Structure Tensor Representation for Robust Oriented Object Detection

TL;DR

This paper introduces a structure tensor-based orientation representation for oriented object detection, effectively addressing boundary discontinuity and symmetry issues, leading to improved accuracy and robustness across multiple datasets.

Contribution

It proposes a novel structure tensor approach for orientation encoding, combining classical edge detection insights with modern object detection, and demonstrates superior performance over existing methods.

Findings

Outperforms previous methods in multiple datasets

Robust to angular periodicity and symmetry ambiguities

Minimal computational overhead

Abstract

Oriented object detection predicts orientation in addition to object location and bounding box. Precisely predicting orientation remains challenging due to angular periodicity, which introduces boundary discontinuity issues and symmetry ambiguities. Inspired by classical works on edge and corner detection, this paper proposes to represent orientation in oriented bounding boxes as a structure tensor. This representation combines the strengths of Gaussian-based methods and angle-coder solutions, providing a simple yet efficient approach that is robust to angular periodicity issues without additional hyperparameters. Extensive evaluations across five datasets demonstrate that the proposed structure tensor representation outperforms previous methods in both fully-supervised and weakly supervised tasks, achieving high precision in angular prediction with minimal computational overhead. Thus, this work establishes structure tensors as a robust and modular alternative for encoding orientation in oriented object detection. We make our code publicly available, allowing for seamless integration into existing object detectors.