Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15086))

Included in the following conference series:

  • 174 Accesses

Abstract

This paper introduces the point-axis representation for oriented object detection, as depicted in aerial images in Fig. 1, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Xia, G.-S., et al.: A large-scale dataset for object detection in aerial images. In: CVPR, Dota (2018)

    Google Scholar 

  2. Ding, J., et al.: Object detection in aerial images: a large-scale benchmark and challenges. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7778–7796 (2021)

    Article  Google Scholar 

  3. Cheng, G., Wang, J., Li, K., Xie, X., Lang, C., Yao, Y., Han, J.: Anchor-free oriented proposal generator for object detection. IEEE Trans. Geosci. Remote Sens. 60, 1–11 (2022)

    Google Scholar 

  4. Zhou, Y., et al.: Mmrotate: a rotated object detection benchmark using pytorch. In: ACM MM (2022)

    Google Scholar 

  5. Gui, S., Song, S., Qin, R., Tang, Y.: Remote sensing object detection in the deep learning era–a review. Remote Sensing 16(2), 327 (2024)

    Article  Google Scholar 

  6. Girshick, R.: Fast r-cnn. In: ICCV (2015)

    Google Scholar 

  7. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: Unified, real-time object detection. In: CVPR, You only look once (2016)

    Google Scholar 

  8. Tian, Z., Shen, C., Chen, H., He, T.: Fully convolutional one-stage object detection. In ICCV, Fcos (2019)

    Google Scholar 

  9. Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: CVPR (2023)

    Google Scholar 

  10. Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proceedings of the IEEE (2023)

    Google Scholar 

  11. Song, X., He, Y, Dong, S., Gong, Y.: Non-exemplar domain incremental object detection via learning domain bias. In: AAAI (2024)

    Google Scholar 

  12. Ding, J., Xue, N., Long, Y., Xia, G.-S., Lu, O.: Learning roi transformer for oriented object detection in aerial images. In: CVPR (2019)

    Google Scholar 

  13. Yang, X., Yan, J.: Arbitrary-oriented object detection with circular smooth label. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 677–694. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_40

    Chapter  Google Scholar 

  14. Yang, X., et al.: The kfiou loss for rotated object detection. In: ICLR (2023)

    Google Scholar 

  15. Yu, Y., Da, F.: Phase-shifting coder: Predicting accurate orientation in oriented object detection. In: CVPR (2023)

    Google Scholar 

  16. Qian, W., Yang, X., Peng, S., Yan, J., Guo, Y.: Learning modulated loss for rotated object detection. In: AAAI (2021)

    Google Scholar 

  17. Yongchao, X., et al.: Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1452–1459 (2020)

    Google Scholar 

  18. Ming, Q., Miao, L., Zhou, Z., Yang, X., Dong, Y.: Optimization for arbitrary-oriented object detection via representation invariance loss. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)

    Article  Google Scholar 

  19. Yi, J., Wu, P., Liu, B., Huang, Q., Qu, H., Metaxas, D.: Oriented object detection in aerial images with box boundary-aware vectors. In: WACV (2021)

    Google Scholar 

  20. Wei, H., Zhang, Y., Chang, Z., Li, H., Wang, H., Sun, X.: Oriented objects as pairs of middle lines. ISPRS J. Photogramm. Remote. Sens. 169, 268–279 (2020)

    Article  Google Scholar 

  21. Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q.: Rethinking rotated object detection with gaussian wasserstein distance loss. In: ICML (2021)

    Google Scholar 

  22. Yang, X., et al.: Learning high-precision bounding box for rotated object detection via kullback-leibler divergence. NeurIPS (2021)

    Google Scholar 

  23. Yu, Y., Da, F.: On boundary discontinuity in angle regression based arbitrary oriented object detection. IEEE Trans. Pattern Anal. Mach. Intell. (2024)

    Google Scholar 

  24. Xiao, Z., Yang, G., Yang, X., Mu, T., Yan, J., Hu, S.: Theoretically achieving continuous representation of oriented bounding boxes. In: CVPR (2024)

    Google Scholar 

  25. Chen, Y., Zhang, Z., Cao, Y., Wang, L., Lin, S., Hu, H.: Reppoints v2: Verification meets regression for object detection. NeurIPS (2020)

    Google Scholar 

  26. Li, W., Chen, Y., Hu, K., Zhu, J.: Oriented reppoints for aerial object detection. In: CVPR (2022)

    Google Scholar 

  27. Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented r-cnn for object detection. In: ICCV (2021)

    Google Scholar 

  28. Han, J., Ding, J., Xue, N., Xia, G.-S.: A rotation-equivariant detector for aerial object detection. In: CVPR, Redet (2021)

    Google Scholar 

  29. Pu, Y., et al.: Adaptive rotated convolution for rotated object detection. In: ICCV (2023)

    Google Scholar 

  30. Li, Y., Hou, Q., Zheng, Z., Cheng, M.-M., Yang, J., Li, X.: Large selective kernel network for remote sensing object detection. In: ICCV (2023)

    Google Scholar 

  31. Yang, X., Hou, L., Zhou, Y., Wang, W., Yan, J.: Dense label encoding for boundary discontinuity free rotation detection. In: CVPR (2021)

    Google Scholar 

  32. Dongchen, L., Li, D., Li, Y., Wang, S.: Orientation-sensitive keypoint localization for rotated object detection. In CVPR, Oskdet (2022)

    Google Scholar 

  33. Yu, H., Tian, Y., Ye, Q., Liu, Y.: Spatial transform decoupling for oriented object detection. In: AAAI (2024)

    Google Scholar 

  34. Chen, Z., et al.: The devil is in the crack orientation: a new perspective for crack detection. In: ICCV (2023)

    Google Scholar 

  35. Vaswani, A., et al.: Attention is all you need. NeurIPS (2017)

    Google Scholar 

  36. Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

    Google Scholar 

  37. Wei, X., et al.: Scene-adaptive attention network for crowd counting. arXiv preprint arXiv:2112.15509 (2021)

  38. Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-end multi-person pose estimation with transformers. In: CVPR (2022)

    Google Scholar 

  39. Wei, X., Bai, Y., Zheng, Y., Shi, D., Gong, Y.: Autoregressive visual tracking. In: CVPR (2023)

    Google Scholar 

  40. Bai, Y., Zhao, Z., Gong, Y., Wei, X.: Artrackv2: Prompting autoregressive tracker where to look and how to describe. In: CVPR (2024)

    Google Scholar 

  41. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  42. Zhu, X., Weijie, S., Lewei, L., Li, B., Wang, X., Dai, J.: Deformable transformers for end-to-end object detection. In: ICLR, Deformable detr (2021)

    Google Scholar 

  43. Liu, S., et al.: Dynamic anchor boxes are better queries for detr. In: ICLR, Dab-detr (2022)

    Google Scholar 

  44. Zhang, G., Luo, Z., Yu, Y., Cui, K., Lu, S.: Accelerating detr convergence via semantic-aligned matching. In: CVPR (2022)

    Google Scholar 

  45. Zhang, G., Luo, Z., Tian, Z., Zhang, J., Zhang, X., Lu, S.: Towards efficient use of multi-scale features in transformer-based object detectors. In: CVPR (2023)

    Google Scholar 

  46. Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In VPR (2018)

    Google Scholar 

  47. Dai, X., et al.: Unifying object detection heads with attentions. In: CVPR, Dynamic head (2021)

    Google Scholar 

  48. Zhang, H., et al.: Detr with improved denoising anchor boxes for end-to-end object detection. In: ICLR (2023)

    Google Scholar 

  49. Zong, Z., Song, G., Liu, Y.: Detrs with collaborative hybrid assignments training. In: ICCV (2023)

    Google Scholar 

  50. Liu, S., et al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv (2023)

    Google Scholar 

  51. Li, F., et al.: Mask dino: Towards a unified transformer-based framework for object detection and segmentation. In: CVPR (2023)

    Google Scholar 

  52. Li, F., et al.: Visual in-context prompting. arXiv, (2023)

    Google Scholar 

  53. Hu, Z., et al.: Emo2-detr: efficient-matching oriented object detection with transformers. IEEE Trans. Geosci. Remote Sensing (2023)

    Google Scholar 

  54. Dai, L., Liu, H., Tang, H., Zhiwei, W., Song, P.: Ao2-detr: arbitrary-oriented object detection transformer. IEEE Trans. Circuits Syst. Video Technol. 33(5), 2342–2356 (2022)

    Article  Google Scholar 

  55. Zeng, Y., Chen, Y., Yang, X., Li, Q., Yan, J.: Ars-detr: aspect ratio-sensitive detection transformer for aerial oriented object detection. IEEE Trans. Geosci. Remote Sens. 62, 1–15 (2024)

    Article  Google Scholar 

  56. Li, K., Wan, G., Cheng, G., Meng, L., Han, J.: Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J. Photogramm. Remote. Sens. 159, 296–307 (2020)

    Article  Google Scholar 

  57. Liu, Z., Yuan, L., Weng, L.,Yang, Y.: A high resolution optical satellite image dataset for ship recognition and some new baselines. In: International Conference on Pattern Recognition Applications and Methods, vol. 2, pp. 324–331. SciTePress (2017)

    Google Scholar 

  58. Lin, T.-Y., et al.: Common objects in context. In ECCV, Microsoft coco (2014)

    Google Scholar 

  59. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  60. Liu, Z., et al.: Hierarchical vision transformer using shifted windows. In ICCV, Swin transformer (2021)

    Google Scholar 

  61. Everingham, M., Winn, J.: The pascal visual object classes challenge 2007 (voc2007) development kit. Int. J. Comput. Vis. 88(2), 303–338 (2010)

    Article  Google Scholar 

  62. Everingham, M., Winn, J.:The pascal visual object classes challenge 2012 (voc2012) development kit. Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep 2007(1-45):5 (2012)

    Google Scholar 

  63. Yang, X., Yan, J., Feng, Z., He, T.: R3det: refined single-stage detector with feature refinement for rotating object. In: AAAI (2021)

    Google Scholar 

  64. Hou, L., Lu, K., Xue, J., Li, Y.: Shape-adaptive selection and measurement for oriented object detection. In: AAAI (2022)

    Google Scholar 

  65. Huang, Z., Li, W., Xia, X.-G., Tao, R.: A general gaussian heatmap label assignment for arbitrary-oriented object detection. IEEE Trans. Image Process. 31, 1895–1910 (2022)

    Article  Google Scholar 

  66. Nie, G., Huang, H.: Multi-oriented object detection in aerial images with double horizontal rectangles. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4932–4944 (2023)

    Google Scholar 

  67. Xu, C., et al.: Dynamic coarse-to-fine learning for oriented tiny object detection. In: CVPR (2023)

    Google Scholar 

  68. Yang, X., et al.: Scrdet: Towards more robust detection for small, cluttered and rotated objects. In: ICCV (2019)

    Google Scholar 

  69. Wang, D., et al.: Advancing plain vision transformer toward remote sensing foundation model. IEEE Trans. Geosci. Remote Sens. 61, 1–15 (2022)

    Google Scholar 

  70. Cai, X., Lai, Q., Wang, Y., Wang, W., Sun, Z., Yao, Y.: Poly kernel inception network for remote sensing detection. In: CVPR (2024)

    Google Scholar 

  71. Cheng, G., et al.: Anchor-free oriented proposal generator for object detection. IEEE Trans. Geosci. Remote Sens. 60, 1–11 (2022)

    Google Scholar 

  72. Lyu, C., et al.: An empirical study of designing real-time object detectors. arXiv, Rtmdet (2022)

    Google Scholar 

  73. Ming, Q., Miao, L., Zhou, Z., Song, J., Dong, Y., Yang, X.: Task interleaving and orientation estimation for high-precision oriented object detection in aerial images. ISPRS J. Photogramm. Remote. Sens. 196, 241–255 (2023)

    Article  Google Scholar 

  74. Yang, X., et al.: Detecting rotated objects as gaussian distributions and its 3-d generalization. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4335–4354 (2022)

    Google Scholar 

  75. Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Accelerate detr training by introducing query denoising. In: CVPR, Dn-detr (2022)

    Google Scholar 

  76. Jia, D., et al.: Detrs with hybrid matching. In: CVPR, Lei Sun (2023)

    Google Scholar 

  77. Ren, T., et al.: detrex: Benchmarking detection transformers. arXiv (2023)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China under Grant No. U21B2048 and No. 62302382, Shenzhen Key Technical Projects under Grant CJGJZD2022051714160501, the Fundamental Research Funds for the Central Universities No. xxj032023020, and sponsored by the CAAI-MindSpore Open Fund, developed on OpenI Community.

Author information

Authors and Affiliations

  1. National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China

    Zeyang Zhao, Yuhang He & Yihong Gong

  2. School of Software Engineering, Xi’an Jiaotong University, Xi’an, China

    Qilong Xue, Yifan Bai & Xing Wei

Authors
  1. Zeyang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qilong Xue
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuhang He
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yifan Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xing Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yihong Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xing Wei .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhao, Z., Xue, Q., He, Y., Bai, Y., Wei, X., Gong, Y. (2025). Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15086. Springer, Cham. https://doi.org/10.1007/978-3-031-73390-1_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-73390-1_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-73389-5

  • Online ISBN: 978-3-031-73390-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation