Implementasi Sistem Identifikasi Senjata Real Time Menggunakan YOLOv7 dan Notifikasi Chat Telegram
- Muhammad Rizqi Sholahuddin Politeknik Negeri Bandung, Bandung Barat, Indonesia
-
Firas Atqiya
*
Universitas Muhammadiyah Bandung, Bandung,
Indonesia
- Sri Ratna Wulan Politeknik Negeri Bandung, Bandung Barat, Indonesia
- Maisevli Harika Politeknik Negeri Bandung, Bandung Barat, Indonesia
- Sofy Fitriani Politeknik Negeri Bandung, Bandung Barat, Indonesia
- Yusuf Sofyan Politeknik Negeri Bandung, Bandung Barat, Indonesia (*) Corresponding Author
Abstract
This research produces an application that can send automatic notifications in the form of a chat on the Telegram platform when a weapon object is detected on CCTV. This application was created utilizing computer vision technology and artificial intelligence, in particular YOLOv7. As demonstrated by the mAP@0.5 value of 0.837 after 50 epochs of training, this application can detect weapon objects such as people, pistols, and knives with a reasonable degree of accuracy. This application is also linked to the telepot library, which enables it to send chats on the Telegram platform. These applications can aid in enhancing security and safety in a variety of environments and have numerous practical applications in fields such as public safety, law enforcement, and others. However, there are still deficiencies in this study that can be addressed in future research, such as the small number of training epochs and the size of the dataset.
Downloads
References
S. Megawan, W. S. Lestari, and A. Halim, “Deteksi Non-Spoofing Wajah pada Video secara Real Time Menggunakan Faster R-CNN,” J. Inf. Syst. Res. JOSH, vol. 3, no. 3, Apr. 2022, [Online]. Available: https://ejurnal.seminar-id.com/index.php/josh/article/view/1519
F. Atqiya, N. Ihsani, M. R. Sholahuddin, F. M. Dwivany, and S. Suhandono, “Segmentasi Citra Digital Objek Hasil Pengamatan In Situ Localization Gen gfp pada Tanaman Transforman,” Edsence J. Pendidik. Multimed., vol. 1, no. 2, pp. 53–60, Dec. 2019, doi: 10.17509/edsence.v1i2.21575.
I. A. Dahlan, D. Ariateja, M. A. Arghanie, M. A. Versantariqh, M. David, and U. D. Fatmawati, “Sistem Deteksi Senjata Otomatis Menggunakan Deep Learning Berbasis CCTV Cerdas,” J. Sist. Cerdas, vol. 4, no. 2, pp. 126–141, Aug. 2021, doi: 10.37396/jsc.v4i2.172.
R. Ivandhani, I. I. Tritoasmoro, and N. Ibrahim, “Perancangan dan Implementasi Sistem Deteksi Manusia Menggunakan Citra Webcam Dengan Fitur Notifikasi pada Ponsel,” in eProceedings of Engineering, vol. 7, pp. 3877–3883. [Online]. Available: https://openlibrarypublications.telkomuniversity.ac.id/index.php/engineering/article/view/12940/12625#
M. Harika, D. R. Ramdania, S. Rahmadika, N. A. Suwastika, and G. G. A. Delilah, “Designing R-CNN Algorithm to Detect Halal Composition of Korean Food and Beverages,” in 2022 8th International Conference on Wireless and Telematics (ICWT), Yogyakarta, Indonesia, Jul. 2022, pp. 1–5. doi: 10.1109/ICWT55831.2022.9935428.
M. Abdul Hadi, R. Ferdian, and L. Arief, “Klasifikasi Tingkat Ancaman Kriminalitas Bersenjata Menggunakan Metode You Only Look Once (YOLO),” CHIPSET, vol. 2, no. 01, pp. 33–40, Apr. 2021, doi: 10.25077/chipset.2.01.33-40.2021.
R. Olmos, S. Tabik, and F. Herrera, “Automatic handgun detection alarm in videos using deep learning,” Neurocomputing, vol. 275, pp. 66–72, Jan. 2018, doi: 10.1016/j.neucom.2017.05.012.
M. R. Sholahuddin and F. Atqiya, “Sistem Tanya Jawab Konsultasi Shalat Berbasis RASA Natural Language Understanding (NLU),” J. Pendidik. Multimed. Edsence, vol. 3, no. 2, pp. 93–102, Dec. 2021, doi: 10.17509/edsence.v3i2.38732.
A. Mahmudi, “Deteksi Senjata Tajam dengan Metode Haar Cascade Classifier Menggunakan Teknologi SMS Gateway,” MATICS, vol. 1, no. 1, Mar. 2014, doi: 10.18860/mat.v1i1.2646.
I. Romadhanti, I. Kurniastuti, and T. D. Wulan, “Pemrosesan Citra Kuku Jari Tangan Menggunakan Metode GLCM (Grey Level Co-Occurrence Matrix),” Natl. Conf. UMMAH NCU 2020, vol. 1, no. 1, Jan. 2021, Accessed: Dec. 28, 2022. [Online]. Available: https://conferences.unusa.ac.id/index.php/NCU2020/article/view/658
J. Pustejovsky and A. Stubbs, Natural Language Annotation for Machine Learning, 3rd ed. O’Reilly Media, 2013.
E. Mozef, “Algoritma Labeling Citra Biner dengan Performansi Optimal Processor-Time,” J. Inform., vol. 5, no. 2, pp. 67–77, Mar. 2005, doi: 10.9744/informatika.5.2.pp.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.” arXiv, Jul. 06, 2022. Accessed: Dec. 22, 2022. [Online]. Available: http://arxiv.org/abs/2207.02696
G. Shobha and S. Rangaswamy, “Machine Learning,” in Handbook of Statistics, vol. 38, Elsevier, 2018, pp. 197–228. doi: 10.1016/bs.host.2018.07.004.
N. Workspace, “3clase Dataset,” Roboflow Universe. Roboflow, Jul. 2022. [Online]. Available: https://universe.roboflow.com/new-workspace-bjaa4/3clase
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Implementasi Sistem Identifikasi Senjata Real Time Menggunakan YOLOv7 dan Notifikasi Chat Telegram
Pages: 598-606
Copyright (c) 2023 Muhammad Rizqi Sholahuddin, Firas Atqiya, Sri Ratna Wulan, Maisevli Harika, Sofy Fitriani, Yusuf Sofyan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
