International Journal of Engineering Research

Open Access Open Access  Restricted Access Subscription Access

Vehicle Feature Extraction and Application Based on Deep Convolution Neural Network


Affiliations
1 College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Long Teng road 333#, Songjiang District, Shanghai 201620, China
 

In view of the existing vehicle image features extraction of large amount of calculation, slow speed, extract the characteristics of the uniqueness is not strong, the complex extraction process and so on, is put forward based on the depth of the convolution of the neural network vehicle feature extraction method, and is applied to extract the depth of the characteristics of vehicle brand recognition and deck vehicle identification. The experiment shows that the proposed method can extract the depth characteristics of the vehicle effectively, and obtain good vehicle identification and identification accuracy.

Keywords

Feature Extraction, Deep Learning, Fake Plate Vehicles, Vehicle Recognition.
User
Notifications
Font Size

  • i F. Tafazzoli and H. Frigui, "Vehicle make and model recognition using local features and logo detection," 2016 International Symposium on Signal, Image, Video and Communications (ISIVC), Tunis, 2016, pp. 353-358.

  • ii M. A. Manzoor and Y. Morgan, "Vehicle Make and Model classification system using bag of SIFT features," 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, 2017, pp. 1-5.

  • iii Llorca D F, Arroyo R, Sotelo M A. Vehicle logo recognition in traffic images using HOG features and SVM[C]// International IEEE Conference on Intelligent Transportation Systems. IEEE, 2014:2229-2234.

  • iv Ma X, Grimson W E L. Edge-Based Rich Representation for Vehicle Classification[C]// Tenth IEEE International Conference on Computer Vision. IEEE, 2005:1185-1192 Vol. 2.

  • v LOHMANN, A. W. & BROWN, B. R. 1966. Complex Spatial Filtering with Binary Masks. Applied Optics, 5, 967.

  • vi Y. Gao and H. J. Lee, "Vehicle Make Recognition Based on Convolutional Neural Network," 2015 2nd International Conference on Information Science and Security (ICISS), Seoul, 2015, pp. 1-4.

  • vii HUEBSCHMAN, M., MUNJULURI, B. & GARNER, H. 2003. Dynamic holographic 3-D image projection. Optics Express, 11, 437-45.

  • viii Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the Acm, 2013, 60(2):2012.

  • ix S. Liu, Y. Sun, Y. Hu, J. Gao, F. Ju and B. Yin, "Matrix variate RBM model with Gaussian distributions," 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, 2017, pp. 808-815.

  • x S. De and T. Goldstein, "Efficient Distributed SGD with Variance Reduction," 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, 2016, pp. 111-120.


Abstract Views: 181

PDF Views: 0




  • Vehicle Feature Extraction and Application Based on Deep Convolution Neural Network

Abstract Views: 181  |  PDF Views: 0

Authors

Hua Zhang
College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Long Teng road 333#, Songjiang District, Shanghai 201620, China
Xiang Liu
College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Long Teng road 333#, Songjiang District, Shanghai 201620, China

Abstract


In view of the existing vehicle image features extraction of large amount of calculation, slow speed, extract the characteristics of the uniqueness is not strong, the complex extraction process and so on, is put forward based on the depth of the convolution of the neural network vehicle feature extraction method, and is applied to extract the depth of the characteristics of vehicle brand recognition and deck vehicle identification. The experiment shows that the proposed method can extract the depth characteristics of the vehicle effectively, and obtain good vehicle identification and identification accuracy.

Keywords


Feature Extraction, Deep Learning, Fake Plate Vehicles, Vehicle Recognition.

References