ETM+ data, it was possible to spectrally differentiate three types of terra firme forest, three types of forests over Paleovarzea geomorphologycal formation, two types of bamboo-dominated forest, palm forest, Heliconia monodominant vegetation, swamp forest, disturbed forests and land Correspondence to: L. O. Anderson (liana.anderson@ouce.ox.ac.uk) use areas. Overall, the plots were generally representative of the forest physiognomies in the landscape in which they are located. Furthermore, the analysis supports the observed regional trends in those important forest parameters. This study demonstrates the utility of landscape scale analysis of forest physiognomies for validating and supporting the finds of plot based studies. Moreover, the more precise geolocation of many key RAINFOR plot clusters achieved during this research provides important contextual information for studies employing the RAINFOR database.

show abstract

Section: Generating the Landscape Mapsmentioning

confidence: 99%

Influence of landscape heterogeneity on spatial patterns of wood productivity, wood specific density and above ground biomass in Amazonia

et al. 2009

View full text Add to dashboard Cite

show abstract

“…For different classification results three accuracy parameters -single class accuracy, total accuracy and total kappa coefficient [11] -were compared. All the classification accuracy parameters of fuzzy ARTMAP were better than those of the other two results.…”

Section: Results and Analysesmentioning

confidence: 99%

Classification of CBERS-2 imagery with fuzzy ARTMAP classifier

Luo

Liu²,

Yan³

2007

Geo-spatial Information Science

View full text Add to dashboard Cite

A fuzzy ARTMAP classifier is adopted for a classification experiment of CBERS-2 imagery. The fundamental theory and processing about the algorithm are first introduced, followed with a land-use classification experiment in Shihezi County on CBERS-2 high resolution imagery. Three classifiers are compared: maximum likelihood classifier (MLC), error back propagation (BP) classifier, and fuzzy ARTMAP classifier. The comparison shows comparably better results for the fuzzy ARTMAP classifier, with overall classification accuracy of 9.9% and 4.6% higher than that of MLC and BP. The results also prove that the fuzzy ARTMAP classifier has better discernment in identifying bare soil on CBERS-2 imagery.

show abstract

“…Each photo interpreter's (observer's) classification accuracy was assessed at each scale (Story and Congalton 1986;Congalton 1991;Fitzgerald and Lees 1994). Data were assembled into classification error matrices by observer and scale comparing observer interpretations to field-sampled reference data at each site.…”

Section: Discussionmentioning

confidence: 99%

Multiscale Detection of Sulfur Cinquefoil Using Aerial Photography

Endress¹

2005

REM

View full text Add to dashboard Cite

We evaluated the effectiveness of natural color aerial photography as a tool to improve detection, monitoring, and mapping of sulfur cinquefoil (Potentilla recta L.) infestations. Sulfur cinquefoil is an exotic perennial plant invading interior Pacific Northwest rangelands. Because sulfur cinquefoil produces distinctive pale yellow flowers, we timed aerial photography for early July, when the plant was at peak bloom. Photography was collected at 3 spatial scales (1:3 000, 1:6 000, and 1:12 000). A grid with 250-m spacing was superimposed over photographs of the entire study area using geographic information systems. At each grid intersection point (n ¼ 80), we visually analyzed the photographs within a 404.7-m 2 (0.1 acre) circular plot, recorded sulfur cinquefoil presence, and estimated sulfur cinquefoil percent cover. Sample points on the grid were then located in the field using a global positioning system. Field data collected at each point included sulfur cinquefoil presence, percent cover, and stem density; and total vegetation composition and percent cover by life form. Results indicate that the accuracy of detecting sulfur cinquefoil increased from small to large scale. At the 1:3 000 scale, sulfur cinquefoil presence was correctly identified in 76.9% of the sites, whereas at the 1:6 000 and 1:12 000 scales, infestations were identified in 67.9% and 59.1% of the sites, respectively. Low-density infestations (, 1% cover) were detected at all scales. Accuracy of percent cover estimates ranged from 33.8% to 38.0% across scales. Although tree canopy hindered detection, our results indicate that aerial photography can be used to detect sulfur cinquefoil infestations in open forests and rangelands in the Intermountain West. ResumenEvaluamos la efectividad de la fotografía aérea de color natural como una herramienta para mejorar la detecció n, monitoreo y mapeo de las infestaciones del ''Sulfur cinquefoil'' (Potentilla recta L.) la cual es una planta perenne exó tica que esta invadiendo los pastizales interiores de la regió n noroeste del Pacífico. Debido a que el ''Sulfur cinquefoil'' produce flores de color amarillo pá lido que es distintivo, programamos la fotografía para inicios de Julio, cuando la planta esta el má ximo de floració n. La fotografía se colectó a tres escalas espaciales (1:3 000, 1:6 000, 1:12 000). Una cuadrícula con espaciamiento de 250-m entre puntos se sobrepuso en las fotografías del á rea total de estudio usando sistemas de informació n geográ fica. En cada punto de intersecció n de la cuadrícula (n ¼ 80), analizamos visualmente las fotografías dentro de una parcela circular de 0.1-acre, registrando la presencia de ''Sulfur cinquefoil'' y estimamos el porcentaje de cobertura de esta especie. Los puntos de la muestra en la cuadrícula fueron localizados en el campo usando un sistema de posicionamiento global. Los datos de campo colectados en cada punto incluyeron la presencia de ''Sulfur cinquefoil'', el porcentaje de cobertura, la densidad de tallos, la composició n total de la ...

show abstract

Assessing the classification accuracy of multisource remote sensing data

Cited by 129 publications

References 5 publications

Influence of landscape heterogeneity on spatial patterns of wood productivity, wood specific density and above ground biomass in Amazonia

Influence of landscape heterogeneity on spatial patterns of wood productivity, wood specific density and above ground biomass in Amazonia

Classification of CBERS-2 imagery with fuzzy ARTMAP classifier

Multiscale Detection of Sulfur Cinquefoil Using Aerial Photography

Contact Info

Product

Resources

About