Rotated Object Detection with Circular Gaussian Distribution

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.

Automated summary

In this study, we propose a circular Gaussian distribution (CGD)-based method for predicting the rotation angle of objects. We convert the labeled angle into a discrete circular Gaussian distribution and let the model predict the distribution parameters. Additionally, we design a rotated object detector based on CenterNet to improve overall efficiency. Experimental results show that our method achieves superior performances, outperforming state-of-the-art competitors on various public datasets.