Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Theoretically Achieving Continuous Representation of Oriented Bounding Boxes (2402.18975v2)

Published 29 Feb 2024 in cs.CV and cs.AI

Abstract: Considerable efforts have been devoted to Oriented Object Detection (OOD). However, one lasting issue regarding the discontinuity in Oriented Bounding Box (OBB) representation remains unresolved, which is an inherent bottleneck for extant OOD methods. This paper endeavors to completely solve this issue in a theoretically guaranteed manner and puts an end to the ad-hoc efforts in this direction. Prior studies typically can only address one of the two cases of discontinuity: rotation and aspect ratio, and often inadvertently introduce decoding discontinuity, e.g. Decoding Incompleteness (DI) and Decoding Ambiguity (DA) as discussed in literature. Specifically, we propose a novel representation method called Continuous OBB (COBB), which can be readily integrated into existing detectors e.g. Faster-RCNN as a plugin. It can theoretically ensure continuity in bounding box regression which to our best knowledge, has not been achieved in literature for rectangle-based object representation. For fairness and transparency of experiments, we have developed a modularized benchmark based on the open-source deep learning framework Jittor's detection toolbox JDet for OOD evaluation. On the popular DOTA dataset, by integrating Faster-RCNN as the same baseline model, our new method outperforms the peer method Gliding Vertex by 1.13% mAP50 (relative improvement 1.54%), and 2.46% mAP75 (relative improvement 5.91%), without any tricks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Piou loss: Towards accurate oriented object detection in complex environments. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16, pages 195–211. Springer, 2020.
  2. Learning roi transformer for oriented object detection in aerial images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2849–2858, 2019.
  3. Object detection in aerial images: A large-scale benchmark and challenges. IEEE transactions on pattern analysis and machine intelligence, 44(11):7778–7796, 2021.
  4. The pascal visual object classes (voc) challenge. International journal of computer vision, 88:303–338, 2010.
  5. Ross Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448, 2015.
  6. Align deep features for oriented object detection. IEEE Transactions on Geoscience and Remote Sensing, 60:1–11, 2021a.
  7. Redet: A rotation-equivariant detector for aerial object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2786–2795, 2021b.
  8. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  9. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
  10. Jittor: a novel deep learning framework with meta-operators and unified graph execution. Science China Information Sciences, 63:1–21, 2020.
  11. Rotation-sensitive regression for oriented scene text detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  12. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017a.
  13. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017b.
  14. Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pages 21–37. Springer, 2016.
  15. Rotated region based cnn for ship detection. In 2017 IEEE International Conference on Image Processing (ICIP), pages 900–904. IEEE, 2017a.
  16. A high resolution optical satellite image dataset for ship recognition and some new baselines. In ICPRAM, pages 324–331, 2017b.
  17. Arbitrary-oriented scene text detection via rotation proposals. IEEE Transactions on Multimedia, 20(11):3111–3122, 2018a.
  18. Arbitrary-oriented scene text detection via rotation proposals. IEEE transactions on multimedia, 20(11):3111–3122, 2018b.
  19. Optimization for arbitrary-oriented object detection via representation invariance loss. IEEE Geoscience and Remote Sensing Letters, 19:1–5, 2021.
  20. Multi-oriented object detection in aerial images with double horizontal rectangles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4932–4944, 2022.
  21. Learning modulated loss for rotated object detection. In Proceedings of the AAAI conference on artificial intelligence, pages 2458–2466, 2021.
  22. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788, 2016.
  23. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 2015.
  24. Fair1m: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 184:116–130, 2022.
  25. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9627–9636, 2019.
  26. Multigrained angle representation for remote-sensing object detection. IEEE Transactions on Geoscience and Remote Sensing, 60:1–13, 2022a.
  27. Gaussian focal loss: Learning distribution polarized angle prediction for rotated object detection in aerial images. IEEE Transactions on Geoscience and Remote Sensing, 60:1–13, 2022b.
  28. Oriented objects as pairs of middle lines. ISPRS Journal of Photogrammetry and Remote Sensing, 169:268–279, 2020.
  29. Dota: A large-scale dataset for object detection in aerial images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3974–3983, 2018.
  30. Oriented r-cnn for object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3520–3529, 2021.
  31. Rethinking boundary discontinuity problem for oriented object detection, 2023.
  32. Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE transactions on pattern analysis and machine intelligence, 43(4):1452–1459, 2020.
  33. Arbitrary-oriented object detection with circular smooth label. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16, pages 677–694. Springer, 2020.
  34. Scrdet: Towards more robust detection for small, cluttered and rotated objects. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8232–8241, 2019.
  35. Dense label encoding for boundary discontinuity free rotation detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15819–15829, 2021a.
  36. Rethinking rotated object detection with gaussian wasserstein distance loss. In International Conference on Machine Learning, pages 11830–11841. PMLR, 2021b.
  37. Learning high-precision bounding box for rotated object detection via kullback-leibler divergence. Advances in Neural Information Processing Systems, 34:18381–18394, 2021c.
  38. The kfiou loss for rotated object detection. arXiv preprint arXiv:2201.12558, 2022.
  39. H2rbox: Horizontal box annotation is all you need for oriented object detection. International Conference on Learning Representations, 2023.
  40. Oriented object detection in aerial images with box boundary-aware vectors. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2150–2159, 2021.
  41. Phase-shifting coder: Predicting accurate orientation in oriented object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13354–13363, 2023.
  42. Feature-aligned single-stage rotation object detection with continuous boundary. IEEE Transactions on Geoscience and Remote Sensing, 60:1–11, 2022.
  43. Ars-detr: Aspect ratio sensitive oriented object detection with transformer. arXiv preprint arXiv:2303.04989, 2023.
  44. Trigonometric-coded refined detector for high precision oriented object detection. IEEE Geoscience and Remote Sensing Letters, 2023.
  45. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 9759–9768, 2020.
  46. Polardet: A fast, more precise detector for rotated target in aerial images. International Journal of Remote Sensing, 42(15):5831–5861, 2021.
  47. Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 30(11):3212–3232, 2019.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now