Land Cover Heterogeneity Effects on Sub-Pixel and  Per-Pixel Classifications

Tran, Trung; Julian, Jason P.; Beurs, Kirsten M. de

doi:10.3390/ijgi3020540

Cited by 21 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tran, Julian, and de Beurs (2014) have demonstrated that sub-pixel classification was only advantageous compared to its per-pixel equivalent for heterogeneous landscapes.…”

Section: S Heremans and J Van Orshovenmentioning

confidence: 99%

Machine learning methods for sub-pixel land-cover classification in the spatially heterogeneous region of Flanders (Belgium): a multi-criteria comparison

Heremans

Orshoven

2015

International Journal of Remote Sensing

View full text Add to dashboard Cite

Until now, few research has addressed the use of machine learning methods for classification at the sub-pixel level. To close this knowledge gap, in this article, six machine learning methods were compared for the specific task of sub-pixel land-cover extraction in the spatially heterogeneous region of Flanders (Belgium). In addition to the classification accuracy at the pixel and the municipality level, three evaluation criteria reflecting the methods' ease-of-use were added to the comparison: the time needed for training, the number of meta-parameters, and the minimum training set size. Robustness to changing training data was also included as the sixth evaluation criterion. Based on their scores for these six criteria, the machine learning methods were ranked according to three multi-criteria ranking scenarios. These ranking scenarios correspond to different decision-making scenarios that differ in their weighting of the criteria. In general, no overall winner could be designated: no method performs best for all evaluation scenarios. However, when both time available for preprocessing and the magnitude of the training data set are unconstrained, Support Vector Machines (SVMs) clearly outperform the other methods.

show abstract

“…Tran, Julian, and de Beurs (2014) have demonstrated that sub-pixel classification was only advantageous compared to its per-pixel equivalent for heterogeneous landscapes.…”

Section: S Heremans and J Van Orshovenmentioning

confidence: 99%

Machine learning methods for sub-pixel land-cover classification in the spatially heterogeneous region of Flanders (Belgium): a multi-criteria comparison

Heremans

Orshoven

2015

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…If mapping is done by fieldwork, the quality may be variable as a result of differences in the complexity of the landscape and in the mapping skills of individual workers, as well as in their perception of the landscape. Smith et al [32], van Oort et al [22], and Tran et al [33] found that the probability of correct classification of satellite images depended on landscape complexity. The probability of correct classification was higher in more homogeneous landscapes and lower in heterogeneous landscapes.…”

Section: Introductionmentioning

confidence: 99%

The Implications of Field Worker Characteristics and Landscape Heterogeneity for Classification Correctness and the Completeness of Topographical Mapping

Mõisja

Uuemaa

Oja

2018

IJGI

View full text Add to dashboard Cite

Abstract:The quality of spatial data may vary spatially. If mapping (interpretation of orthophotos) is done during fieldwork, this variation in quality may occur as a result of differences in the complexity of the landscape, differences in the characteristics of individual field workers, and differences in their perception of the landscape. In this study, we explored the interaction between the characteristics of these workers, including their gender and years of experience (as a proxy for their mapping skills), and landscape heterogeneity. There was no significant difference between male and female workers. Although field workers with more years of experience generally had higher mapping quality, the relationship was not statistically significant. We found differences in the rates of misclassification, omission, and commission errors between workers in different landscape types. We conclude that the error rates due to misclassification, omission, and commission were the lowest in more diverse landscapes (high number of different land use types) with a relatively high amount of buildings, whereas the error rates were the highest in mainly forested landscapes with larger and more complex shaped patches.

show abstract

“…Confusion matrices are the most commonly used method for evaluating the classification accuracy of remote-sensing images [55]. They are mainly used to compare the classification results with real information from the surface.…”

Section: Accuracy Evaluation Of Classification Resultsmentioning

confidence: 99%

Land Cover Information Extraction Based on Daily NDVI Time Series and Multiclassifier Combination

Zhao

Zhang

Pan

2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A timely and accurate understanding of land cover change has great significance in management of area resources. To explore the application of a daily normalized difference vegetation index (NDVI) time series in land cover classification, the present study used HJ-1 data to derive a daily NDVI time series by pretreatment. Different classifiers were then applied to classify the daily NDVI time series. Finally, the daily NDVI time series were classified based on multiclassifier combination. The results indicate that support vector machine (SVM), spectral angle mapper, and classification and regression tree classifiers can be used to classify daily NDVI time series, with SVM providing the optimal classification. The classifiers of -means and Mahalanobis distance are not suited for classification because of their classification accuracy and mechanism, respectively. This study proposes a method of dimensionality reduction based on the statistical features of daily NDVI time series for classification. The method can be applied to land resource information extraction. In addition, an improved multiclassifier combination is proposed. The classification results indicate that the improved multiclassifier combination is superior to different single classifier combinations, particularly regarding subclassifiers with greater differences.

show abstract

Land Cover Heterogeneity Effects on Sub-Pixel and Per-Pixel Classifications

Cited by 21 publications

References 45 publications

Machine learning methods for sub-pixel land-cover classification in the spatially heterogeneous region of Flanders (Belgium): a multi-criteria comparison

Machine learning methods for sub-pixel land-cover classification in the spatially heterogeneous region of Flanders (Belgium): a multi-criteria comparison

The Implications of Field Worker Characteristics and Landscape Heterogeneity for Classification Correctness and the Completeness of Topographical Mapping

Land Cover Information Extraction Based on Daily NDVI Time Series and Multiclassifier Combination

Contact Info

Product

Resources

About