| Title |
Vehicle Type Classification Under Traffic Monitoring Based On Improved Capsule Network |
| ID_Doc |
60968 |
| Authors |
Yu X.; Zhang W.; Wang Y.; Huang Z.; Hong X.; Jiang B. |
| Year |
2022 |
| Published |
Proceedings of SPIE - The International Society for Optical Engineering, 12249 |
| DOI |
http://dx.doi.org/10.1117/12.2636610 |
| Abstract |
In order to solve the problem of vehicle congestion in smart cities, this paper proposes a new network model structure (VGG8-1-CapsNet) to classify the types of vehicles. First, the first 8 convolutional layers of VGG16 and one convolutional layer are combined to form the feature extraction layer of the network model. Secondly, the obtained features are input into the capsule network, and the three-dimensional spatial feature conversion is performed on the extracted features. Finally, the dynamic routing algorithm is used to output, so as to achieve the purpose of vehicle classification. The experiment-al results show that the model has 98.98% accuracy on the expanded BIT-Vehicle, and the training speed is faster. © 2022 SPIE |
| Author Keywords |
CapsNet; traffic monitoring; vehicle type classification; VGG16 |
