Vehicle type classification under traffic monitoring based on improved capsule network

Xiaokang Yu; Weizhong Zhang; Ying Wang; Zhikai Huang; Xin Hong; Bowen Jiang

doi:10.1117/12.2636610

8 May 2022 Vehicle type classification under traffic monitoring based on improved capsule network

Xiaokang Yu, Weizhong Zhang, Ying Wang, Zhikai Huang, Xin Hong, Bowen Jiang

Proceedings Volume 12249, 2nd International Conference on Internet of Things and Smart City (IoTSC 2022）; 122493A (2022) https://doi.org/10.1117/12.2636610
Event: 2022 2nd International Conference on Internet of Things and Smart City (IoTSC 2022）, 2022, Xiamen, China

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.

Citation Download Citation

Xiaokang Yu, Weizhong Zhang, Ying Wang, Zhikai Huang, Xin Hong, and Bowen Jiang "Vehicle type classification under traffic monitoring based on improved capsule network", Proc. SPIE 12249, 2nd International Conference on Internet of Things and Smart City (IoTSC 2022）, 122493A (8 May 2022); https://doi.org/10.1117/12.2636610

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available