skip to main content

Peningkatan Akurasi Penghitungan Jumlah Kendaraan dengan Membangkitkan Urutan Identitas Deteksi Berbasis Yolov4 Deep Neural Networks

Vehicle Counting Accuracy Improvement By Identity Sequences Detection Based on Yolov4 Deep Neural Networks

*Faqih Rofii orcid scopus  -  Teknik Elektro, Fakultas Teknik, Universitas Widyagama Malang, Indonesia
Gigih Priyandoko orcid scopus  -  Teknik Elektro, Fakultas Teknik, Universitas Widyagama Malang, Indonesia
Muhammad Ifan Fanani  -  Teknik Elektro, Fakultas Teknik, Universitas Widyagama Malang, Indonesia
Aji Suraji  -  Teknik Sipil, Fakultas Teknik, Universitas Widyagama Malang, Indonesia
Open Access Copyright (c) 2021 TEKNIK

Citation Format:
Abstract
Models for vehicle detection, classification, and counting based on computer vision and artificial intelligence are constantly evolving. In this study, we present the Yolov4-based vehicle detection, classification, and counting model approach. The number of vehicles was calculated by generating the serial number of the identity of each vehicle. The object is detected and classified, marked by the display of bounding boxes, classes, and confidence scores. The system input is a video dataset that considers the camera position, light intensity, and vehicle traffic density. The method has counted the number of vehicles: cars, motorcycles, buses, and trucks. Evaluation of model performance is based on accuracy, precision, and total recall of the confusion matrix. The results of the dataset test and the calculation of the model performance parameters had obtained the best accuracy, precision. Total recall values when the model testing was carried out during the day where the camera position was at the height of 6 m and the loss of 500 was 83%, 93%, and 94%. Meanwhile, the lowest total accuracy, precision, and recall were obtained when the model was tested at night. The camera position was at the height of 1.5 m, and 900 losses were 68%, 77%, and 78%.
Fulltext View|Download
Keywords: detection and classification; vehicles counting; Yolov4; deep neural networks; accuracy

Article Metrics:

  1. Adistya, R., & Muslim, M. A. (2016). Deteksi Dan Klasifikasi Kendaraan Menggunakan Algoritma Backpropagation Dan Sobel. Journal of Mechanical Engineering and Mechatronics 1(02), 282312
  2. Antony, J. J., & Suchetha, M (2016). Vision Based Vehicle Detection: A Literature Review. International Journal of Applied Engineering Research 11(5):3128–33
  3. Badan Pusat Statistik (n.d.). Perkembangan Jumlah Kendaraan Bermotor Menurut Jenis, 1949-2018. Retrieved November 23, 2020 ( https://www.bps.go.id/linkTableDinamis/view/id/1133)
  4. Balid, Walid, Tafish, H., & Refai, H. H. (2017). Intelligent Vehicle Counting and Classification Sensor for Real-Time Traffic Surveillance. IEEE Transactions on Intelligent Transportation Systems 19(6):1784–94
  5. Bochkovskiy, A., Wang, C., & Liao, H. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. ArXiv:2004.10934 [Cs, Eess]
  6. Gomaa, A., Abdelwahab, M. M., Abo-Zahhad, M., Minematsu, T., & Taniguchi, R. (2019). Robust Vehicle Detection and Counting Algorithm Employing a Convolution Neural Network and Optical Flow. Sensors 19(20):4588
  7. Kim, J., Sung, J., & Park, S. (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
  8. Mahto, Pooja and Garg, Priyamm and Seth, Pranav and Panda, J, Refining Yolov4 for Vehicle Detection (June 16, 2020). International Journal of Advanced Research in Engineering and Technology (IJARET), 11(5), 2020, pp. 409-419., Available at SSRN: https://ssrn.com/abstract=3628439
  9. Manajang, D., Sompie, S. R. U. A., & Jacobus, A.(2020). Implementasi Framework Tensorflow Object Detection API Dalam Mengklasifikasi Jenis Kendaraan Bermotor. Jurnal Teknik Informatika 15(3):171–78
  10. Mashudi, A., Rofii, F., & Mukhsim, M. (2020). Sistem Kamera Cerdas Untuk Deteksi Pelanggaran Marka Jalan. JASEE Journal of Application and Science on Electrical Engineering 1(01):15–25
  11. Rachmawati, F., & Widhyaestoeti, D. (2020) Deteksi Jumlah Kendaraan Di Jalur SSA Kota Bogor Menggunakan Algoritma Deep Learning YOLO. Prosiding LPPM UIKA BOGOR
  12. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.(2016). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE conference on computer vision and pattern recognition, 779–88
  13. Redmon, J. (2016). Darknet: open source neural networks in C. 2013–2016. URL http://pjreddie. com/darknet
  14. Setyawan, G. E., Adiwijaya, B., & Fitriyah, H. (2019). Sistem Deteksi Jumlah, Jenis Dan Kecepatan Kendaraan Menggunakan Analisa Blob Berbasis Raspberry Pi. Jurnal Teknologi Informasi Dan Ilmu Komputer (JTIIK) 6(2)
  15. Wang, H., Yu, Y., Cai, Y., Chen, Xi., Chen, L., & Liu, Q.(2019). A Comparative Study of State-of-the-Art Deep Learning Algorithms for Vehicle Detection. IEEE Intelligent Transportation Systems Magazine 11(2):82–95
  16. Wibowo, D. W., Muslim, M. A., & Sarosa, M. (2014). Perhitungan Jumlah Dan Jenis Kendaraan Menggunakan Metode Fuzzy C-Means Dan Segmentasi Deteksi Tepi Canny. Jurnal EECCIS 7(2):103–10
  17. Yuniarto, A. (2008). Deteksi Kepadatan Lalu Lintas Menggunakan Sensor Ultrasonik Pada Persimpangan Jalan Berbasis Mikrokontroller. PhD Thesis, Universitas Muhammadiyah Surakarta

Last update:

No citation recorded.

Last update:

No citation recorded.