Satellite Object Detection Using Machine Learning: A Review

Satellite object detection using machine learning is a rapidly evolving field with applications in environmental monitoring, disaster management, urban planning, and national security. Satellites capture vast amounts of imagery daily, providing an enormous dataset that requires efficient and automated techniques for analysis. Machine learning, particularly deep learning, offers promising solutions for identifying and classifying objects such as buildings, vehicles, vegetation, and ships within satellite images. Machine learning models for satellite object detection typically involve several stages: preprocessing, feature extraction, model training, and validation. Preprocessing includes correcting image distortions, resizing, and enhancing image quality. This paper presents a review of machine learning based models for satellite object detection so as to render insights into developing future techniques which can yield high accuracy.