Structure Tensor Representation for Robust Oriented Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929593295831040 |
|---|---|
| author | Bou, Xavier Facciolo, Gabriele von Gioi, Rafael Grompone Morel, Jean-Michel Ehret, Thibaud |
| author_facet | Bou, Xavier Facciolo, Gabriele von Gioi, Rafael Grompone Morel, Jean-Michel Ehret, Thibaud |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Structure Tensor Representation for Robust Oriented Object Detection Bou, Xavier Facciolo, Gabriele von Gioi, Rafael Grompone Morel, Jean-Michel Ehret, Thibaud Computer Vision and Pattern Recognition 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. |
| title | Structure Tensor Representation for Robust Oriented Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.10497 |