Paper Info
Title
SAFDet: A Semi-Anchor-Free Detector for Effective Detection of Oriented Objects in Aerial Images.
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.
Year
DOI
Venue
2020
10.3390/rs12193225
REMOTE SENSING
Keywords
DocType
Volume
rotate region,convolutional neural network,anchor free,aerial object detection
Journal
12
Issue
Citations 
PageRank 
19
1
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Zhenyu Fang131.77
Jinchang Ren2114488.54
He Sun37914.18
Stephen Marshall422725.35
Junwei Han53501194.57
Huimin Zhao620623.43