Multi-label Land Cover Indices Classification of Satellite Images Using Deep Learning

Accurate classification of land cover indices is important for diverse disciplines (e.g., ecology, geography, and climatology) because it serves as a basis for various real world applications. For detection and classification of land cover, remote sensing has long been used as an excellent source of data for finding different types of data attribute present in the land cover. A variety of feature extraction and classification methods in machine learning have been used to classify land cover using satellite images. In recent years, deep learning have recently emerged as a dominant paradigm for machine learning in a variety of domains. The objective of this paper presents the multi-labeled land cover indices classification using Google Earth Satellite images with deep convolutional neural network (DCNN). Since the lack of massive labeled land cover dataset, the own created labeled dataset for Ayeyarwaddy Delta is applied and tested with AlexNet. Then the results of land cover classification are compared with Multiclass-SVM using confusion matrices. According to the tested results, 76.6% of building index, 81.5% road index, 91.8% of vegetation index and 93.2% of water index can be correctly classified by using DCNN. The confusion matrix for Multiclass-SVM, 78.9% of building index, 72.7% road index, 94.2% of vegetation index and 98.1% of water index can be correctly classified.