Deep learning assisted automated vehicle detection and classification for intelligent transportation systems
Abstract
Vehicle classification is one of the key elements of intelligent transportation systems (ITS). Various ITS applications, such as surveillance structures, security systems, fleet monitoring, traffic protection, and automatic parking employs vehicle classification. Current developments in artificial intelligence (AI) have greatly impacted the study related to vehicle detection and classification. This study presents a fusion-based transfer learning model with a crayfish optimization algorithm for robust vehicle classification in intelligent transportation system (FTLMCOA-VCITS). The FTLMCOA-VCITS model aims to enhancing vehicle classification using advanced deep learning (ADL) models. In the initial stage, the image preprocessing utilizes Wiener filtering (WF) to remove the noise. For the feature representation process, the fusion of the DenseNet-201, EfficientNet-B7, and CapsNet is employed. For the classification process, COA with deep belief network (DBN) approach is used. The comprehensive comparative results demonstrate an increased accuracy of 99.08% over existing methods under the vehicle classification dataset.
Keywords
Crayfish optimization algorithm; Deep belief network; Intelligent transportation system; Transfer learning; Vehicle classification
Full Text:
PDFDOI: https://doi.org/10.11591/eei.v15i6.13430
Refbacks
- There are currently no refbacks.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191
,
e-ISSN: 2302-9285
This journal is published by the
Institute of Advanced Engineering and Science (IAES)
.