Effects of Training Samples and Classifiers on Classification of Landsat-8 Imagery

In this study, we used Landsat-8 imagery to test object- and pixel-based image classification approaches in an urban fringe area. For object-based classification, we applied four machine learning classifiers: decision tree (DT), naive Bayes (NB), random trees (RT), and support vector machine (SVM). For pixel-based classification, we utilized the maximum likelihood classifier (MLC). Specifically, we explored the influence of repeated sampling on classification results with different training sample sizes. We found that (1) except the overall accuracy of NB, those of the other four classifiers increased as the training sample size increased; (2) repeated sampling had a significant effect on classification accuracy, especially for the DT and NB classifiers; and (3) SVM achieved the best classification accuracy. In addition, the performance of the object-based classifiers was superior to that of the pixel-based classifier. The results of this study can provide guidance on the training sample size and classifier selection.

[1]  Weiqi Zhou,et al.  Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery , 2014, Remote Sensing.

[2]  Paul M. Mather,et al.  Computer Processing of Remotely-Sensed Images: An Introduction , 1988 .

[3]  Massimiliano Pittore,et al.  Performance Evaluation of Machine Learning Algorithms for Urban Pattern Recognition from Multi-spectral Satellite Images , 2014, Remote. Sens..

[4]  Patricia Gober,et al.  Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery , 2011, Remote Sensing of Environment.

[5]  Jie Wang,et al.  Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery , 2014, Remote. Sens..

[6]  Ruiliang Pu,et al.  Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery , 2011 .

[7]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[8]  Farhad Samadzadegan,et al.  Context Aware Modification on the Object Based Image Analysis , 2015, Journal of the Indian Society of Remote Sensing.

[9]  Annemarie Schneider,et al.  Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach , 2012 .

[10]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[13]  Zhang Xiangmin,et al.  Comparison of pixel‐based and object‐oriented image classification approaches—a case study in a coal fire area, Wuda, Inner Mongolia, China , 2006 .

[14]  Jim Piper.  The effect of zero feature correlation assumption on maximum likelihood based classification of chromosomes , 1987 .

[15]  Y. Shimabukuro,et al.  Landsat‐5 Thematic Mapper data for pre‐planting crop area evaluation in tropical countries , 2003 .

[16]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .

[17]  Lei Ma,et al.  Training set size, scale, and features in Geographic Object-Based Image Analysis of very high resolution unmanned aerial vehicle imagery , 2015 .

[18]  Giles M. Foody,et al.  Training set size requirements for the classification of a specific class , 2006 .

[19]  B. Datt,et al.  On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification , 2005 .

[20]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[21]  P. Gong,et al.  Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery , 2006 .

[22]  D. Civco,et al.  Optimizing multi-resolution segmentation scale using empirical methods: Exploring the sensitivity of the supervised discrepancy measure Euclidean distance 2 (ED2) , 2014 .