SAFDet: a semi-anchor-free detector for effective detection of oriented objects in aerial images

Zhenyu Fang, Jinchang Ren, He Sun, Stephen Marshall, Junwei Han, Huimin Zhao

Research output: Contribution to journalArticle

1 Downloads (Pure)

Abstract

An oriented bounding box (OBB) is preferable over a horizontal bounding box (HBB) in accurate object detection. Most of existing works utilize a two-stage detector for locating the HBB and OBB, respectively, which have suffered from the misaligned horizontal proposals and the interference from complex backgrounds. To tackle these issues, region of interest transformer and attention models were proposed, yet they are extremely computationally intensive. To this end, we propose a semi-anchor-free detector (SAFDet) for object detection in aerial images, where a rotation-anchor-free-branch (RAFB) is used to enhance the foreground features via precisely regressing the OBB. Meanwhile, a center-prediction-module (CPM) is introduced for enhancing object localization and suppressing the background noise. Both RAFB and CPM are deployed during training, avoiding increased computational cost of inference. By evaluating on DOTA and HRSC2016 datasets, the efficacy of our approach has been fully validated for a good balance between the accuracy and computational cost.
Original languageEnglish
Article number3225
Number of pages16
JournalRemote Sensing
Volume12
Issue number19
DOIs
Publication statusPublished - 3 Oct 2020

Keywords

  • rotate region
  • convolutional neural network
  • anchor free
  • aerial object detection

Fingerprint Dive into the research topics of 'SAFDet: a semi-anchor-free detector for effective detection of oriented objects in aerial images'. Together they form a unique fingerprint.

Cite this