Deep Learning-Based Vehicle Type Detection and Classification

9b59f5bc-a7f6-47dc-93e3-45894e29a53b20230602092340094wseas:wseasmdt@crossref.orgMDT DepositInternational Journal of Computational and Applied Mathematics & Computer Science2769-247710.37394/232028https://wseas.com/journals/camcs/index.php41020234102023310.37394/232028.2023.3https://wseas.com/journals/camcs/2023.phpDeep Learning-Based Vehicle Type Detection and ClassificationNadinPethiyagodaDepartment of Computer Engineering General Sir John Kotelawala Defence Univerity 10390, Ratmalana, SRI LANKAMwpMadurangaDepartment of Computer Engineering General Sir John Kotelawala Defence Univerity 10390, Ratmalana, SRI LANKADmrKulasekaraDepartment of Computer Engineering General Sir John Kotelawala Defence Univerity 10390, Ratmalana, SRI LANKATlWeerawardaneDepartment of Computer Engineering General Sir John Kotelawala Defence Univerity 10390, Ratmalana, SRI LANKAModern intelligent transportation systems heavily rely on vehicle-type classification technology. Deep learning-based vehicle-type categorization technology has sparked growing concern as image processing, pattern recognition, and deep learning have all advanced. Over the past few years, convolutional neural work, in particular You Only Look Once (YOLO), has shown to have considerable advantages in object detection and image classification. This method speeds up detection because it can predict objects in real time. High accuracy: The YOLO prediction method produces accurate results with low background errors. YOLO also understands generalized object representation. This approach, which is among the best at object detection, outperforms R-CNN approaches by a wide margin. In this paper, YOLOv5 is used to demonstrate vehicle type detection; the YOLOv5m model was chosen since it suits mobile deployments, the model was trained with a dataset of 3000 images, where 500 images were allocated for each class with a variety of vehicles. Hyperparameter tuning was applied to optimize the model for better prediction and accuracy. Experimental results for a batch size of 32 trained for 300 epochs show a precision of 98.2%, recall of 94.9%, mAP@.5 of 97.9%, mAP@.5:.95 of 92.8%, and overall accuracy of 95.3% trained and tested on four vehicle classes.62202362202318263https://wseas.com/journals/camcs/2023/a06camcs-003(2023).pdf10.37394/232028.2023.3.3https://wseas.com/journals/camcs/2023/a06camcs-003(2023).pdf10.1109/icitbs.2019.00010Lin, M. Zhao, X. (2019) ‘Application Research of Neural Network in Vehicle Target Recognition and Classification’, 2019 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), 5–8. doi: 10.1109/ICITBS.2019.00010. 10.1109/icce-asia49877.2020.9277040Kim, J.-A., Sung, J.-Y. και Park, S.-H. (2020) ‘Comparison of Faster-RCNN, YOLO, and SSD for Real-Time Vehicle Type Recognition’, 2020 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), 1–4. doi: 10.1109/ICCEAsia49877.2020.9277040. 10.1109/icpics50287.2020.9202376Yang, Y. (2020) ‘Realization of Vehicle Classification System Based on Deep Learning’, 2020 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS), 308–311. doi: 10.1109/ICPICS50287.2020.9202376. 10.1109/conecct.2018.8482366Aishwarya, C. N., Mukherjee, R. Mahato, D. K. (2018) ‘Multilayer vehicle classification integrated with single frame optimized object detection framework using CNN based deep learning architecture’, 2018 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). 1–6. doi: 10.1109/CONECCT.2018.8482366. 10.1109/gcce50665.2020.9291978Htet, K. S. Sein, M. M. (2020) ‘Event Analysis for Vehicle Classification using Fast RCNN’, 2020 IEEE 9th Global Conference on Consumer Electronics (GCCE), 403–404. doi: 10.1109/GCCE50665.2020.9291978. 10.5815/ijigsp.2022.03.05MWP Maduranga, Dilshan Nandasena, "Mobile-Based Skin Disease Diagnosis System Using Convolutional Neural Networks (CNN)", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.14, No.3, pp. 47- 57, 2022.DOI: 10.5815/ijigsp.2022.03.05 10.1109/kse50997.2020.9287483Doan, T.-N. Truong, M.-T. (2020) ‘Realtime vehicle detection and counting based on YOLO and DeepSORT’, 2020 12th International Conference on Knowledge and Systems Engineering (KSE), 67–72. doi: 10.1109/KSE50997.2020.9287483. 10.1109/iwssip.2018.8439406Roecker, M. N. (2018) ‘Automatic Vehicle type Classification with Convolutional Neural Networks’, 2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP), 1–5. doi: 10.1109/IWSSIP.2018.8439406. 10.1109/eiconcit50028.2021.9431863Harianto, R. A., Pranoto, Y. M. Gunawan, T. P. (2021) ‘Data Augmentation and Faster RCNN Improve Vehicle Detection and Recognition’, 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), 128–133. doi: 10.1109/EIConCIT50028.2021.9431863. 10.1109/ccoms.2019.8821689Maungmai, W. Nuthong, C. (2019) ‘Vehicle Classification with Deep Learning’, 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS), 294–298. doi: 10.1109/CCOMS.2019.8821689. Wang, X. (2019) ‘Real-time vehicle type classification with deep convolutional neural networks, Journal of Real-Time Image Processing, 16(1), 5–14. doi: 10.1007/s11554-017-0712-5. 10.1109/i2cacis.2018.8603700San, W. J., Lim, M. G. Chuah, J. H. (2018) ‘Efficient Vehicle Recognition and Classification using Convolutional Neural Network’, 2018 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), 117–122. doi: 10.1109/I2CACIS.2018.8603700. 10.1109/cvpr.2016.91Redmon, J. (2015) ‘You Only Look Once: Unified, Real-Time Object Detection’, CoRR, abs/1506.02640. http://arxiv.org/abs/1506.02640. 10.1109/ic3iot53935.2022.9767991W. T. S. Wickramanayake, P. K. T. V. Kumararathhe, U. G. B. A. Jayashan and M. Maduranga, "ParkMate: An Image Processing Based Automated Car Parking System," 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), 2022, pp. 1-5, doi: 10.1109/IC3IOT53935.2022.9767991. Redmon, J. Farhadi, A. (2018) ‘YOLOv3: An Incremental Improvement’, CoRR, abs/1804.02767. http://arxiv.org/abs/1804.02767. Bochkovskiy, A., Wang, C.-Y. και Liao, H.-Y. M. (2020) ‘YOLOv4: Optimal Speed and Accuracy of Object Detection’, CoRR, abs/2004.10934. https://arxiv.org/abs/2004.10934. 10.1109/cac.2017.8243078Chen, Y. (2017) ‘Vehicle type classification based on convolutional neural network’, 2017 Chinese Automation Congress (CAC), 1898–1901. doi: 10.1109/CAC.2017.8243078. 10.1109/icoiact50329.2020.9332047Armin, E. U., Bejo, A. Hidayat, R. (2020) ‘Vehicle Type Classification in Surveillance Image based on Deep Learning Method’, 2020 3rd International Conference on Information and Communications Technology (ICOIACT), 400–404. doi: 10.1109/ICOIACT50329.2020.9332047. Jocher, G., 2020. GitHub - ultralytics/yolov5: YOLOv5 in PyTorch > ONNX > CoreML > TFLite. [online] GitHub. Available at: <https://github.com/ultralytics/yolov5> [Accessed 23 June 2022].