Abstract
Small object detection in large-scale remote sensing images is crucial for military and civil applications, but it remains challenging. Since small objects occupy few pixels, their features are easily interfered with by complex backgrounds and large objects. In addition, they are susceptible to localization offsets, which prone to false or missed detections as there are few predicted bounding boxes matching the ground truth. To overcome these issues, this paper proposes a filter progressive small object detection (FPSOD) model that is based on the progressive mechanism. With the proposed attention-based soft threshold filtering module, FPSOD significantly filters out redundant information in high-level feature maps thus enhancing the semantic features of small objects. Furthermore, a progressive regression loss function is proposed to facilitate the precise localization, which mitigates predicted bounding boxes drift by limiting the fluctuated range of the gradients. The experimental results show that the proposed model substantially improves the precision and recall of small objects, effectively reduces missed detections and improves detection performance.
Funding Information
  • Digital Grid Open Fund of China Southern Power Grid Company Ltd.
  • National Key Research and Development Program of China (2021YFE0204200)
  • National Natural Science Foundation of China (62101378, 62171318)

This publication has 44 references indexed in Scilit: