Implementasi Teknologi Mediapipe Menggunakan Metode CNN Berbasis Website Untuk Pengamanan VVIP Dalam Mobil

Authors

  • M. Ilham AlFatrah Universitas Pertahanan Republik Indonesia Author
  • Hery Sudaryanto Universitas Pertahanan Republik Indonesia Author
  • H. A. Danang Rimbawa Universitas Pertahanan Republik Indonesia Author

DOI:

https://doi.org/10.5281/zenodo.16734263

Keywords:

Keamanan VVIP, MediaPipe, CNN, Deteksi Gestur, Pengawasan Real-Time

Abstract

Penelitian ini bertujuan mengembangkan sistem deteksi gestur tangan berbasis MediaPipe dan Convolutional Neural Network (CNN) guna meningkatkan efektivitas pengamanan VVIP. Mengingat ancaman modern yang semakin kompleks, sistem ini dirancang untuk mendeteksi gestur darurat secara real-time dan memungkinkan respons cepat. Metodologi yang digunakan meliputi pengumpulan dataset gestur tangan, anotasi data menggunakan MediaPipe, dan pelatihan model CNN di Google Colab. Kinerja model dievaluasi dengan metrik akurasi, presisi, recall, dan F1-score. Pengujian juga dilakukan dalam berbagai kondisi, seperti pencahayaan rendah dan gerakan cepat, untuk menilai ketangguhan sistem di dunia nyata. Hasilnya, sistem ini berhasil mendeteksi gestur tangan darurat dengan akurasi tinggi dan kecepatan kurang dari satu detik. Kinerja optimal, dengan akurasi mendekati 100%, tercapai pada kondisi pencahayaan yang baik. Meskipun akurasi sedikit menurun pada kondisi ekstrem, integrasi sistem pada platform website memungkinkan pengawasan dan pengambilan keputusan cepat di pusat komando. Penelitian ini membuktikan bahwa kombinasi MediaPipe dan CNN adalah solusi inovatif, namun optimasi lebih lanjut tetap dibutuhkan.

Downloads

Download data is not yet available.

References

Arinuryadi, M. (2018). Pengembangan model pengamanan VVIP berbasis teknologi informasi dan komunikasi untuk mendukung keamanan nasional. (Disertasi doktoral, Universitas Pertahanan).

Chen, Y., Li, S., & Wang, Q. (2022). The role of artificial intelligence in modern security systems. Journal of Cybernetics and Information Technology, 18(3), 45-60.

Ganaie, M. A., & Hu, M. (2022). A review on convolutional neural networks for computer vision. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(8), 4890-4905.

Guo, H., Li, X., & Chen, Y. (2022). Real-time anomaly detection in surveillance videos using deep learning and attention mechanisms. Journal of Computer Security, 40(3), 456–472.

Indriani, F., Putra, I. D. G., & Wibawa, I. K. A. (2021). Penerapan MediaPipe Hand Landmark untuk pengenalan gestur tangan pada aplikasi panduan digital. Jurnal Ilmiah Komputer dan Informasi, 14(2), 1–8.

Jilidi, A., Ben Messaoud, M., & Amine, A. (2024). Emergency hand gesture recognition using convolutional neural networks for smart surveillance systems. International Journal of Computer Vision and Signal Processing, 12(1), 15-28.

Khodadin, A., & Pudaruth, S. (2020). Smart surveillance system for VVIP protection using artificial intelligence. International Journal of Computer Networks and Communications Security, 8(1), 1–8.

Kim, J., & Lee, S. (2021). AI-based threat detection system for VVIP protection. International Journal of Security Technology, 10(2), 112–125.

Kulkarni, A. P., & Shinde, M. (2023). A comprehensive review on image augmentation techniques for deep learning models. International Journal of Computer Science and Engineering, 11(2), 115-128.

Li, J., Chen, Y., & Zhang, W. (2021). An intelligent surveillance system for proactive threat detection in VVIP security. Journal of Cybersecurity and Information Management, 15(4), 211-225.

Lugaresi, C., Tiao, C., & Lee, W. S. (2019). MediaPipe: A cross-platform framework for building multimodal applied machine learning pipelines. arXiv preprint arXiv:1906.05220.

Marianna, L. (2024). Vision transformers for image recognition: A survey of recent advances. International Journal of Computer Vision and Image Processing, 14(1), 45–60.

Pinar, A., & Aksoy, S. (2022). A comparative study of image preprocessing techniques for improved object detection. Journal of Applied Machine Learning, 5(1), 34-45.

Pulli, K., Baksheev, A., Kornyakov, V., & Eruhimov, V. (2012). Real-time computer vision with OpenCV. Communications of the ACM, 55(1), 105–112. https://doi.org/10.1145/2184319.2184337

Singh, B., & Singh, P. (2021). Dataset splitting and cross-validation techniques for machine learning models. Journal of Data Science and Analytics, 9(4), 211-225.

Wameed, A. H., Al-Mansoori, M. F., & Al-Samarraie, A. (2023). Hand gesture control of a robotic arm using MediaPipe: A comparative study. Journal of Robotics and Control, 4(2), 112-120.

Wang, T., Zhang, Y., & Li, J. (2023). A real-time sign language recognition system based on MediaPipe and deep learning. Journal of Artificial Intelligence Research, 35(1), 78–92.

Zhang, S., Li, H., & Liu, Q. (2020). Pose and gesture detection with MediaPipe for human-computer interaction. Proceedings of the 2020 International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 123-130.

Zhou, Q., & Lv, P. (2023). Real-time gesture recognition using MediaPipe and convolutional neural networks. Journal of Image and Video Processing, 32(4), 1-10.

SITEKNIK Vol. 2 No. 3 (2025): July

Downloads

Published

31-07-2025

Issue

Vol. 2 No. 3 (2025): July

Section

Articles

License

Copyright (c) 2025 M. Ilham AlFatrah, Hery Sudaryanto, H. A. Danang Rimbawa (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Implementasi Teknologi Mediapipe Menggunakan Metode CNN Berbasis Website Untuk Pengamanan VVIP Dalam Mobil. (2025). SITEKNIK: Sistem Informasi, Teknik Dan Teknologi Terapan, 2(3), 260-371. https://doi.org/10.5281/zenodo.16734263

Share

Similar Articles

You may also start an advanced similarity search for this article.