Performance Evaluation of the Transfer Learning Model in Car Vehicle Detection

Dafa Fidini Asqav, Rahmawati Rahmawati, Monica Marito Manurung

Abstract


Congestion is a common problem that occurs in big cities. It is necessary to make an ITS (Intelligent Transportation System) using computer vision to monitor street density by counting the number of passing vehicles. The basis of vehicle counting is vehicle detection. This study will compare the performance of vehicle detection models in order to make it easier to determine which model is suitable for implementation. The dataset used is the Vehicle Detection Image Set. The models used are InceptionV3, Xception, MobileNet, MobileNet V2, VGG 16, VGG 19, Efficientnet (B7), and Efficientnet V2 (L). The results show that Inception, Xception, Mobilenet, and VGG19 are the models with the highest test accuracy. The VGG 16 model has the shortest training duration while the Efficientnet V2 (L) has the longest training duration.


Keywords


EfficientNet; MobileNet; Transfer Learning; Vehicle Detection; VGG

Full Text:

PDF

References


Li, S., Chang, F., and Liu, C. (2020). Bi-directional dense traffic counting based on spatio-temporal counting feature and counting-LSTM network. IEEE Transactions on Intelligent Transportation Systems, 22(12), 7395-7407.

Azimjonov, J., and Özmen, A. (2021). A real-time vehicle detection and a novel vehicle tracking systems for estimating and monitoring traffic flow on highways. Advanced Engineering Informatics, 50(1), 1-14.

Song, H., Liang, H., Li, H., Dai, Z., and Yun, X. (2019). Vision-based vehicle detection and counting system using deep learning in highway scenes. European Transport Research Review, 11(1), 1-16.

Chen, Y., and Li, Z. (2022). An effective approach of vehicle detection using deep learning. Computational Intelligence and Neuroscience, 2022(1), 1-9.

Li, Y., Song, B., Kang, X., Du, X., and Guizani, M. (2018). Vehicle-type detection based on compressed sensing and deep learning in vehicular networks. Sensors, 18(12), 1-15.

Arora, N., Kumar, Y., Karkra, R., and Kumar, M. (2022). Automatic vehicle detection system in different environment conditions using fast R-CNN. Multimedia Tools and Applications, 81(13), 18715-18735.

Gai, W., Liu, Y., Zhang, J., and Jing, G. (2021). An improved tiny YOLOv3 for real-time object detection. Systems Science and Control Engineering, 9(1), 314-321.

Al Husaini, M. A. S., Habaebi, M. H., Gunawan, T. S., Islam, M. R., Elsheikh, E. A., and Suliman, F. M. (2022). Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4. Neural Computing and Applications, 34(1), 333-348.

Lin, C., Li, L., Luo, W., Wang, K. C., and Guo, J. (2019). Transfer learning based traffic sign recognition using inception-v3 model. Periodica Polytechnica Transportation Engineering, 47(3), 242-250.

Chen, B., Liu, X., Zheng, Y., Zhao, G., and Shi, Y. Q. (2021). A robust GAN-generated face detection method based on dual-color spaces and an improved xception. IEEE Transactions on Circuits and Systems for Video Technology, 32(6), 3527-3538.

Polat, Ö. Z. L. E. M. (2021). Detection of COVID-19 from chest CT images using xception architecture: a deep transfer learning based approach. Sakarya University Journal of Science (SAUJS), 25(3), 813-823.

Jing, J., Wang, Z., Rätsch, M., and Zhang, H. (2022). Mobile-unet: an efficient convolutional neural network for fabric defect detection. Textile Research Journal, 92(1), 30-42.

Kulkarni, U., Meena, S. M., Gurlahosur, S. V., and Bhogar, G. (2021). Quantization friendly mobilenet (QF-mobilenet) architecture for vision based applications on embedded platforms. Neural Networks, 136(1), 28-39.

Ghosh, T., Abedin, M. M. H. Z., Chowdhury, S. M., Tasnim, Z., Karim, T., Reza, S., Saika, S., and Yousuf, M. A. (2020). Bangla handwritten character recognition using MobileNet V1 architecture. Bulletin of Electrical Engineering and Informatics, 9(6), 2547-2554.

Wibowo, A., Adhi Hartanto, C., and Wisnu Wirawan, P. (2020). Android skin cancer detection and classification based on MobileNet V2 model. International Journal of Advances in Intelligent Informatics, 6(2), 135-148.

Pardede, J., Sitohang, B., Akbar, S., and Khodra, M. L. (2021). Implementation of transfer learning using VGG16 on fruit ripeness detection. International Journal of Intelligent Systems and Applications, 13(2), 52-61.

Rangarajan, A. K., and Purushothaman, R. (2020). Disease classification in eggplant using pre-trained VGG16 and MSVM. Scientific Reports, 10(1), 1-11.

Mateen, M., Wen, J., Nasrullah, N., Song, S., and Huang, Z. (2018). Fundus image classification using VGG-19 architecture with PCA and SVD. Symmetry, 11(1), 1-12.

Chowdhury, M. E., Rahman, T., Khandakar, A., Ayari, M. A., Khan, A. U., Khan, M. S., Al-Emadi, N., Ibne Reaz, M. B., Islam, M. T., and Ali, S. H. M. (2021). Automatic and reliable leaf disease detection using deep learning techniques. AgriEngineering, 3(2), 294-312.

Ali, K., Shaikh, Z. A., Khan, A. A., and Laghari, A. A. (2022). Multiclass skin cancer classification using EfficientNets–a first step towards preventing skin cancer. Neuroscience Informatics, 2(4), 1-10.

Rizal, S., Ibrahim, N., Pratiwi, N. K. C., Saidah, S., and Fu’adah, R. Y. N. (2020). Deep learning untuk klasifikasi diabetic retinopathy menggunakan model efficientnet. ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, and Teknik Elektronika, 8(3), 693-705.




DOI: https://doi.org/10.17509/coelite.v2i1.59716

Refbacks

  • There are currently no refbacks.


Journal of Computer Engineering, Electronics and Information Technology (COELITE)


is published by UNIVERSITAS PENDIDIKAN INDONESIA (UPI),
and managed by Department of Computer Enginering.
Jl. Dr. Setiabudi No.229, Kota Bandung, Indonesia - 40154
email: coelite@upi.edu
e-ISSN: 2829-4149
p-ISSN: 2829-4157