IMPLEMENTASI OBJECT RECOGNITION PADA RAMBU-RAMBU DAN LAMPU LALU LINTAS DENGAN RASPBERRY PI DENGAN ALGORITMA YOLOV5
DOI:
https://doi.org/10.46984/sebatik.v26i2.2047Keywords:
ADAS, YOLOv5, Traffic Light, Traffic Lamp, Rekognisi Objek, Raspberry PiAbstract
Salah satu teknologi yang saat ini berkembang pesat khususnya untuk mendukung mobil otonom adalah fitur ADAS (Advanced Driver Assistance System). Salah satu fitur sistem ADAS yaitu kemampuan untuk mendeteksi dan mengenali rambu-rambu lalu lintas. Dalam penelitian ini akan dikembangkan dan diimplementasikan sistem pendeteksi lambu dan rambu lalu lintas berbasis kecerdasan buatan. Algoritma yang digunakan dalam penelitian ini yaitu dengan algoritma YOLO (You Only Look Once) versi 5. Sistem kecerdasan buatan ini akan diimplementasikan dalam perangkat Raspberry Pi yang dilengkapi dengan webcam dan speaker. Total jenis rambu yang digunakan sejumlah 12 jenis rambu lalu lintas dengan masing-masing data citra yang diolah sejumlah 100 data. Jenis rambu dan lampu lalu lintas yang diklasifikasikan meliputi : belok kanan, belok kiri, dilarang belok kanan, dilarang belok kiri, dilarang putar balik, dilarang berhenti, dilarang parkir, lampu merah, lampu hijau, lampu kuning, dan putar balik. Dilakukan variasi ukuran gambar dari 320x320, 416x416 dan 480x480, serta dilakukan variasi jumlah training yaitu 50, 100, 250 dan 500 epoch untuk mendapatkan nilai akurasi yang paling optimal. Didapatkan hasil yang optimal dengan ukuran gambar 320x320 pixel dan dengan jumlah training sejumlah 50 epoch. Dari hasil training didapatkan mAP (mean Average Precision) sebesar 89,50%, di mana ketika dilakukan pengujian gambar lampu dan rambu lalu lintas didapatkan ketepatan sebesar 88,88%. Sistem mampu diimplementasikan dalam perangkat Raspberry Pi 4 dan dipasang di mobil dan mampu berjalan dengan baik.
References
Ansor, A., & Afrianto, Y. (2020). Mask Detection Using Framework Tensorflow and Pre-Trained CNN Model Based on Raspberry Pi. Jurnal Mantik, 4(3), 1539–1545. https://iocscience.org/ejournal/index.php/mantik
Asmara, R. A., Syahputro, B., Supriyanto, D., & Handayani, A. N. (2020). Prediction of traffic density using yolo object detection and implemented in raspberry pi 3b + and intel ncs 2. 4th International Conference on Vocational Education and Training, ICOVET 2020, 391–395. https://doi.org/10.1109/ICOVET50258.2020.9230145
Bansal, P., & Kockelman, K. M. (2018). Are we ready to embrace connected and self-driving vehicles? A case study of Texans. Transportation, 45(2), 641-675.
Cengil, E., & Çinar, A. (2021). Poisonous Mushroom Detection using YOLOV5. Dalam Turkish Journal of Science & Technology (Vol. 16, Issue 1).
Chrisdwianto, T. O., Fitriyah, H., & Widasari, E. R. (2018). Perancangan Sistem Deteksi dan Pengenalan Rambu Peringatan Menggunakan Metode Template Matching. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 2(3), 1265–1274. http://j-ptiik.ub.ac.id
Dewi, C., Chen, R. C., & Tai, S. K. (2020). Evaluation of robust spatial pyramid pooling based on convolutional neural network for traffic sign recognition system. Electronics (Switzerland), 9(6). https://doi.org/10.3390/electronics9060889
Du, J. (2018, April). Understanding of object detection based on CNN family and YOLO. Di Journal of Physics: Conference Series (Vol. 1004, No. 1, p. 012029). IOP Publishing.
Geirhos, R., Janssen, D. H., Schütt, H. H., Rauber, J., Bethge, M., & Wichmann, F. A. (2017). Comparing deep neural networks against humans: object recognition when the signal gets weaker. arXiv preprint arXiv:1706.06969.
Hasibuan, N. N., Zarlis, M., & Efendi, S. (2021). Detection and tracking different type of cars with YOLO model combination and deep sort algorithm based on computer vision of traffic controlling. Jurnal Dan Penelitian Teknik Informatika, 6(1). https://doi.org/10.33395/sinkron.v6i1.11231
Ismail, S. (2019). Analisis Probabilitas Pengemudi Mobil Melakukan Driving Distractions di Kota Medan.
Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., & Chen, Y. (2017). Ron: Reverse connection with objectness prior networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5936-5944).
Krishnaveni, P., & Sutha, J. (2020). Novel deep learning framework for broadcasting abnormal events obtained from surveillance applications. Journal of Ambient Intelligence and Humanized Computing, 1-15.
Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988).
Liu, C., Li, S., Chang, F., & Wang, Y. (2019). Machine Vision Based Traffic Sign Detection Methods: Review, Analyses and Perspectives. IEEE Access, 7, 86578–86596. https://doi.org/10.1109/ACCESS.2019.2924947
Luo, H., Kong, Q., & Wu, F. (2018). Traffic Sign Image Synthesis withGenerative Adversarial Networks. 2018 24th International Conference on Pattern Recognition (ICPR)., 2540–2545.
Mohd-Isa, W. N., Abdullah, M. S., Sarzil, M., Abdullah, J., Ali, A., & Hashim, N. (2020, Oktober 26). Detection of Malaysian Traffic Signs via Modified YOLOv3 Algorithm. 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020. https://doi.org/10.1109/ICDABI51230.2020.9325690
M.R., S., Ghate R, G., Khan, F., & S., H. (2019). Object Detection and Human Identification using Raspberry Pi. ICAIT - 2019 : First IEEE International Conference on Advances in Information Technology : Proceedings : 24th - 27th July 2019.
Novak, B., Ilić, V., & Pavković, B. (2020). YOLOv3 Algorithm with additional convolutional neural network trained for traffic sign recognition. 2020 Zooming Innovation in Consumer Technologies Conference, ZINC 2020, 165–168. https://doi.org/10.1109/ZINC50678.2020.9161446
Rahmad, C., Rahmah, I. F., & Asmara, R. A. (2017). Deteksi dan Pengenalan Rambu Lalu Lintas di Indonesia Menggunakan RGBN dan Gabor. SENTRINOV, 13–22.
Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. IEEE Conference on Computer Vision and Pattern Recognition, 7263–7271. http://pjreddie.com/yolo9000/
Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell, 39(6), 1–9. https://github.com/
Sitanggang, O. R., Fitriyah, H., & Utaminingrum, F. (2018). Sistem Deteksi dan Pengenalan Jenis Rambu Lalu Lintas Menggunakan Metode Shape Detection Pada Raspberry Pi. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 2(12), 6108–6117. http://j-ptiik.ub.ac.id
Sonntag, D., Barz, M., Zacharias, J., Stauden, S., Rahmani, V., Fóthi, Á., & Lőrincz, A. (2017). Fine-tuning deep cnn models on specific ms coco categories. arXiv preprint arXiv:1709.01476.
Triyadi, A., & Utaminingrum, F. (2020). Pengembangan Sistem Rekognisi Rambu Kecepatan Menggunakan Circle Hough Transform dan Convolutional Neural Network Berbasis Raspberry Pi. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 2(1), 56–64. http://j-ptiik.ub.ac.id
Wang, Q., Zhang, Q., Liang, X., Wang, Y., Zhou, C., & Mikulovich, V. I. (2022). Traffic lights detection and recognition method based on the improved yolov4 algorithm. Sensors, 22(1). https://doi.org/10.3390/s22010200
Yu, Y., Sun, Y., Zhao, C., & Qu, C. (2021). Research on Defect Detection of Electric Energy Metering Box Based on YOLOv5. Journal of Physics: Conference Series, 2087(1). https://doi.org/10.1088/1742-6596/2087/1/012081
Downloads
Published
How to Cite
Issue
Section
License
Authors retain all their rights to the published works, such as (but not limited to) the following rights; Copyright and other proprietary rights relating to the article, such as patent rights, The right to use the substance of the article in own future works, including lectures and books, The right to reproduce the article for own purposes, The right to self-archive the article
