G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection
Remote Sensing · 28.01.2023 · 15 (3) · 757
DOI: 10.3390/rs15030757 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.01.2023. Verfasst von Liping Hou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 100-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, NSFC Key Projects of International (Regional) Cooperation and Exchanges, Key Project of Education Commission of Beijing Municipal.
Abstract (Originalsprache)
Typical representations for arbitrary-oriented object detection tasks include the oriented bounding box (OBB), the quadrilateral bounding box (QBB), and the point set (PointSet). Each representation encounters problems that correspond to its characteristics, such as boundary discontinuity, square-like problems, representation ambiguity, and isolated points, which lead to inaccurate detection. Although many effective strategies have been proposed for various representations, there is still no unified solution. Current detection methods based on Gaussian modeling have demonstrated the possibility of resolving this dilemma; however, they remain limited to OBB. To go further, in this paper, we propose a unified Gaussian representation called G-Rep to construct Gaussian distributions for OBB, QBB, and PointSet, which achieves a unified solution to various representations and problems. Specifically, PointSet- or QBB-based object representations are converted into Gaussian distributions and their parameters are optimized using the maximum likelihood estimation algorithm. Then, three optional Gaussian metrics are explored to optimize the regression loss of the detector because of their excellent parameter optimization mechanisms. Furthermore, we also use Gaussian metrics for sampling to align label assignment and regression loss. Experimental results obtained on several publicly available datasets, such as DOTA, HRSC2016, UCAS-AOD, and ICDAR2015, show the excellent performance of the proposed method for arbitrary-oriented object detection.
Förderung
- National Natural Science Foundation of China
- NSFC Key Projects of International (Regional) Cooperation and Exchanges
- Key Project of Education Commission of Beijing Municipal
Zitieren
APA
Hou, L., Lu, K., Yang, X., Li, Y., & Xue, J. (2023). G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection. Remote Sensing, 15(3), 757. https://doi.org/10.3390/rs15030757
Vancouver
Hou L, Lu K, Yang X, Li Y, Xue J. G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection. Remote Sensing. 2023;15(3):757. doi:10.3390/rs15030757
BibTeX
@article{Hou2023,
author = {Hou, Liping and Lu, Ke and Yang, Xue and Li, Yuqiu and Xue, Jian},
title = {G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {3},
pages = {757},
doi = {10.3390/rs15030757}
}
EUVIMED