Abstract
In this study, a method based on supervised machine learning is proposed to identify village buildings from open high-resolution remote sensing images. We select Google Earth (GE) RGB images to perform the classification in order to examine its suitability for village mapping, and investigate the feasibility of using machine learning methods to provide automatic classification in such fields. By analyzing the characteristics of GE images, we design different features on the basis of two kinds of supervised machine learning methods for classification: adaptive boosting (AdaBoost) and convolutional neural networks (CNN). To recognize village buildings via their color and texture information, the RGB color features and a large number of Haar-like features in a local window are utilized in the AdaBoost method; with multilayer trained networks based on gradient descent algorithms and back propagation, CNN perform the identification by mining deeper information from buildings and their neighborhood. Experimental results from the testing area at Savannakhet province in Laos show that our proposed AdaBoost method achieves an overall accuracy of 96.22% and the CNN method is also competitive with an overall accuracy of 96.30%.
Highlights
With the rapid development of urbanization processes, maps used to illustrate buildings and their distribution are significant and are required in a wide range of fields
True Positives: actual buildings that were correctly classified as buildings, False Positives: non-buildings were incorrectly labeled as buildings, False Negatives: buildings that were incorrectly marked as non-buildings, True
As we mentioned in the definition of the confusion matrix, in the method based on convolutional neural networks (CNN), actual buildings thatmentioned were correctly classified of asthe buildings is matrix, 12,540, in non-buildings incorrectly labeled
Summary
With the rapid development of urbanization processes, maps used to illustrate buildings and their distribution are significant and are required in a wide range of fields. In the field of remote sensing detection, using the convolutional neural networks (CNN) method [28], Chen et al [29] address vehicle detection, Li et al [30] focus on building pattern classifiers, and Yue et al [31] use both spectral and spatial features for hyperspectral image classification. To investigate the accuracy and efficiency of identification considering the characteristics of GE images, we explore the feasibility of supervised machine learning approaches for building identification using AdaBoost and CNN, respectively. Both methods adopt different feature extraction schemes, enabling full exploitation of the texture, spectral, geometry, and other characteristics in the images.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
