Deep learning has promoted the research of object detection in aerial scenes. However, most of the existing networks are limited by the large-scale variation of objects and the confusion of category features. To overcome these limitations, this paper proposes a novel aerial object detection framework called DFCformer. DFCformer is mainly composed of three parts: the backbone network DMViT, which introduces deformation patch embedding and multi-scale adaptive self-attention to capture sufficient features of the objects; FRGC guides feature interaction layer by layer to break the barriers between feature layers and improve the information discrimination and processing ability of multi-scale critical features; CAIM adopts an attention mechanism to fuse multi-scale features to perform hierarchical reasoning on the relationship between different levels and fully utilize the complementary information in multi-scale features. Extensive experiments have been conducted on the FAIR1M dataset, and DFCformer shows its advantages by achieving the highest scores with stronger scene adaptability.
A Novel Multi-Scale Transformer for Object Detection in Aerial Scenes
2022
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Bayesian object detection in dynamic scenes
IEEE | 2005
|Multi-object reconstruction from dynamic scenes: An object-centered approach
British Library Online Contents | 2013
|MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography
DOAJ | 2023
|Detection of Extended Object Images in Optical Scenes
British Library Online Contents | 1998
|