Structure Tensor Representation for Robust Oriented Object Detection
This work addresses a specific problem in computer vision for researchers and practitioners by providing a robust and modular solution for encoding orientation in object detection, though it is incremental as it builds on classical edge and corner detection methods.
The paper tackles the challenge of predicting orientation in oriented object detection, which suffers from angular periodicity issues, by proposing a structure tensor representation that outperforms previous methods across five datasets with high precision and minimal computational overhead.
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.