A Rapid Object Detection Method for Satellite Image with Large Size

The existing approaches for object detection from remote sensing images usually have the assumptions that the location is already known or determined manually. Our paper proposes an automatic and rapid method to detect objects from satellite image with large size, which is the precondition for detailed object recognition. Since feature based method usually performs better and faster than pixel based method, Haar-training algorithm is adopted based on some Haar-like structural features with the help of Adaboost classifier. Object of baseball field is taken as the example, and the detected results are further decided with size constraint to improve the accuracy. To reduce the computational cost, three approaches are proposed including pyramid detection model, sub-blocks detection model and spread detection model. Differences of them are analyzed and the suitable model can be chosen for certain kind of satellite image. From the detected object, its details can be further recognized.