Sistem Deteksi Jenis Kendaraan Metode YOLOv4 Untuk Mendukung Transportasi Cerdas Kota Medan

M Rizky Pramana Putra; Haida Dafitri; Sumi Khairani

doi:10.70340/jirsi.v3i2.125

Penulis

M Rizky Pramana Putra Mahasiswa
Haida Dafitri Universitas Harapan Medan
Sumi Khairani Universitas Harapan Medan

DOI:

https://doi.org/10.70340/jirsi.v3i2.125

Kata Kunci:

YOLOv4, vehicle detection, tracking, traffic, accuracy

Abstrak

This research discusses the evaluation and implementation of the YOLOv4 model in detecting and tracking vehicle types in the context of road traffic. To address the research questions, the study examined the model's performance across various aspects. The results indicate that the YOLOv4 model achieved a Mean Average Precision (mAP) of 77.88% on the training dataset after 7000 iterations. The model exhibits a commendable ability to detect different vehicle types within images, with varying accuracy rates across distinct classes. The developed application within this study can record detection data for every frame within a video sequence, providing crucial information for analyzing vehicle density on roads. Despite its relatively high accuracy level, errors persist in object detection and labeling. In conclusion, this research offers insights into the capabilities and potential of the YOLOv4 model in addressing challenges related to vehicle detection in road traffic, while also identifying areas that warrant further improvement.

Unduhan

Data unduhan belum tersedia.

Referensi

J. Sang et al., “An improved YOLOv2 for vehicle detection,” Sensors (Switzerland), vol. 18, no. 12, 2018, doi: 10.3390/s18124272.

Q. Meng, H. Song, Y. Zhang, X. Zhang, G. Li, and Y. Yang, “Video-Based Vehicle Counting for Expressway: A Novel Approach Based on Vehicle Detection and Correlation-Matched Tracking Using Image Data from PTZ Cameras,” Math. Probl. Eng., vol. 2020, 2020, doi: 10.1155/2020/1969408.

J. B. Kim, “Efficient vehicle detection and distance estimation based on aggregated channel features and inverse perspective mapping from a single camera,” Symmetry (Basel)., vol. 11, no. 10, pp. 8–10, 2019, doi: 10.3390/sym11101205.

S. C. Hsu, C. L. Huang, and C. H. Chuang, “Vehicle detection using simplified fast R-CNN,” 2018 Int. Work. Adv. Image Technol. IWAIT 2018, pp. 1–3, 2018, doi: 10.1109/IWAIT.2018.8369767.

C. S. Asha and A. V Narasimhadhan, “Vehicle Counting for Traffic Management System using YOLO and Correlation Filter,” in 2018 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Mar. 2018, pp. 1–6. doi: 10.1109/CONECCT.2018.8482380.

G. Oltean, C. Florea, R. Orghidan, and V. Oltean, “Towards Real Time Vehicle Counting using YOLO-Tiny and Fast Motion Estimation,” SIITME 2019 - 2019 IEEE 25th Int. Symp. Des. Technol. Electron. Packag. Proc., pp. 240–243, 2019, doi: 10.1109/SIITME47687.2019.8990708.

K. H. Nam Bui, H. Yi, and J. Cho, “A multi-class multi-movement vehicle counting framework for traffic analysis in complex areas using CCTV systems,” Energies, vol. 13, no. 8, 2020, doi: 10.3390/en13082036.

Z. He, Y. Lei, S. Bai, and W. Wu, “Multi-Camera Vehicle Tracking with Powerful Visual Features and Spatial-Temporal Cue,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., p. 10, 2019.

X. F. Gu, Z. W. Chen, T. S. Ma, F. Li, and L. Yan, “Real-Time vehicle detection and tracking using deep neural networks,” 2016 13th Int. Comput. Conf. Wavelet Act. Media Technol. Inf. Process. ICCWAMTIP 2017, pp. 167–170, 2017, doi: 10.1109/ICCWAMTIP.2016.8079830.

R. Watkins, N. Pears, and S. Manandhar, “Vehicle classification using ResNets, localisation and spatially-weighted pooling,” arXiv, 2018.

A. Schumann, L. Sommer, K. Valev, and J. Beyerer, “A systematic evaluation of recent deep learning architectures for fine-grained vehicle classification,” in Pattern Recognition and Tracking XXIX, Apr. 2018, p. 1. doi: 10.1117/12.2305062.

X. Li, Y. Liu, Z. Zhao, Y. Zhang, and L. He, “A deep learning approach of vehicle multitarget detection from traffic video,” J. Adv. Transp., vol. 2018, 2018, doi: 10.1155/2018/7075814.

H. Song, H. Liang, H. Li, Z. Dai, and X. Yun, “Vision-based vehicle detection and counting system using deep learning in highway scenes,” Eur. Transp. Res. Rev., vol. 11, no. 1, 2019, doi: 10.1186/s12544-019-0390-4.

S. Zhang, L. Wen, X. Bian, Z. Lei, and S. Z. Li, “Single-Shot Refinement Neural Network for Object Detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, pp. 4203–4212. doi: 10.1109/CVPR.2018.00442.

K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, “CenterNet: Keypoint triplets for object detection,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2019-Octob, pp. 6568–6577, 2019, doi: 10.1109/ICCV.2019.00667.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, “Focal Loss for Dense Object Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp. 318–327, 2020, doi: 10.1109/TPAMI.2018.2858826.

M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 10691–10700, 2019.

M. Tan, R. Pang, and Q. V. Le, “EfficientDet: Scalable and efficient object detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Nov. 2020, pp. 10778–10787. doi: 10.1109/CVPR42600.2020.01079.

X. Zhang, F. Wan, C. Liu, X. Ji, and Q. Ye, “Learning to Match Anchors for Visual Object Detection,” IEEE Trans. Pattern Anal. Mach. Intell., Sep. 2021, doi: 10.1109/TPAMI.2021.3050494.

P. Mahto, P. Garg, P. Seth, and J. Panda, “Refining Yolov4 for vehicle detection,” Int. J. Adv. Res. Eng. Technol., vol. 11, no. 5, pp. 409–419, 2020, doi: 10.34218/IJARET.11.5.2020.043.

Y. Q. Huang, J. C. Zheng, S. D. Sun, C. F. Yang, and J. Liu, “Optimized YOLOv3 algorithm and its application in traffic flow detections,” Appl. Sci., vol. 10, no. 9, p. 3079, Apr. 2020, doi: 10.3390/app10093079.

L. Ouyang and H. Wang, “Vehicle target detection in complex scenes based on YOLOv3 algorithm,” IOP Conf. Ser. Mater. Sci. Eng., vol. 569, no. 5, 2019, doi: 10.1088/1757-899X/569/5/052018.

X. Wang, S. Wang, J. Cao, and Y. Wang, “Data-Driven Based Tiny-YOLOv3 Method for Front Vehicle Detection Inducing SPP-Net,” IEEE Access, vol. 8, pp. 110227–110236, 2020, doi: 10.1109/ACCESS.2020.3001279.

J. Choi, D. Chun, H. Kim, and H. J. Lee, “Gaussian YOLOv3: An accurate and fast object detector using localization uncertainty for autonomous driving,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2019-Octob, pp. 502–511, 2019, doi: 10.1109/ICCV.2019.00059.

J. Zhu, X. Li, P. Jin, Q. Xu, Z. Sun, and X. Song, “MME-YOLO: Multi-sensor multi-level enhanced yolo for robust vehicle detection in traffic surveillance,” Sensors (Switzerland), vol. 21, no. 1, pp. 1–17, Dec. 2021, doi: 10.3390/s21010027.

B. G. Han, J. G. Lee, K. T. Lim, and D. H. Choi, “Design of a scalable and fast yolo for edge-computing devices,” Sensors (Switzerland), vol. 20, no. 23, pp. 1–15, Nov. 2020, doi: 10.3390/s20236779.

F. Wu, G. Jin, M. Gao, Z. He, and Y. Yang, “Helmet detection based on improved YOLO V3 deep model,” Proc. 2019 IEEE 16th Int. Conf. Networking, Sens. Control. ICNSC 2019, pp. 363–368, 2019, doi: 10.1109/ICNSC.2019.8743246.

R. Wei, N. He, and K. Lu, “YOLO-mini-tiger: Amur tiger detection,” in ICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval, 2020, pp. 517–524. doi: 10.1145/3372278.3390710.

J. Zhou, Y. Tian, C. Yuan, K. Yin, G. Yang, and M. Wen, “Improved UAV opium poppy detection using an updated YOLOV3 model,” Sensors (Switzerland), vol. 19, no. 22, pp. 1–23, 2019, doi: 10.3390/s19224851.

Y. Lai, F. Sun, and H. Liu, “Small Object Detection Base on YOLOv3 for Pedestrian Recognition,” in 2020 5th International Conference on Control and Robotics Engineering, ICCRE 2020, 2020, pp. 235–241. doi: 10.1109/ICCRE49379.2020.9096492.

Á. Arcos-García, J. A. Álvarez-García, and L. M. Soria-Morillo, “Evaluation of deep neural networks for traffic sign detection systems,” Neurocomputing, vol. 316, pp. 332–344, 2018, doi: 10.1016/j.neucom.2018.08.009.

R. Laroca, L. A. Zanlorensi, G. R. Gonçalves, E. Todt, W. R. Schwartz, and D. Menotti, “An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector,” arXiv, Sep. 2019.

A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv. 2020.