Abstract
Object detection, one of the core missions in computer vision, plays a significant role in various real-life scenarios. To address the limitations of pre-defined anchor boxes in object detection, a novel multi-scale key-point detector is proposed to achieve rapid detection of natural scenes with high accuracy. Compared with the method based on key-point detection, our proposed method has fewer detection points which are the sum of pixels on four-layer compared to one-layer. Furthermore, we use feature pyramids to avoid ambiguous samples. Besides, in order to generate feature maps with high quality, a novel residual dense block with coordinate attention is proposed. In addition to reducing gradient explosion and gradient disappearance, it can reduce the number of parameters by 5.3 times compared to the original feature pyramid network. Moreover, a non-key-point suppression branch is proposed to restrain the score of bounding boxes far away from the center of the target. We conduct numerous experiments to comprehensively verify the real-time, effectiveness, and robustness of our proposed algorithm. The proposed method with ResNet-18 and resolution of \(384\times 384\) achieves \(77.3\%\) mean average precision at a speed of 87 FPS on the VOC2007 test, better than CenterNet under the same settings.
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
References
Zheng, Y., Pal, D.K., Savvides, M.: Ring loss: convex feature normalization for face recognition. In: 2018 CVPR, pp. 5089–5097. IEEE, Salt Lake City (2018)
Wang, D., Devin, C., Cai, Q., et al.: Deep object-centric policies for autonomous driving. In: ICRA, pp. 8853–8859. IEEE, Montreal (2019)
Lin, T.Y., Dollár, P., Girshick, R., Hariharan, B., Belongie, S., et al.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125. IEEE (2017)
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: CVPR, pp. 2980–2988. IEEE (2017)
Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. Int. J. Comput. Vis. 128(3), 642–656 (2019). https://doi.org/10.1007/s11263-019-01204-1
Xingyi, Z., Jiacheng, Z., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: CVPR, pp. 850–859. IEEE (2019)
Zhou, X., Wang, D., Philipp K.: Objects as points. arXiv:1904.07850 (2019)
Huang, L., Yang, Y., Deng, Y., et al.: DenseBox: unifying landmark localization with end to end object detection. arXiv:1509.04874 (2015)
Tian, Z., Shen, C., Chen, H., et al.: FCOS: fully convolutional one-stage object detection. In: ICCV, pp. 9627–9636. IEEE (2019)
Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: CVPR, pp. 840–849. IEEE (2019)
Zhu, C., Chen, F., Shen, Z., et al.: Soft anchor-point object detection. In: ECCV, vol. 12354. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_6
Kong, T., Sun, F., Liu, H., et al.: FoveaBox: beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389–7398. IEEE (2020)
Bodla, N., Singh, B., Chellappa, R., et al.: Soft-NMS-improving object detection with one line of code. In: ICCV, pp. 5561–5569. IEEE (2017)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: CVPR, pp. 770–778. IEEE (2016)
Everingham, M., Van Gool, L., Williams, C.K., et al.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Zhang, Y., Tian, Y., Kong, Y., et al.: Residual dense network for image super-resolution. In: CVPR, pp. 2472–2481. IEEE (2018)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: CVPR. IEEE (2021)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier networks. In: Proceedings of the AISTATS, pp. 315–323 (2011)
Yu, J., Jiang, Y., Wang, Z., et al.: UnitBox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516–520. Elsevier (2016)
Ilya, L., Frank, H.: SGDR: Stochastic gradient descent with warm restarts. In: 5th International Conference on Learning Representations. Elsevier (2017)
Sandler, M., Howard, A., Zhu, M., et al.: MobileNetV2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510–4520. IEEE (2018)
https://github.com/Cartucho/mAP, 29 May 2020
Acknowledgments
This work was supported by National Natural Science Foundation of China under Grants 61901061, 61972056, Natural Science Foundation of Hunan Province of China under Grant 2020JJ5603, the Scientific Research Fund of Hunan Provincial Education Department under Grant 19C0031, 19C0028, the Young Teachers’ Growth Plan of Changsha University of Science and Technology under Grant 2019QJCZ011.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Kuang, LD., Tao, JJ., Zhang, J., Li, F., Chen, X. (2021). A Novel Multi-scale Key-Point Detector Using Residual Dense Block and Coordinate Attention. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13110. Springer, Cham. https://doi.org/10.1007/978-3-030-92238-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-92238-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92237-5
Online ISBN: 978-3-030-92238-2
eBook Packages: Computer ScienceComputer Science (R0)