Edge Detection for Satellite Images without Deep Networks

Satellite imagery is widely used in many application sectors, including agriculture, navigation, and urban planning. Frequently, satellite imagery involves both large numbers of images as well as high pixel counts, making satellite datasets computationally expensive to analyze. Recent approaches to satellite image analysis have largely emphasized deep learning methods. Though extremely powerful, deep learning has some drawbacks, including the requirement of specialized computing hardware and a high reliance on training data. When dealing with large satellite datasets, the cost of both computational resources and training data annotation may be prohibitive. In this paper, we demonstrate that a carefully designed image pre-processing pipeline allows traditional computer vision techniques to achieve semantic edge detection in satellite imagery that is competitive with deep learning methods at a fraction of the resource costs. We focus on the task of semantic edge detection due to its general-purpose usage in remote sensing, including the detection of natural and man-made borders, coast lines, roads, and buildings.