Sistem Pintu Gerbang Otomatis Menggunakan Deep Learning Object Detection
DOI:
https://doi.org/10.34818/eoe.v9i6.19154Abstrak
Abstrak—Internet of Things (IoT) merupakan salah satu bentuk perkembangan teknologi yang dapat diterapkan di hampir berbagai bidang pekerjaan atau industri. Dengan adanya IoT, aktivitas manusia dapat dimudahkan terutama dalam hal pengawasan dan pengendalian, selama ada koneksi antara (minimal) dua perangkat. IoT dapat dipadukan dengan berbagai perangkat dan teknologi, salah satunya adalah kamera untuk pendeteksi objek (computer vision). Dalam proyek ini, konsep IoT digunakan untuk kontrol gerbang dengan menggunakan kamera untuk mendeteksi kode QR dan plat nomor kendaraan terdaftar. Proyek ini menggunakan beberapa alat; di antaranya laptop, motor servo, sensor ultrasonik, Rasberry Pi, dan webcam. Dari hasil training dataset, diperoleh confusion matrix untuk mengukur kualitas dataset. Dari confusion matrix, akurasi 90%, presisi 86%, recall 100%, dan F1- score 92%. Quality of Service (QoS) juga diperoleh dari pengiriman data dari Raspberry Pi ke database Firebase; throughput 29,66 kbps, packet loss rata-rata 0%, delay rata-rata 24,244 ms, dan jitter rata-rata 32,3351 ms. Kata kunci—QoS, deteksi objek, dataset, Raspberry Pi, Internet of Things, databaseUnduhan
Referensi
[1] Mathilda Gian Ayu, “Perkembangan dan Penggunaan IoT di Indonesia Tahun 2021 Diprediksi Meningkat,” Cloud Computing Indonesia, 2020. https://www.cloudcomputing.id/berita/perkembangan-dan-penggunaan-iot-di-indonesia.
[2] Y. Zhao, J. Gu, C. Liu, S. Han, Y. Gao, and Q. Hu, “License Plate Location Based on Haar-like Cascade Classifiers and Edges,” Second WRI Glob. Congr. Intell. Syst. 2010 Second WRI Glob. Congr. Intell. Syst. Licens., pp. 2–5, 2010, doi: 10.1109/GCIS.2010.55.
[3] B. Y. Amirgaliyev, K. K. Kuatov, Z. Y. Baibatyr, M. Z. Kairanbay, C. A. Kenshimov, and A. K. Jantassov, “License Plate Verification Method For Automatic License Plate Recognition Systems,” 2015 Twelve Int. Conf. Electron. Comput. Comput., vol. 1, no. 1, pp. 3–5, 2015, doi: 10.1109/ICECCO.2015.7416892.
[4] A. Menon, “Detection And Recognition of Multiple License Plate From Still Images,” 2018 Int. Conf. Circuits Syst. Digit. Enterp. Technol., pp. 1–5, 2018.
[5] Y. Yudhanto, “Apa itu IOT (Internet Of Things) ?,” 2007. [Online]. Available: https://ilmukomputer.org/wp-content/uploads/2015/05/apa-itu-iot-internet-of-things.pdf.
[6] M. Asad, S. Qaisar, and A. Basit, “Client Based Access Layer QoS Provisioning in Beyond 5G IoT Networks,” 2020 3rd Int. Conf. Adv. Commun. Technol. Netw., vol. 1, no. 2, pp. 1–8, 2022, doi: 10.1109/CommNet49926.2020.9199612.
[7] I. O. P. C. Series and M. Science, “Face Mask Detection for Covid-19 Pandemic using Pytorch in Deep Learning,” IOP Conf. Ser. Mater. Sci. Eng., 2021, doi: 10.1088/1757-899X/1070/1/012061.
[8] F. Rofii, G. Priyandoko, M. I. Fanani, and A. Suraji, “Vehicle Counting Accuracy Improvement By Identity Sequences Detection Based on Yolov4 Deep Neural Networks,” Teknik, vol. 42, no. 2, pp. 169–177, 2021, doi: 10.14710/teknik.v42i2.37019.
[9] T. D. Indriasari, M. Sc, F. S. R. S. T, and M. Kom, “Analisis dan Perancangan Layanan Perpustakaan UAJY Berbasis Mobile dengan Memanfaatkan QR Code,” http://e-journal.uajy.ac.id/, vol. 1, no. 1, pp. 1–47, 2012.
[10] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” 2020, [Online]. Available: http://arxiv.org/abs/2004.10934.
[11] G. T. U. A. Colleges et al., “Microsoft COCO: Common Objects in Context,” Eccv, vol. 1, no. 1, pp. 740–755, 2014, doi: 10.48550/arXiv.1405.0312.
[12] Y. Orland Kristiawan, J. Triyono, and P. Haryani, “Membangun Server Portable Berbasis Raspberry Pi Sebagai Media Streaming,” J. JARKOM, vol. 7, no. 1, pp. 35–43, 2019.
[13] A. Kumar and G. Rahul, “IOT based Electrical Device Surveillance and Control System,” 2019 4th Int. Conf. Internet Things Smart Innov. Usages, pp. 1–5, 2019.
[14] N. Seitz, “ITU-T QoS Standards for IP-Based Networks,” no. June, pp. 82–89, 2003.
[15] ITU-T, “G.1010: End-user multimedia QoS Categories,” Int. Telecommun. Union, vol. 1010, 2001, [Online]. Available: http://scholar.google.com.au/scholar?hl=en&q=ITU-T+Recommendation+G.1010&btnG=&as_sdt=1,5&as_sdtp=#7.
[16] J. Page, M. Bain, and F. Mukhlish, “The Risks of Low Level Narrow Artificial Intelligence,” 2018 IEEE Int. Conf. Intell. Saf. Robot., pp. 1–6, 2018.
[17] A. Mackin, F. Zhang, and D. R. Bull, “A Study of High Frame Rate Video Formats,” IEEE Trans. Multimed., vol. PP, pp. 1–14, 2018, doi: 10.1109/TMM.2018.2880603.



