I. Introduction
In recent years, remote sensing technology has entered a new stage. With the increasing of high-quality remote sensing images, remote sensing data is no longer the bottleneck of re-search and application in remote sensing image analysis. How to accurately extract valuable information from the massive re-mote sensing data has become an urgent problem [1]. As a hot research direction in remote sensing image processing, object detection has important applications in military and civilian fields. In the military field, enemy objects could be detected in time, which improves one’s battlefield awareness and provides favorable information for the formulation of military strategies. In the civilian field, it can monitor traffic conditions, analyze road conditions, and relieve traffic pressure. Therefore, object detection technology has great significance and value in remote sensing image analysis.