| Title |
Hybrid Model Of Vehicle Recognition Based On Convolutional Neural Network |
| ID_Doc |
29782 |
| Authors |
Su C.; Wei J. |
| Year |
2020 |
| Published |
Proceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 |
| DOI |
http://dx.doi.org/10.1109/HPCC-SmartCity-DSS50907.2020.00161 |
| Abstract |
With the improvement of people's living standard, the number of cars on the road has increased dramatically. Vehicle recognition is greatly significant for intelligent traffic management. In this paper, a hybrid model of vehicle recognition algorithm based on VGG16-softmax hybrid model is proposed. The convolutional neural network called VGG16 is used, Imagenet is used for pre-Training, migration learning is used to migrate parameters to the new training model, variational auto-encoder is used for data reconstruction, and finally softmax multi-classifier is used for classification. Experiments show that this method can save time, get better vehicle feature of details and higher accuracy. © 2020 IEEE. |
| Author Keywords |
convolutional neural network; softmax; variational auto-coder; VGG16 |
