This article presents an approach to automating the creation of land-use/land-cover classification (LULC) maps from satellite images using deep neural networks that were developed to perform semantic segmentation of natural images. This work is important since the production of accurate and timely LULC maps is becoming essential to government and private companies that rely on them for large-scale monitoring of land resource changes. In this work, deep neural networks re trained to classify each pixel of a satellite image into one of a number of LULC classes. The presented deep neural networks are all pre-trained using the ImageNet Large-Scale Visual Recognition Competition (ILSVRC) datasets and then fine-tuned using approximately 19,000 Landsat 5/7 satellite images of resolution 224 × 224 taken of the Province of Manitoba in Canada. The result is an automated solution that can produce LULC maps images significantly faster than current semi-automated methods. The contributions of this article are the observation that deep neural networks developed for semantic segmentation can be used to automate the task of producing LULC maps; the use of these networks to produce LULC maps; and a comparison of several popular semantic segmentation architectures for solving the problem of automated LULC map production.
In this article, we present an approach to Land use and Land cover (LULC) mapping from multispectral satellite images using deep learning methods. The terms satellite image classification and map production, although used interchangeably have specific meanings in the field of remote sensing. Satellite image classification describes assignment of global labels to entire scenes, whereas LULC map production involves producing maps by assigning a class to each pixel. We show that by classifying each pixel in a satellite image into a number of LULC categories we are able to successfully produce LULC maps. This process of LULC mapping is achieved using deep neural networks pre-trained on the ImageNet Large-Scale Visual Recognition Competition (ILSVRC) datasets and fine-tuned on our target dataset, which consists of Landsat 5/7 multispectral satellite images taken of the Province of Manitoba in Canada. This approach resulted in 88% global accuracy. Performance was further improved by considering the stateof-the-art generative adversarial architecture and context module integrated with the original networks. The result is an automated deep learning framework that can produce highly accurate LULC maps images significantly faster than current semi-automated methods. The contribution of this article includes extensive experimentation of different FCN architectures with extensions on a unique dataset, high classification accuracy of 90.46%, and a thorough analysis and accuracy assessment of our results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.