Improving urban classification through fuzzy supervised classification and spectral mixture analysis

Tang, Jinshan; Wang, L.; Myint, Soe W.

doi:10.1080/01431160701227687

Cited by 31 publications

(23 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That is, the entire study area is classified into three pure land cover types (e.g., ISA, soil, vegetation) and three mixed land cover types (e.g., ISA-vegetation, soil-vegetation, and ISA-soil-vegetation). With this approach, a major limitation of pixel-based hard classifications, that only one land cover class can be assigned to a pixel [13,20], has been successfully addressed by allowing the assignment of pixels into a mixed land cover class.…”

Section: Discussionmentioning

confidence: 99%

“…In urban and suburban environments, however, inter-class and intra-class spectral variability widely exist [6][7][8][9][10]. Therefore, the capability of traditional SMA models in dealing with complex urban and suburban landscapes has been questioned, as the few endmembers may not be able to represent their corresponding land cover classes [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Class-Based Multiple Endmember Spectral Mixture Analysis (C-MESMA) Approach for Analyzing Urban Environments

Deng

2016

Remote Sensing

View full text Add to dashboard Cite

Abstract:Multiple endmember spectral mixture analysis (MESMA) has been widely applied for estimating fractional land covers from remote sensing imagery. MESMA has proven effective in addressing inter-class and intra-class endmember variability by allowing pixel-specific endmember combinations. This method, however, assumes that each land cover type has an equal probability of being included in the model, and the one with the least estimation error (e.g., root mean square error) was chosen as the "best-fit" model. Such an approach may mistakenly include a land cover class in the model and overestimate its abundance, or it might omit a class from the model and subsequently lead to underestimation. To address this problem, this paper developed a land cover class-based multiple endmember spectral mixture analysis (C-MESMA) method. In particular, a support vector machine (SVM) method with reflectance spectra and spectral indices, including the normalized difference vegetation index (NDVI), the biophysical composition index (BCI), and the ratio normalized difference soil index (RNDSI), were employed to classify the image into six land cover classes: pure impervious surface area (ISA), pure vegetation, pure soil, ISA-vegetation, vegetation-soil, and vegetation-ISA-soil. With the information of land cover classes, an individual MESMA method was applied to each mixed class. Finally, the fractional maps were derived through integrating land cover fractions of each land cover class. Quantitative analysis of the resulting percent ISA (%ISA) and comparative analyses with traditional MESMA indicate that C-MESMA improved the estimation accuracy of %ISA.Keywords: multiple endmember spectral mixture analysis (MESMA); class-based multiple endmember spectral mixture analysis (C-MESMA); support vector machine (SVM)

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development of a Class-Based Multiple Endmember Spectral Mixture Analysis (C-MESMA) Approach for Analyzing Urban Environments

Deng

2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In the pixel based validation, we used the Cohen`s kappa statistics (Congalton, 1991), which is also known as kappa coefficient to assess the accuracy of the generated SRM using the contingency tables. For the sub pixel based validation we used the mean absolute error (MAE) (Tang et al, 2007)- Table 2. Fuzzy and conventional mean values for the V-I-S classes.…”

Section: Resultsmentioning

confidence: 99%

Improving Markov Random Field Based Super Resolution Mapping Through Fuzzy Parameter Integration

Welikanna

Tamura

Tolpekin

et al. 2012

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

The objective of this study was to improve the Markov Random Field (MRF) based Super Resolution Mapping (SRM) technique to account for the vague land-cover interpretations (class mixture and the intermediate conditions) in an urban area. The algorithm has been improved to integrate the fuzzy mean and fuzzy covariance measurements, to a MRF based SRM scheme to optimize the classification results. The technique was tested on a WORLDVIEW-2 data set, acquired over a highway construction area, in Colombo, Sri Lanka. Based on the visual interpretation of the image, three major land-cover types of this area were identified for the study; those were vegetation, soil and exposed grass and impervious surface with low medium and high albedo. The membership values for each pixel were determined from training samples through Spectral Angle Mapper (SAM) technique. The compulsory fuzzy mean and the covariance measurements were derived using these membership grades, and subsequently was applied in MRF based SRM technique. The primary reference data was generated using Maximum Likelihood Classification (MLC) performed on the same data which was resampled to 1m resolution. The scale factor was set to be (S) =2, to generate SRM of 1m resolution. The smoothening parameter (λ) which balances the prior and likelihood energy terms were tested in the range from 0.3 to 0.9. SRM were generated using fuzzy MRF and the conventional MRF models respectively. Results suggest that the fuzzy integrated model has improved the results with an overall accuracy of 85.60% and kappa value of 0.78 between the optimal results and the reference data, while in the conventional case it was 77.81% of overall accuracy with kappa being 0.65. Among the two MRF models, fuzzy parameter integrated model shows the highest agreement with class fractions from the reference image with a smallest average _MAE (MAE, Mean Absolute Error) of 0.03.

show abstract

“…However the rapid change of the urban land-cover categories within a small distance resulting similar entities at different locations, majority of land-cover types being internally heterogeneous and intermediate conditions of the class boundaries make the urban landscape a complex and vague entity (Forster, 1983;Wang, 1990;Wood and Foody, 1993;Bastin et al, 2002;Fisher et al, 2006;Tang et al, 2007;Foody and Matur, 2006). Satellite missions with their global view over the earth surface provide useful and rapid information for urban mapping, map updating and urban change detection.…”

Section: Introductionmentioning

confidence: 99%

Incorporating uncertanity into Markov random field classification with the combine use of optical and SAR images and aduptive fuzzy mean vector

Welikanna

Tamura

Susaki

2014

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:A Markov Random Field (MRF) model accounting for the classification uncertainty using multisource satellite images and an adaptive fuzzy class mean vector is proposed in this study. The work also highlights the initialization of the class values for an MRF based classification for synthetic aperture radar (SAR) images using optical data. The model uses the contextual information from the optical image pixels and the SAR pixel intensity with corresponding fuzzy grade of memberships respectively, in the classification mechanism. Sub pixel class fractions estimated using Singular Value Decomposition (SVD) from the optical image initializes the class arrangement for the MRF process. Pair-site interactions of the pixels are used to model the prior energy from the initial class arrangement. Fuzzy class mean vector from the SAR intensity pixels is calculated using Fuzzy C-means (FCM) partitioning. Conditional probability for each class was determined by a Gamma distribution for the SAR image. Simulated annealing (SA) to minimize the global energy was executed using a logarithmic and power-law combined annealing schedule. Proposed technique was tested using an Advanced Land Observation Satellite (ALOS) phased array type L-band SAR (PALSAR) and Advanced Visible and Near-Infrared Radiometer-2 (AVNIR-2) data set over a disaster effected urban region in Japan. Proposed method and the conventional MRF results were evaluated with neural network (NN) and support vector machine (SVM) based classifications. The results suggest the possible integration of an adaptive fuzzy class mean vector and multisource data is promising for imprecise class discrimination using a MRF based classification.

show abstract

Improving urban classification through fuzzy supervised classification and spectral mixture analysis

Cited by 31 publications

References 39 publications

Development of a Class-Based Multiple Endmember Spectral Mixture Analysis (C-MESMA) Approach for Analyzing Urban Environments

Development of a Class-Based Multiple Endmember Spectral Mixture Analysis (C-MESMA) Approach for Analyzing Urban Environments

Improving Markov Random Field Based Super Resolution Mapping Through Fuzzy Parameter Integration

Incorporating uncertanity into Markov random field classification with the combine use of optical and SAR images and aduptive fuzzy mean vector

Contact Info

Product

Resources

About