Abstract
Rotated object detection aims to identify and locate objects in images with oriented angles. In this case, the detection scenario varies a lot in multi-dimensions. Besides, multiple oriented objects always exist within a single image, which increase the complexity for angle prediction. Although representing the angle by an extra regression branch can enhance precision in rotated box detector, it’s more plausible to optimize the prediction process in a global view including feature-extraction, detection field partition and angle regression branch. In this paper, we introduced a partitioned detection architecture to identify objects which are at different scales, corresponding to different feature levels of the network. Inspired by Vision Transformer, a series of novel attention layers are embedded seamlessly for extracting necessary features from different scales and regions. We also conducted a short-term diffusion process to produce Gaussian noise in original image considering generalizability. As is shown, our detectors show a significant improvement of mAP and balance between performance and accuracy in two challenging aerial detection task, DOTA and HRSC2016.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zaidi, S.S.A., et al.: A survey of modern deep learning based object detection models. Digit. Signal Process. 126, 103514 (2022)
Yang, X., et al.: SCRDet: towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8232–8241 (2019)
Wang, X., et al.: PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector. arXiv preprint arXiv:2211.02386 (2022)
Wang, J., et al.: Learning center probability map for detecting objects in aerial images. IEEE Trans. Geosci. Remote Sens. 59(5), 4307–4323 (2020)
Wang, H., et al.: Multigrained angle representation for remote-sensing object detection. IEEE Trans. Geosci. Remote Sens. 60, 1–13 (2022)
Yang, X., et al.: R3Det: refined single-stage detector with feature refinement for rotating object. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3163–3171 (2021)
Li, W., et al.: Oriented reppoints for aerial object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1829–1838 (2022)
Zhu, B., et al.: Autoassign: differentiable label assignment for dense object detection. arXiv preprint arXiv:2007.03496 (2020)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Yang, X., et al.: H2RBox: Horizonal Box Annotation is All You Need for Oriented Object Detection. arXiv preprint arXiv:2210.06742 (2022)
Yang, X., et al.: The KFIoU loss for rotated object detection. arXiv preprint arXiv:2201.12558 (2022)
Park, J., Woo, S., Lee, J.Y., Kweon, I.S.: BAM: bottleneck attention module. In: British Machine Vision Conference (2018)
Woo, S., Park, J.C., Lee, J.-Y., Kweon, I.: CBAM: convolutional block attention module. In: 15th European Conference, Munich, Germany, 8–14 September 2018, Part VII (2018). https://doi.org/10.1007/978-3-030-01234-2-1
Xia, G.-S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974–3983 (2018)
Liu, Z., et al.: A high resolution optical satellite image dataset for ship recognition and some new baselines. In: ICPRAM, pp. 324–331 (2017)
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
Yang, X., et al.: Learning high-precision bounding box for rotated object detection via kullback-leibler divergence. In: Advances in Neural Information Processing Systems, vol. 34, pp. 18381–18394 (2021)
Hou, L., Lu, K., Yang, X., Li, Y., Xue, J.: G-Rep: gaussian representation for arbitrary-oriented object detection. Remote. Sens. 15, 757 (2022)
Guan, J., et al.: EARL: An Elliptical Distribution aided Adaptive Rotation Label Assignment for Oriented Object Detection in Remote Sensing Images. arXiv preprint arXiv:2301.05856 (2023)
Yang, F., Fan, H., Chu, P., Blasch, E., Ling, H.: Clustered object detection in aerial images. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp. 8310–8319 (2019). https://doi.org/10.1109/ICCV.2019.00840
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Ge, Z., et al.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)
Han, J., et al.: Align deep features for oriented object detection. IEEE Trans. Geosci. Remote Sens. 60, 1–11 (2021)
Chen, Z., et al.: PIoU loss: towards accurate oriented object detection in complex environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 195–211. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_12
Zhang, S., et al.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759–9768 (2020)
Pan, X., et al.: Dynamic refinement network for oriented and densely packed object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11207–11216 (2020)
Wei, H., et al.: Oriented objects as pairs of middle lines. ISPRS J. Photogramm. Remote. Sens. 169, 268–279 (2020)
Jiang, Y., et al.: R2CNN: rotational region CNN for orientation robust scene text detection. arXiv preprint arXiv:1706.09579 (2017)
Ding, J., et al.: Learning ROI transformer for oriented object detection in aerial images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2849–2858 (2019)
Ming, Q., et al.: Dynamic anchor learning for arbitrary-oriented object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2355–2363 (2021)
Liu, Z., et al.: Rotated region based CNN for ship detection. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 900–904. IEEE (2017)
Xiao, Z., Qian, L., Shao, W., Tan, X., Wang, K.: Axis learning for orientated objects detection in aerial images. Remote Sens. 12, 908 (2020)
Feng, P., et al.: TOSO: Student’sT distribution aided one-stage orientation target detection in remote sensing images. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4057–4061. IEEE (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, S., Wei, Y. (2023). A Partitioned Detection Architecture for Oriented Objects. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14256. Springer, Cham. https://doi.org/10.1007/978-3-031-44213-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-44213-1_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44212-4
Online ISBN: 978-3-031-44213-1
eBook Packages: Computer ScienceComputer Science (R0)