Object detection in optical remote sensing images, being a fundamental butchallenging problem in the field of aerial and satellite image analysis, playsan important role for a wide range of applications and is receiving significantattention in recent years. While enormous methods exist, a deep review of theliterature concerning generic object detection is still lacking. This paperaims to provide a review of the recent progress in this field. Different fromseveral previously published surveys that focus on a specific object class suchas building and road, we concentrate on more generic object categoriesincluding, but are not limited to, road, building, tree, vehicle, ship,airport, urban-area. Covering about 270 publications we survey 1) templatematching-based object detection methods, 2) knowledge-based object detectionmethods, 3) object-based image analysis (OBIA)-based object detection methods,4) machine learning-based object detection methods, and 5) five publiclyavailable datasets and three standard evaluation metrics. We also discuss thechallenges of current studies and propose two promising research directions,namely deep learning-based feature representation and weakly supervisedlearning-based geospatial object detection. It is our hope that this surveywill be beneficial for the researchers to have better understanding of thisresearch field.
展开▼
