Efficient Object Detection in Large-Scale Remote Sensing Images via Situation-Aware Model

With the continuous improvement of high-resolution remote-sensing image-acquisition technologies, image quality and resolution are constantly improved, which greatly promotes the development of object detection in large-scale remote sensing images. However, due to the memory constraints of graphics processing units, directly inputting large-scale remote-sensing images into detectors poses significant challenges. Downsampling these images to sizes suitable for detectors often leads to the loss of critical details. Current mainstream object detection methods for large-scale images typically divide large images into patches and detect the objects of interest in all patches. These methods allocate computational resources uniformly on each patch, regardless of the presence of objects or variations in their density and size. This not only disrupts the delicate balance between accuracy and speed but also results in inefficient utilization of computational resources. To address these challenges, we propose a situation-aware network (SANet) for object detection in large-scale remote sensing images. SANet introduces a situation-aware (SA) module designed to filter out invalid information in large-scale images, thereby reducing computational complexity. Moreover, it integrates a region-adaptive module, which dynamically adjusts the level of granularity for object regions and allocates them to appropriate detectors, thus minimizing resource wastage. Our method has been tested on challenging datasets such as DOTA-v1.0, DOTA-v1.5, DOTA-v2.0, and TT100 K, demonstrating consistent advantages in both speed and accuracy compared to existing object detection methodologies.