Edge Detection for Satellite Images without Deep Networks
This addresses the challenge of high computational and annotation costs for satellite imagery analysis in sectors like agriculture and urban planning, but appears incremental as it builds on existing edge detection techniques.
The paper tackles the problem of computationally expensive satellite image analysis by proposing an edge detection method that avoids deep networks, aiming to reduce reliance on specialized hardware and annotated training data.
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.