Sub-pixel mapping of remote sensing images based on radial basis function interpolation

Wang, Qunming; Shi, Wenzhong; Atkinson, Peter M.

doi:10.1016/j.isprsjprs.2014.02.012

Cited by 101 publications

(61 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decades, many SRM methods have been proposed. These methods involve the pixel swapping algorithm [7,13], Hopfield neural networks [14][15][16], subpixel/pixel spatial attraction models [17][18][19], Markov random fields [20][21][22][23], the geometric methods [24,25], geostatistical methods [26][27][28], artificial intelligence-based algorithms [29][30][31][32][33] and interpolation-based methods [34][35][36]. These methods have obtained acceptable performances in various applications, such as urban tree identification [37], urban building extraction [38], floodplain inundation mapping [39,40] and land use mapping [41].…”

mentioning

confidence: 99%

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Chen

Heuvelink

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

mentioning

confidence: 99%

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Chen

Heuvelink

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

“…Additional types of neural networks (e.g., a radial basis functions or RBFs) and other advanced machine learning algorithms (e.g., Random Forest and Support Vector Machines) showed strong generalization performance for various remote sensing classification problems (Mountrakis et al, 2011;H. Wang et al, 2014, Q. Wang et al, 2014. For a future study, their spatial generalization effectiveness needs to be examined and compared with the NN classifier used in this study.…”

Section: Discussionmentioning

confidence: 99%

Characterizing major agricultural land change trends in the Western Corn Belt

Shao

Taff²,

Ren

et al. 2016

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

a b s t r a c tIn this study we developed annual corn/soybean maps for the Western Corn Belt within the United States using multi-temporal MODIS NDVI products from 2001 to 2015 to support long-term cropland change analysis. Based on the availability of training data (cropland data layer from the USDA-NASS), we designed a cross-validation scheme for 2006-2015 MODIS data to examine the spatial generalization capability of a neural network classifier. Training data points were derived from a three-state subregion consisting of North Dakota, Nebraska, and Iowa. Trained neural networks were applied to the testing sub-region (South Dakota, Kansas, Minnesota, and Missouri) to generate corn/soybean maps. Using a default threshold value (neural network output signal P 0.5), the neural networks performed well for South Dakota and Minnesota. Overall accuracy was higher than 80% (kappa > 0.55) for all testing years from 2006 to 2015. However, we observed high variation of classification performance for Kansas (overall accuracy: 0.71-0.82) and Missouri (overall accuracy: 0.65-0.77) for various testing years. We developed a threshold-moving method that decreases/increases threshold values of neural network output signals to match MODIS-derived corn/soybean acreage with the NASS acreage statistics. Over 70% of testing states and years showed improved classification performance compared to the use of a default 0.5 threshold. The largest improvement of kappa value was about 0.08. This threshold-moving method was used to generate MODIS-based annual corn/soybean map products for 2001-2015. A non-parametric Mann-Kendall test was then used to identify areas that showed significant (p < 0.05) upward/downward trends. Areas showing fast increase of corn/soybean intensities were mainly located in North Dakota, South Dakota, and the west portion of Minnesota. The highest annual increase rate for a 5-km moving window was about 6.8%. Ó

show abstract

“…The APP is an index with which to evaluate the areal spatial pattern, because most existing SPM methods are suited to areal features [16,18,24,25,40]. The APP is equal to the area of features with areal pattern, divided by the total area:…”

Section: Areal Pattern Proportionmentioning

confidence: 99%

“…The accuracy might decrease with increasing zoom factor [6,24,40,41], and therefore we are interested in establishing at which zoom factor the accuracy stabilizes.…”

Section: Spm Performance With Different Zoom Factorsmentioning

confidence: 99%

Designing an Experiment to Investigate Subpixel Mapping as an Alternative Method to Obtain Land Use/Land Cover Maps

Jiang

Chen

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Abstract:Various subpixel mapping (SPM) methods have been proposed as downscaling techniques to reduce uncertainty in classifying mixed pixels. Such methods can provide category maps of a higher spatial resolution than the original input images. The aim of this study was to explore and validate the potential of SPM as an alternative method for obtaining land use/land cover (LULC) maps of regions where high-spatial-resolution LULC maps are unavailable. An experimental design was proposed to evaluate the feasibility of SPM for providing the alternative LULC maps. A case study was implemented in the Jingjinji region of China. SPM results for spatial resolutions of 500-100 m were derived from a single 1-km synthetic fraction image using two representative SPM methods. The 1-km synthetic fraction image was assumed to be error free. Accuracy assessment and analysis showed that overall accuracies of the SPM results were reduced from about 85% to 75% with increasing spatial resolution, and that producer's accuracies varied considerably from about 62% to 93%. SPM performed best when handling areal features in comparison with linear and point features. The highest accuracies were achieved for areas with the lowest complexity. The study concluded that the results from SPM could provide an alternative LULC data source with acceptable accuracy, especially in areas with low complexity and with a large proportion of areal features.

show abstract

Sub-pixel mapping of remote sensing images based on radial basis function interpolation

Cited by 101 publications

References 49 publications

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Characterizing major agricultural land change trends in the Western Corn Belt

Designing an Experiment to Investigate Subpixel Mapping as an Alternative Method to Obtain Land Use/Land Cover Maps

Contact Info

Product

Resources

About