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

Fang, Zhenyu and Ren, Jinchang and Sun, He and Marshall, Stephen and Han, Junwei and Zhao, Huimin (2020) SAFDet : a semi-anchor-free detector for effective detection of oriented objects in aerial images. Remote Sensing, 12 (19). 3225. ISSN 2072-4292 (https://doi.org/10.3390/rs12193225)

[thumbnail of Fang-etal-RS-2020-a-semi-anchor-free-detector-for-effective-detection-of-oriented-objects]
Preview
 Text. Filename: Fang_etal_RS_2020_a_semi_anchor_free_detector_for_effective_detection_of_oriented_objects.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (7MB)| Preview

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.

CORE (COnnecting REpositories)