Abstract
In the road scenarios, small-sized license plates are challenging to detect due to their small area. The direct detection methods based on anchors are not experts in detecting small-sized license plates due to foreground-background class imbalance. In this work, we propose an anchor-free location refinement network to alleviate the imbalance problem. First, we adopt the anchor-free mechanism to increase the proportion of foreground samples. Second, we use a coarse-to-fine strategy to reduce the background noises. Specifically, the whole network is combined with a coarse detection module (CDM) and a location refinement module (LRM), where the anchor-free CDM can approximately locate the local region around the license plate, and LRM can get a more accurate location of the license plate in the local region. The whole network can be trained in an end-to-end manner. Moreover, the proposed network can detect multi-directional license plates by regressing the four corners of the license plate in LRM. Extensive experiments verify that our method outperforms the baseline model by 6\(\%\) AP on the road license plate detection dataset and improves the recall of small-sized license plates by 7.5\(\%\), thus improving license plate recognition by 3.5\(\%\). Moreover, we improve the AP by 4.2\(\%\) on the traffic sign dataset TT100K, verifying its generalization ability.
Z.-J. Li and S.-L. Chen—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xu, Z., et al.: Towards end-to-end license plate detection and recognition: a large dataset and baseline. In: Proceedings of the European Conference on Computer Vision, Munich, pp. 261–277 (2018)
Chou, J., Liu, C.: Automated sensing system for real-time recognition of trucks in river dredging areas using computer vision and convolutional deep learning. Sensors 21(2), 555 (2021)
Chen, S., et al.: End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining. Neurocomputing 446, 1–10 (2021)
Silva, S.M., Jung, C.R.: License plate detection and recognition in unconstrained scenarios. In: Proceedings of the European Conference on Computer Vision, Munich, pp. 593–609 (2018)
Laroca, R., et al.: A robust real-time automatic license plate recognition based on the YOLO detector. In: International Joint Conference on Neural Networks, Rio de Janeiro, pp. 1–10 (2018)
Silva, S.M., Jung, C.R.: Real-time license plate detection and recognition using deep convolutional neural networks. J. Vis. Commun. Image Represent. 71, 102773 (2020)
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE International Conference on Computer Vision, Seoul, pp. 9626–9635 (2019)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Annual Conference on Neural Information Processing Systems, Montreal, Quebec, pp. 91–99 (2015)
Girshick, R.B.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, Santiago, pp. 1440–1448 (2015)
Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: Retinaface: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, pp. 5202–5211 (2020)
Fang, F., Xu, Q., Li, L., Gu, Y., Lim, J.: Detecting objects with high object region percentage. In: International Conference on Pattern Recognition, Virtual Event/Milan, pp. 7173–7180 (2020)
Deguerre, B, Chatelain, C., Gasso, G.: Object detection in the DCT domain: is luminance the solution? In: International Conference on Pattern Recognition, Virtual Event/Milan, pp. 2627–2634 (2020)
Gan, Y., Xu, W., Su, J.: SFPN: semantic feature pyramid network for object detection. In: International Conference on Pattern Recognition, Virtual Event/Milan, pp. 795–802 (2020)
Guo, T., Zhang, L., Ding, R., Yang, G.: Edd-net: an efficient defect detection network. In: International Conference on Pattern Recognition, Virtual Event/Milan, pp. 8899–8905 (2020)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, pp. 6517–6525 (2017)
Bochkovskiy, A., Wang, C., Liao, H.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Liu, W., et al.: SSD: single shot multibox detector. In: Proceedings of the European Conference on Computer Vision, Amsterdam, pp. 21–37 (2016)
Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 779–788 (2016)
Duan, K., Xie, L., Qi, H., Bai, S., Huang, Q., Tian, Q.: Corner proposal network for anchor-free, two-stage object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 399–416. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_24
Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision, Munich. Lecture Notes in Computer Science, vol. 11218, pp. 765–781 (2018)
He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386–397 (2020)
Li, H., Wang, P., Shen, C.: Toward end-to-end car license plate detection and recognition with deep neural networks. IEEE Trans. Intell. Transp. Syst. 20(3), 1126–1136 (2019)
Salau, A.O.: An effective graph-cut segmentation approach for license plate detection. In: Recent Trends in Image and Signal Processing in Computer Vision, p. 19 (2020)
Omar, N., Abdulazeez, A.M., Sengur, A., Al-Ali, S.G.S.: Fused faster RCNNs for efficient detection of the license plates. Indonesian J. Electric. Eng. Comput. Sci. 19(2), 974–982 (2020)
Chen, S., Yang, C., Ma, J., Chen, F., Yin, X.: Simultaneous end-to-end vehicle and license plate detection with multi-branch attention neural network. IEEE Trans. Intell. Transp. Syst. 21(9), 3686–3695 (2020)
He, M., Hao, P.: Robust automatic recognition of Chinese license plates in natural scenes. IEEE Access 8, 173804–173814 (2020)
Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10778–10787 (2020)
Fu, Q., Shen, Y., Guo, Z.: License plate detection using deep cascaded convolutional neural networks in complex scenes. In: Proceedings of the International Conference on Neural Information Processing, Guangzhou, pp. 696–706 (2017)
Chen, S.-L., Liu, Q., Ma, J.-W., Yang, C.: Scale-invariant multidirectional license plate detection with the network combining indirect and direct branches. Sensors 21(4), 1074 (2021)
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: Conference on Artificial Intelligence, New York, pp. 12993–13000 (2020)
Lin, T., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, Venice, pp. 2999–3007 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 770–778 (2016)
Madsen, K., Nielsen, H.B.: A finite smoothing algorithm for linear l\({}_{\text{1 }}\) estimation. SIAM J. Optim. 3(2), 223–235 (1993)
G.J., et al.: ultralytics/yolov5: v6.0 - YOLOv5n ‘Nano’ models, Roboflow integration, TensorFlow export, OpenCV DNN support (2021)
Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, pp. 840–849 (2019)
gm19900510. Pytorch retina license plate. https://github.com/gm19900510/Pytorch_Retina_License_Plate/ (2020)
Liu, Q., Chen, S., Li, Z., Yang, C., Chen, F., Yin, X.: Fast recognition for multidirectional and multi-type license plates with 2d spatial attention. In: International Conference on Document Analysis and Recognition, Lausanne, pp. 125–139 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, ZJ., Chen, SL., Liu, Q., Chen, F., Yin, XC. (2022). Anchor-Free Location Refinement Network for Small License Plate Detection. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13537. Springer, Cham. https://doi.org/10.1007/978-3-031-18916-6_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-18916-6_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18915-9
Online ISBN: 978-3-031-18916-6
eBook Packages: Computer ScienceComputer Science (R0)