GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection

TL;DR

GauCho introduces a Gaussian-based regression head for oriented object detection that mitigates boundary discontinuity issues and improves detection accuracy, especially for elongated objects in remote sensing images.

Contribution

The paper proposes GauCho, a novel regression head using Cholesky decomposition for Gaussian distributions, addressing boundary discontinuity and encoding ambiguity in oriented object detection.

Findings

Achieves comparable or better results than state-of-the-art detectors on DOTA dataset.

Effectively mitigates angular boundary discontinuity in oriented object detection.

Utilizes Gaussian distributions and Oriented Ellipses for improved object representation.

Abstract

Oriented Object Detection (OOD) has received increased attention in the past years, being a suitable solution for detecting elongated objects in remote sensing analysis. In particular, using regression loss functions based on Gaussian distributions has become attractive since they yield simple and differentiable terms. However, existing solutions are still based on regression heads that produce Oriented Bounding Boxes (OBBs), and the known problem of angular boundary discontinuity persists. In this work, we propose a regression head for OOD that directly produces Gaussian distributions based on the Cholesky matrix decomposition. The proposed head, named GauCho, theoretically mitigates the boundary discontinuity problem and is fully compatible with recent Gaussian-based regression loss functions. Furthermore, we advocate using Oriented Ellipses (OEs) to represent oriented objects, which relates to GauCho through a bijective function and alleviates the encoding ambiguity problem for circular objects. Our experimental results show that GauCho can be a viable alternative to the traditional OBB head, achieving results comparable to or better than state-of-the-art detectors for the challenging dataset DOTA