Rotated Object Detection with Circular Gaussian Distribution
Electronics · 29.07.2023 · 12 (15) · 3265
DOI: 10.3390/electronics12153265 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 29.07.2023. Verfasst von Hang Xu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Nature Science Foundation of China, Strategic Priority Research Program of Chinese Academy of Sciences.
Abstract (Originalsprache)
Rotated object detection is a challenging task due to the difficulties of locating the rotated objects and separating them effectively from the background. For rotated object prediction, researchers have explored numerous regression-based and classification-based approaches to predict a rotation angle. However, both paradigms are constrained by some flaws that make it difficult to accurately predict angles, such as multi-solution and boundary issues, which limits the performance upper bound of detectors. To address these issues, we propose a circular Gaussian distribution (CGD)-based method for angular prediction. We convert the labeled angle into a discrete circular Gaussian distribution spanning a single minimal positive period, and let the model predict the distribution parameters instead of directly regressing or classifying the angle. To improve the overall efficiency of the detection model, we also design a rotated object detector based on CenterNet. Experimental results on various public datasets demonstrated the effectiveness and superior performances of our method. In particular, our approach achieves better results than state-of-the-art competitors, with improvements of 1.92% and 1.04% in terms of AP points on the HRSC2016 and DOTA datasets, respectively.
Förderung
- National Key R&D Program of China
- National Nature Science Foundation of China
- Strategic Priority Research Program of Chinese Academy of Sciences
- Natural Science Foundation of Shandong Province
- Key R&D Plan of Shandong Province
- Central Leading Local Science and Technology Development Special Fund Project
- Science & Technology Specific Projects in Agricultural High-Tech Industrial Demonstration Area of the Yellow River Delta
Zitieren
APA
Xu, H., Liu, X., Ma, Y., Zhu, Z., Wang, S., Yan, C., & Dai, F. (2023). Rotated Object Detection with Circular Gaussian Distribution. Electronics, 12(15), 3265. https://doi.org/10.3390/electronics12153265
Vancouver
Xu H, Liu X, Ma Y, Zhu Z, Wang S, Yan C, et al. Rotated Object Detection with Circular Gaussian Distribution. Electronics. 2023;12(15):3265. doi:10.3390/electronics12153265
BibTeX
@article{Xu2023,
author = {Xu, Hang and Liu, Xinyuan and Ma, Yike and Zhu, Zunjie and Wang, Shuai and Yan, Chenggang and Dai, Feng},
title = {Rotated Object Detection with Circular Gaussian Distribution},
journal = {Electronics},
year = {2023},
volume = {12},
number = {15},
pages = {3265},
doi = {10.3390/electronics12153265}
}
EUVIMED