Improving specific class mapping from remotely sensed data by cost-sensitive learning

Silva, Joel; Bacao, Fernando; Dieng, Maguette; Foody, Giles M.; Caetano, Mario

Abstract

In many remote-sensing projects, one is usually interested in a small number of land-cover classes present in a study area and not in all the land-cover classes that make-up the landscape. Previous studies in supervised classification of satellite images have tackled specific class mapping problem by isolating the classes of interest and combining all other classes into one large class, usually called others, and by developing a binary classifier to discriminate the class of interest from the others. Here, this approach is called focused approach. The strength of the focused approach is to decompose the original multi-class supervised classification problem into a binary classification problem, focusing the process on the discrimination of the class of interest. Previous studies have shown that this method is able to discriminate more accurately the classes of interest when compared with the standard multi-class supervised approach. However, it may be susceptible to data imbalance problems present in the training data set, since the classes of interest are often a small part of the training set. A result the classification may be biased towards the largest classes and, thus, be sub-optimal for the discrimination of the classes of interest. This study presents a way to minimize the effects of data imbalance problems in specific class mapping using cost-sensitive learning. In this approach errors committed in the minority class are treated as being costlier than errors committed in the majority class. Cost-sensitive approaches are typically implemented by weighting training data points accordingly to their importance to the analysis. By changing the weight of individual data points, it is possible to shift the weight from the larger classes to the smaller ones, balancing the data set. To illustrate the use of the cost-sensitive approach to map specific classes of interest, a series of experiments with weighted support vector machines classifier and Landsat Thematic Mapper data were conducted to discriminate two types of mangrove forest (high-mangrove and low-mangrove) in Saloum estuary, Senegal, a United Nations Educational, Scientific and Cultural Organisation World Heritage site. Results suggest an increase in overall classification accuracy with the use of cost-sensitive method (97.3%) over the standard multi-class (94.3%) and the focused approach (91.0%). In particular, cost-sensitive method yielded higher sensitivity and specificity values on the discrimination of the classes of interest when compared with the standard multi-class and focused approaches.

Citation

Silva, J., Bacao, F., Dieng, M., Foody, G. M., & Caetano, M. (2017). Improving specific class mapping from remotely sensed data by cost-sensitive learning. International Journal of Remote Sensing, 38(11), 3294-3316. https://doi.org/10.1080/01431161.2017.1292073

• Journal Article Type: Article
• Acceptance Date: Jan 30, 2017
• Online Publication Date: Mar 21, 2017
• Publication Date: Jun 3, 2017
• Deposit Date: Mar 23, 2017
• Publicly Available Date: Mar 23, 2017
• Journal: International Journal of Remote Sensing
• Print ISSN: 0143-1161
• Electronic ISSN: 1366-5901
• Publisher: Taylor and Francis
• Peer Reviewed: Peer Reviewed
• Volume: 38
• Issue: 11
• Pages: 3294-3316
• DOI: https://doi.org/10.1080/01431161.2017.1292073
• Keywords: Support vector machines; land cover mapping; specific class mapping; remote sensing; Landsat; cost-sensitive learning
• Public URL: https://nottingham-repository.worktribe.com/output/851478
• Publisher URL: http://www.tandfonline.com/doi/full/10.1080/01431161.2017.1292073
• Additional Information: This is an Accepted Manuscript of an article published by Taylor & Francis in International Journal of Remote Sensing on 21 March 2017, available online: http://www.tandfonline.com/10.1080/01431161.2017.1292073.