AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Article Link
Collect
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Full Length Article | Open Access

Learning power Gaussian modeling loss for dense rotated object detection in remote sensing images

Yang LIa,b, Haining WANGa, Yuqiang FANGa, Shengjin WANGc, Zhi LIa, Bitao JIANGb( )
Department of Space Information, Space Engineering University, Beijing 101416, China
Beijing Institute of Remote Sensing Information, Beijing 100192, China
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

Peer review under responsibility of Editorial Committee of CJA.

Show Author Information

Abstract

Object detection in Remote Sensing (RS) has achieved tremendous advances in recent years, but it remains challenging for rotated object detection due to cluttered backgrounds, dense object arrangements and the wide range of size variations among objects. To tackle this problem, Dense Context Feature Pyramid Network (DCFPN) and a power α-Gaussian loss are designed for rotated object detection in this paper. The proposed DCFPN can extract multi-scale information densely and accurately by leveraging a dense multi-path dilation layer to cover all sizes of objects in remote sensing scenarios. For more accurate detection while avoiding bottlenecks such as boundary discontinuity in rotated bounding box regression, α-Gaussian loss, a unified power generalization of existing Gaussian modeling losses is proposed. Furthermore, the properties of α-Gaussian loss are analyzed comprehensively for a wider range of applications. Experimental results on four datasets (UCAS-AOD, HRSC2016, DIOR-R, and DOTA) show the effectiveness of the proposed method using different detectors, and are superior to the existing methods in both feature extraction and bounding box regression.

References

【1】
【1】
 
 
Chinese Journal of Aeronautics
Pages 353-365

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
LI Y, WANG H, FANG Y, et al. Learning power Gaussian modeling loss for dense rotated object detection in remote sensing images. Chinese Journal of Aeronautics, 2023, 36(10): 353-365. https://doi.org/10.1016/j.cja.2023.04.022

1036

Views

12

Crossref

10

Web of Science

15

Scopus

3

CSCD

Received: 16 September 2022
Revised: 20 November 2022
Accepted: 01 February 2023
Published: 25 April 2023
© 2023 Chinese Society of Aeronautics and Astronautics.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).