Quality assessment of image classification algorithms for land-cover mapping: A review and a proposal for a cost-based approach

Smits, P.C.; Dellepiane, S.; Schowengerdt, Robert A.

doi:10.1080/014311699212560

Cited by 304 publications

(180 citation statements)

References 0 publications

Supporting

Mentioning

154

Contrasting

Unclassified

Order By: Relevance

“…Error matrices were used to assess classification accuracy using four measures of accuracy: overall accuracy, user's accuracy, producer's accuracy and Kappa statistics. The meaning of and calculation for these terms have been explained in detail in many studies (Congalton 1991;Smits et al, 1999;Plourde and Congalton, 2003;Foody 2002).The user's accuracy indicates the probability that a pixel on the image actually represents that class on the ground (Story and Congalton, 1986). It is calculated for each class by dividing the correctly classified pixels by the row total for that class.…”

Section: Forestmentioning

confidence: 99%

“…The error matrix is the most widely used approach for image classification accuracy assessment and can be used to derive a series of descriptive and analytical statistics (Congalton and Mead;Congalton, 1991;Congalton and Green, 1999;Smits et al, 1999;Congalton and Plourde, 2002;Foody, 2002;Liu et al, 2007). In this study, accuracy assessment was performed for the classified maps of all three time steps.…”

Section: Forestmentioning

confidence: 99%

See 1 more Smart Citation

Using Landsat Satellite Imagery to Determine Land Use/Land Cover Changes in Međimurje County, Croatia

Horvat¹

2014

Hrv. geogr. glas.

View full text Add to dashboard Cite

using Landsat satellite images. Spatial dynamics of LU/LC changes were quantified using three Landsat satellite images: MSS, TM and ETM+. Three series of the LU/LC maps of 1978, 1992 and 2007 were produced. Based on the Anderson classification system, LU/LC are classified as: water bodies, forest land, barren land, agricultural land and urban built-up land. Error matrices were used to assess classification accuracy. Significant buildings construction, construction of the reservoir lakes on the Drava River and construction of a highway were major drives of LU/ LC changes in Međimurje County over the study period. This study showed a continuous decrease in agricultural lands in Međimurje County. Consequently, the urban built-up area and the water area increased.Key words: land use/land cover, land use/land cover changes, satellite imageries, Međimurje County Upotreba satelitskih snimaka Landsat za utvrđivanje promjena u načinu upotrebe i pokrovu zemljišta u Međimurskoj županiji u Hrvatskoj U radu se procjenjuju promjene u načinu upotrebe i pokrovu zemljišta u Međimurskoj županiji u Hrvatskoj u razdobljima 1978Hrvatskoj u razdobljima . -1992Hrvatskoj u razdobljima ., 1992Hrvatskoj u razdobljima . -2007Hrvatskoj u razdobljima . i 1978Hrvatskoj u razdobljima . -2007. upotrebom satelitskih snimaka Landsat. Prostorna dinamika promjena načina upotrebe zemljišta i pokrova kvantificirana je upotrebom triju serija satelitskih snimaka Landsat. Izrađene su tri serije karata načina upotrebe i pokrova zemljišta, za 1978., 1992. i 2007. godinu. Na temelju Andersonova klasifikacijskog sustava način upotrebe i pokrov zemljišta klasificirani su kao vodene površine, šumske površine, golo tlo, poljoprivredne površine i urbano područje. Za ocjenu točnosti klasifikacije poslužila je matrica pogrešaka. Značajna izgradnja zgrada, izgradnja akumulacijskih jezera na rijeci Dravi i autoceste najznačajnije su promjene u načinu upotrebe i pokrovu zemljišta u Međimurskoj županiji tijekom promatranog razdoblja. Istraživanje pokazuje kontinuirano smanjenje poljoprivrednog zemljišta u Međimurskoj županiji, zbog čega su građevinsko zemljište i vodene površine povećani.Ključne riječi: upotreba zemljišta, promjene upotrebe zemljišta, satelitske snimke, Međimurska županija Preliminary communicationPrethodno priopćenje 6Hrvatski geografski glasnik 75/2 (2013.)

show abstract

Section: Forestmentioning

confidence: 99%

Section: Forestmentioning

confidence: 99%

Using Landsat Satellite Imagery to Determine Land Use/Land Cover Changes in Međimurje County, Croatia

Horvat¹

2014

Hrv. geogr. glas.

View full text Add to dashboard Cite

show abstract

“…Review papers on the use of remote sensing for land use land cover classification are provided in Bastiaanssen (1998), Smits et al (1999), Mucher et al (2000), Cihlar (2000), Franklin and Wulder (2002), Thenkabail et al (2009b), and García-Mora et al (2012).…”

Section: Land Usementioning

confidence: 99%

Spatial evapotranspiration, rainfall and land use data in water accounting – Part 1: Review of the accuracy of the remote sensing data

Karimi

Bastiaanssen

2015

Hydrol. Earth Syst. Sci.

124

View full text Add to dashboard Cite

Abstract. The scarcity of water encourages scientists to develop new analytical tools to enhance water resource management. Water accounting and distributed hydrological models are examples of such tools. Water accounting needs accurate input data for adequate descriptions of water distribution and water depletion in river basins. Ground-based observatories are decreasing, and not generally accessible. Remote sensing data is a suitable alternative to measure the required input variables. This paper reviews the reliability of remote sensing algorithms to accurately determine the spatial distribution of actual evapotranspiration, rainfall and land use. For our validation we used only those papers that covered study periods of seasonal to annual cycles because the accumulated water balance is the primary concern. Review papers covering shorter periods only (days, weeks) were not included in our review. Our review shows that by using remote sensing, the absolute values of evapotranspiration can be estimated with an overall accuracy of 95 % (SD 5 %) and rainfall with an overall absolute accuracy of 82 % (SD 15 %). Land use can be identified with an overall accuracy of 85 % (SD 7 %). Hence, more scientific work is needed to improve the spatial mapping of rainfall and land use using multiple space-borne sensors. While not always perfect at all spatial and temporal scales, seasonally accumulated actual evapotranspiration maps can be used with confidence in water accounting and hydrological modeling.

show abstract

“…The 'error matrix' (also known as confusion matrix, confusion table, and contingency table) is central to most measures of thematic map accuracy (Story and Congalton, 1986;Smits et al, 1999;Foody, 2004;Powell et al, 2004 andGupta et al, 2008). Once a prediction threshold has been adopted by the mathematical model, the binary prediction (failed/unfailed) can be compared with the landslide observed.…”

Section: Introductionmentioning

confidence: 99%

“…A number of approaches have been developed to test the accuracy of landslide spatial prediction maps (Congalton, 1991;Stehman and Czaplewski, 1998;Smits et al, 1999) that can be used to assess the classification maps. The 'error matrix' (also known as confusion matrix, confusion table, and contingency table) is central to most measures of thematic map accuracy (Story and Congalton, 1986;Smits et al, 1999;Foody, 2004;Powell et al, 2004 andGupta et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

Statistical and spatial analysis of landslide susceptibility maps with different classification systems

Baeza¹,

Lantada

Amorim

2016

Environ Earth Sci

View full text Add to dashboard Cite

A landslide susceptibility map is an essential tool for land-use spatial planning and management in mountain areas. However, a classification system used for readability determines the final appearance of the map and may therefore influence the decision-making tasks adopted. The present paper addresses the spatial comparison and the accuracy assessment of some well-known classification methods applied to a susceptibility map that was based on a discriminant statistical model in an area in the Eastern Pyrenees. A number of statistical approaches (Spearman's correlation, Kappa index, Factorial and Cluster analyses and Landslide density index) for map comparison were performed to quantify the information provided by the usual image analysis.The results showed the reliability and consistency of the Kappa index against Spearman's correlation as accuracy measures to assess the spatial agreement between maps. Inferential tests between unweighted and linear weighted Kappa results showed that all the maps were more reliable in classifying areas of highest susceptibility and less reliable in classifying areas of low to moderate susceptibility. The spatial variability detected and quantified by Factorial and Cluster analyses showed that the maps classified by Quantile and Natural Break methods were the closest whereas those classified by Landslide Percentage and Equal Interval methods displayed the greatest differences. The difference image analysis showed that the five classified maps only matched 9% of the area. This area corresponded to the steeper slopes and the steeper watershed angle with forestless and sunny slopes at low altitudes. This means that the five maps coincide in identifying and classifying the most dangerous areas. The Equal Interval map overestimated the susceptibility of the study area and the Landslide Percentage map was considered to be a very optimistic model. The spatial pattern of the Quantile and Natural Break maps was very similar but the latter was more consistent and predicted potential landslides more efficiently and reliably in the study area.

show abstract

Quality assessment of image classification algorithms for land-cover mapping: A review and a proposal for a cost-based approach

Cited by 304 publications

References 0 publications

Using Landsat Satellite Imagery to Determine Land Use/Land Cover Changes in Međimurje County, Croatia

Using Landsat Satellite Imagery to Determine Land Use/Land Cover Changes in Međimurje County, Croatia

Spatial evapotranspiration, rainfall and land use data in water accounting – Part 1: Review of the accuracy of the remote sensing data

Statistical and spatial analysis of landslide susceptibility maps with different classification systems

Contact Info

Product

Resources

About