Abstract
Confirming the vehicle information in the surveillance video is an important issue in the intelligent transportation system at present. As a key and fixed feature, the vehicle logo can play a role in assisting the discrimination. According to the characteristics of the vehicle logo image, we propose a high-efficiency logo detection method based on the improved YOLOv2, which adopts the strategies of separable convolution, multi-scale channel fusion and automated multi-scale test, compared with the traditional vehicle identification method based on manual extraction features, so the method has the advantages of self-learning features, direct input of images, and the like, and can realize the dual functions of positioning and recognition of the vehicle logo. Experiments show that the model has excellent stability under low-resolution (very small target), illumination effects, angular rotation and noise pollution, and has high accuracy, recall and real-time. On the data set used, our model was trained on the NVIDIA GTX1070 GPU (8G memory) server, which achieved a recall rate of Recall = 0.997, an average accuracy of mAP = 0.990, and a test speed of approximately 21.3 FPS, far exceeding the performance of any other current vehicle logo detection method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Luo, B., You, Z., Cao, G.: Fast vehicle identification method based on edge histogram. J. Comput. Appl. 21(6), 150–151 (2004)
Wang, Y., Liu, Z., Xiao, F.: A fast coarse-to-fine vehicle logo detection and recognition method. In: IEEE International Conference on Robotics & Biomimetics (2008)
Wang, M., Wang, G., Fang, P., Sun, S.: Method for vehicle-logo location and recognition based on PCA and invariant moment. Geomat. Inf. Sci. Wuhan Univ. 33(1), 36–40 (2008)
Mu, S., Liu, Z., Zhang, J.: Vehicle identification method based on image quality and PCA subspace. J. Comput. Appl. 30(8), 2244–2246 (2010)
Yu, S., Zheng, S., Hua, Y., et al.: Vehicle logo recognition based on Bag-of-Words. In: IEEE International Conference on Advanced Video & Signal Based Surveillance (2013)
Llorca, D.F., Arroyo, R., Sotelo, M.Á.: Vehicle logo recognition in traffic images using HOG features and SVM. In: IEEE Intelligent Transportation Systems Conference (ITSC). IEEE (2013)
Sam, K.T., Tian, X.L.: Vehicle logo recognition using modest AdaBoost and radial Tchebichef moments. In: International Proceedings of Computer Science & Information Tech (2012)
Wang, Y., Liu, Z., Xiao, F.: Real-time vehicle location and recognition method based on symmetry. J. Syst. Simul. 21(4) (2009)
Wang, S.K., Liu, L., Xu, X.: Vehicle logo recognition based on local feature descriptor. Appl. Mech. Mater. 263–266, 2418–2421 (2013)
Psyllos, A.P., Kayafas, E.: Vehicle logo recognition using a SIFT-based enhanced matching scheme. IEEE Trans. Intell. Transp. Syst. 11(2), 322–328 (2010)
Guan, X., Huang, Y., Cai, Z., Ohtsuki, T.: Intersection-based forwarding protocol for vehicular ad hoc networks. Telecommun. Syst. J. 62(1), 67–76 (2016)
Xiong, Z., Li, W., Han, Q., Cai, Z.: Privacy-preserving auto-driving: a GAN-based approach to protect vehicular camera data. In: 19th IEEE International Conference on Data Mining (ICDM 2019) (2019)
Wang, J., Cai, Z., Yu, J.: Achieving personalized k-anonymity based content privacy for autonomous vehicles in CPS. IEEE Trans. Ind. Inform. (TII) 16(6), 4242–4251 (2020)
Fan, J., Xu, W., Wu, Y., et al.: Human tracking using convolutional neural networks. IEEE Trans. Neural Netw. 21(10), 1610–1623 (2010)
Karpathy, A., Toderici, G., Shetty, S., et al.: Large-scale video classification with convolutional neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2014)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision & Pattern Recognition (2017)
Everingham, M., Winn, J.: The PASCAL visual object classes challenge 2007 (VOC 2007) development kit. Int. J. Comput. Vis. 111(1), 98–136 (2006)
Purkait, P., Zhao, C., Zach, C.: SPP-Net: Deep Absolute Pose Regression with Synthetic Views (2017)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition (CVPR), pp. 580–587. IEEE (2014)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (2015)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)
Bo, P., Di, Y.: Research on vehicle identification method based on deep learning. Comput. Sci. 42(4), 268–273 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yin, K., Hou, S., Li, Y., Li, C., Yin, G. (2020). A Real-Time Vehicle Logo Detection Method Based on Improved YOLOv2. In: Yu, D., Dressler, F., Yu, J. (eds) Wireless Algorithms, Systems, and Applications. WASA 2020. Lecture Notes in Computer Science(), vol 12384. Springer, Cham. https://doi.org/10.1007/978-3-030-59016-1_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-59016-1_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59015-4
Online ISBN: 978-3-030-59016-1
eBook Packages: Computer ScienceComputer Science (R0)