Abstract
Traffic vehicle detection and recognition is a core technology of advanced driver assistant system (ADSD) for the intelligent vehicle. In this paper, we employ the convolution neural network (CNN) to perform the end-to-end vehicle detection and recognition.
Two vehicle classification CNNs are proposed. One is a convolution neural network consisting of four convolution layers and another is a multi-label classification network. The first networks can achieve the accuracy more than 95% while the second can achieve the accuracy more than 98%. Due to the multiple constraints, the proposed multi-label classification network is able to converge fast and achieve higher accuracy.
The vehicle detection model proposed in this paper is a model on the basis of the network model single shot multibox detector (SSD). Our network model employs the network proposed for vehicle classification as a basis network for feature extraction and design a multi-label loss for detection. The proposed network structure can achieve 77.31% mAP on the vehicle detection dataset. Compared with that of SSD network model, the obtained mAP is improved by 2.17%. The processing speed of proposed vehicle detection network can reach 12FPS, which can meet the real-time requirements.
Sponsored by the Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University, ZZ2019140 and National College Students’ innovation and entrepreneurship training program, 201810699167.
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
Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642–3649, June 2012
Ciresan, D.C., Meier, U., Masci, J., Gambardella, L.M., Schmidhuber, J.: Flexible, high performance convolutional neural networks for image classification, pp. 1237–1242, July 2011
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886–893, June 2005
Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition, pp. 647–655 (2014)
Forsyth, D.: Object detection with discriminatively trained part-based models. Computer 47(02), 6–7 (2014)
Hu, Y., et al.: Algorithm for vision-based vehicle detection and classification, pp. 568–572, December 2013
Krause, J., Stark, M., Deng, J., Li, F.F.: 3D object representations for fine-grained categorization. In: 2013 IEEE International Conference on Computer Vision Workshops, pp. 554–561, December 2013
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Neural Inf. Process. Syst. 25, 1097–1105 (2012)
Lawrence, S., Giles, C.L., Tsoi, A.C., Back, A.D.: Face recognition: a convolutional neural-network approach. IEEE Trans. Neural Networks 8(1), 98–113 (1997)
Ren, S., He, K., Ross, G., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 91–99 (2015)
Sarfraz, M.S., Saeed, A., Haris Khan, M., Zahid, R.: Bayesian prior models for vehicle make and model recognition, p. 35, January 2009
Shams, F.: Joint deep learning for car detection, December 2014
Vojislav, K.: Learning and soft Computing: Support Vector Machines, Neural Networks and Fuzzy Logic Models. MIT Press, Cambridge (2001)
Zhang, F., Xu, X., Qiao, Y.: Deep classification of vehicle makers and models: the effectiveness of pre-training and data enhancement. In: 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 231–236, December 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Rao, Y., Zhang, G., Zhou, W., Wang, C., Lv, Y. (2020). Deep Convolutional Neural Network Based Traffic Vehicle Detection and Recognition. In: Li, B., Zheng, J., Fang, Y., Yang, M., Yan, Z. (eds) IoT as a Service. IoTaaS 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 316. Springer, Cham. https://doi.org/10.1007/978-3-030-44751-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-44751-9_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44750-2
Online ISBN: 978-3-030-44751-9
eBook Packages: Computer ScienceComputer Science (R0)