TY - GEN
T1 - Indonesia Toll Road Vehicle Classification Using Transfer Learning with Pre-Trained Resnet Models
AU - Sasongko, Ananto Tri
AU - Ivan Fanany, Mohamad
N1 - Funding Information:
ACKNOWLEDGMENT This article was supported and funded by Q1Q2 Research Grant from Directorate of Research and Public Services, Universitas Indonesia No. NKB-0209/UN2.R3.1/HKP.05.00/ 2019 and special thanks to Google for the CoLaboratory.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Research in vehicle classification through various methods has become a popular field of study for decades. Mainly, vehicles are categorized based on the model, manufactured, logo, types, and dimensions, and the dataset for it is available publicly and relatively easy to get. However, based on our survey, vehicle classification based on the number of axles using deep learning has not been conducted, and the public dataset for it is not available yet. This paper aims to compose a vehicle classification based on type and number of axles then categorize it into five groups, namely, Group-I, Group-II, Group-III, Group-IV, and Group-V. This vehicle grouping refers to the Indonesia toll road tariff regulation. Nowadays, deep learning as one of the most advanced methods becomes the preferred technique to apply in image classifications due to its high performance, so do this study. Utilizing Convolution Neural Networks (CNN) as image segmentation and classification, Transfer Learning as a technique, Resnet architectures as base models, and fine-Tuning as an enhancement, we can achieve accuracy about 99% for the specific vehicle classification in this study.
AB - Research in vehicle classification through various methods has become a popular field of study for decades. Mainly, vehicles are categorized based on the model, manufactured, logo, types, and dimensions, and the dataset for it is available publicly and relatively easy to get. However, based on our survey, vehicle classification based on the number of axles using deep learning has not been conducted, and the public dataset for it is not available yet. This paper aims to compose a vehicle classification based on type and number of axles then categorize it into five groups, namely, Group-I, Group-II, Group-III, Group-IV, and Group-V. This vehicle grouping refers to the Indonesia toll road tariff regulation. Nowadays, deep learning as one of the most advanced methods becomes the preferred technique to apply in image classifications due to its high performance, so do this study. Utilizing Convolution Neural Networks (CNN) as image segmentation and classification, Transfer Learning as a technique, Resnet architectures as base models, and fine-Tuning as an enhancement, we can achieve accuracy about 99% for the specific vehicle classification in this study.
KW - Convolutional Neural Networks
KW - Dataset
KW - Deep Learning
KW - Fine-Tuning
KW - Transfer Learning
KW - Vehicle Classification
UR - http://www.scopus.com/inward/record.url?scp=85083308597&partnerID=8YFLogxK
U2 - 10.1109/ISRITI48646.2019.9034590
DO - 10.1109/ISRITI48646.2019.9034590
M3 - Conference contribution
AN - SCOPUS:85083308597
T3 - 2019 2nd International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2019
SP - 373
EP - 378
BT - 2019 2nd International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2019
A2 - Wibowo, Ferry Wahyu
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2019
Y2 - 5 December 2019 through 6 December 2019
ER -