Next Article in Journal
Diagnostics of Es Layer Scintillation Observations Using FS3/COSMIC Data: Dependence on Sampling Spatial Scale
Next Article in Special Issue
Fast and High-Quality 3-D Terahertz Super-Resolution Imaging Using Lightweight SR-CNN
Previous Article in Journal
Typhoon Warm-Core Structures Derived from FY-3D MWTS-2 Observations
Previous Article in Special Issue
Learning Rotated Inscribed Ellipse for Oriented Object Detection in Remote Sensing Images
Article

Predicting Arbitrary-Oriented Objects as Points in Remote Sensing Images

School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, China
*
Author to whom correspondence should be addressed.
Academic Editors: Jukka Heikkonen, Fahimeh Farahnakian and Pouya Jafarzadeh
Remote Sens. 2021, 13(18), 3731; https://doi.org/10.3390/rs13183731
Received: 10 August 2021 / Revised: 7 September 2021 / Accepted: 15 September 2021 / Published: 17 September 2021
(This article belongs to the Special Issue Deep Learning and Computer Vision in Remote Sensing)
To detect rotated objects in remote sensing images, researchers have proposed a series of arbitrary-oriented object detection methods, which place multiple anchors with different angles, scales, and aspect ratios on the images. However, a major difference between remote sensing images and natural images is the small probability of overlap between objects in the same category, so the anchor-based design can introduce much redundancy during the detection process. In this paper, we convert the detection problem to a center point prediction problem, where the pre-defined anchors can be discarded. By directly predicting the center point, orientation, and corresponding height and width of the object, our methods can simplify the design of the model and reduce the computations related to anchors. In order to further fuse the multi-level features and get accurate object centers, a deformable feature pyramid network is proposed, to detect objects under complex backgrounds and various orientations of rotated objects. Experiments and analysis on two remote sensing datasets, DOTA and HRSC2016, demonstrate the effectiveness of our approach. Our best model, equipped with Deformable-FPN, achieved 74.75% mAP on DOTA and 96.59% on HRSC2016 with a single-stage model, single-scale training, and testing. By detecting arbitrarily oriented objects from their centers, the proposed model performs competitively against oriented anchor-based methods. View Full-Text
Keywords: object detection; remote sensing image; anchor free; oriented bounding boxes; deformable convolution object detection; remote sensing image; anchor free; oriented bounding boxes; deformable convolution
Show Figures

Graphical abstract

MDPI and ACS Style

Wang, J.; Yang, L.; Li, F. Predicting Arbitrary-Oriented Objects as Points in Remote Sensing Images. Remote Sens. 2021, 13, 3731. https://doi.org/10.3390/rs13183731

AMA Style

Wang J, Yang L, Li F. Predicting Arbitrary-Oriented Objects as Points in Remote Sensing Images. Remote Sensing. 2021; 13(18):3731. https://doi.org/10.3390/rs13183731

Chicago/Turabian Style

Wang, Jian, Le Yang, and Fan Li. 2021. "Predicting Arbitrary-Oriented Objects as Points in Remote Sensing Images" Remote Sensing 13, no. 18: 3731. https://doi.org/10.3390/rs13183731

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop