Improving the Detection of Small Oriented Objects in Aerial Images
This work addresses the challenge of detecting small, oriented objects in aerial imagery for applications like surveillance or mapping, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting small oriented objects in aerial images by proposing an Attention-Points Network with Guided-Attention Loss and Box-Points Loss to enhance classification and regression tasks. Experimental results demonstrate effectiveness on datasets like DOTA-v1.5 and HRSC2016, with code made publicly available.
Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.