Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

Improving the Detection of Small Oriented Objects in Aerial Images (2401.06503v1)

Published 12 Jan 2024 in cs.CV and cs.AI

Abstract: Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2015.
  2. Cascade r-cnn: Delving into high quality object detection. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6154–6162, 2018.
  3. Dual-modality vehicle anomaly detection via bilateral trajectory tracing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 4016–4025, June 2021.
  4. Hybrid task cascade for instance segmentation. In IEEE Conference on Computer Vision and Pattern Recognition, 2019.
  5. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019.
  6. PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments. In Proceedings of the European Conference on Computer Vision, volume 12350 LNCS, pages 195–211, 2020.
  7. Learning roi transformer for oriented object detection in aerial images. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 2019-June, pages 2844–2853, 2019.
  8. Object detection in aerial images: A large-scale benchmark and challenges, 2021.
  9. Pascal visual object classes challenge 2007 (voc2007) complete dataset.
  10. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html, 2012.
  11. Align Deep Features for Oriented Object Detection. In IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, pages 1–11, 2021.
  12. ReDet: A Rotation-equivariant Detector for Aerial Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2786–2795, 2021.
  13. Mask r-cnn, 2017. cite arxiv:1703.06870Comment: open source; appendix on more results.
  14. Deep Residual Learning for Image Recognition. In Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’16, pages 770–778. IEEE, June 2016.
  15. R2cnn: Rotational region cnn for orientation robust scene text detection. ArXiv, abs/1706.09579, 2017.
  16. Oriented reppoints for aerial object detection. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1819–1828, Los Alamitos, CA, USA, jun 2022. IEEE Computer Society.
  17. Feature pyramid networks for object detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 936–944, Los Alamitos, CA, USA, jul 2017. IEEE Computer Society.
  18. Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2):318–327, 2020.
  19. Mogface: Towards a deeper appreciation on face detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4093–4102, June 2022.
  20. A high resolution optical satellite image dataset for ship recognition and some new baselines. In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,, pages 324–331. INSTICC, SciTePress, 2017.
  21. Arbitrary-oriented scene text detection via rotation proposals. In IEEE Transactions on Multimedia, volume 20, pages 3111–3122, 2018.
  22. Dynamic anchor learning for arbitrary-oriented object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2355–2363, 2021.
  23. Mask-guided attention network for occluded pedestrian detection. In Proceedings of the IEEE International Conference on Computer Vision, volume 2019-Octob, pages 4966–4974, 2019.
  24. Rsdet++: Point-based modulated loss for more accurate rotated object detection. ArXiv, abs/2109.11906, 2021.
  25. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 39, pages 1137–1149, 2017.
  26. FCOS: Fully convolutional one-stage object detection. In Proc. Int. Conf. Computer Vision (ICCV), 2019.
  27. Selective search for object recognition. In International Journal of Computer Vision, volume 104, pages 154–171, 2013.
  28. Seadronessee: A maritime benchmark for detecting humans in open water. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 2260–2270, January 2022.
  29. Learning maritime obstacle detection from weak annotations by scaffolding. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 955–964, January 2022.
  30. Hla-face: Joint high-low adaptation for low light face detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021.
  31. Non-local Neural Networks. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 7794–7803, 2018.
  32. A multi-camera vehicle tracking system based on city-scale vehicle re-id and spatial-temporal information. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 4077–4086, June 2021.
  33. DOTA : A Large-scale Dataset for Object Detection in Aerial Images. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
  34. Oriented R-CNN for Object Detection. In Proceedings of 2021 International Conference on Computer Vision, pages 3520–3529, 2021.
  35. Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 43, pages 1452–1459. IEEE, 2021.
  36. Dense label encoding for boundary discontinuity free rotation detection. arXiv preprint arXiv:2011.09670, 2020.
  37. R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object. In Proceedings of The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) R3Det:, 2021.
  38. Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss. In Proceedings of the International Conference on Machine Learning, 2021.
  39. SCRDet: Towards more robust detection for small, cluttered and rotated objects. In Proceedings of the IEEE International Conference on Computer Vision, volume 2019-Octob, pages 8231–8240, 2019.
  40. Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence. In Proceedings of 2021 Conference on Neural Information Processing Systems, pages 1–16, 2021.
  41. Detecting rotated objects as gaussian distributions and its 3-d generalization, 2022.
  42. Alpharotate: A rotation detection benchmark using tensorflow. arXiv preprint arXiv:2111.06677, 2021.
  43. The kfiou loss for rotated object detection, 2022.
  44. Oriented object detection in aerial images with box boundary-aware vectors. In Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021, pages 2149–2158, 2020.
  45. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proceedings of International Conference on Learning Representations, page s, 2021.
  46. Efficient attention: Attention with linear complexities. In Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021, pages 3530–3538, 2021.
Citations (7)
View on Semantic Scholar

Summary

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

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