Pengembangan Real-Time Object Detection System pada Perangkat Single-Board Computer
DOI:
https://doi.org/10.30865/klik.v4i2.1224Keywords:
Real-Time Object Detection; Raspberry Pi; TensorFlow Lite; Embedded Systems; Computer VisionAbstract
Technological developments in the field of artificial intelligence have opened the door to increasingly sophisticated applications in visual analysis and object detection. This research aims to implement a real-time object detection system using a Raspberry Pi device, a low-power Single Board Computer (SBC) based device with limited hardware resources. We used TensorFlow Lite, a lightweight version of the TensorFlow deep learning framework, to run object detection models on a Raspberry Pi. Our system is powered by a USB web cam as an image source. The research results show that the Raspberry Pi is able to carry out real-time object detection well, with adequate resource usage efficiency. The system built is able to perform better classification, which shows a better detection speed from using TensorFlow Lite, compared to using TensorFlow. Although there are constraints in terms of detection speed depending on the complexity of the model and the number of objects, these results open up great opportunities for the use of embedded devices in various applications such as security monitoring and image analysis. This study also emphasizes the importance of model optimization to achieve the best performance on low-power devices
Downloads
References
I. Muslem, “Prototype Kunci RFID (Radio Frequency Identification) dalam Meningkatkan Keamanan Kendaraan Bermotor,” JURNAL TIKA, vol. 5, no. 3, 2021, doi: 10.51179/tika.v5i3.104.
Ferdinand Louis, M. Ficky Duskarnaen, and Hamidillah Ajie, “UJI KECEPATAN RASPBERRY PI SEBAGAI PRIVATE CLOUD STORAGE UNTUK SMALL OFFICE HOME OFFICE: DENGAN STUDI KASUS DI UPT TIK,” PINTER?: Jurnal Pendidikan Teknik Informatika dan Komputer, vol. 5, no. 2, 2021, doi: 10.21009/pinter.5.2.7.
W. Najib, S. Sulistyo, and Widyawan, “Tinjauan Ancaman dan Solusi Keamanan pada Teknologi Internet of Things,” Jurnal Nasional Teknik Elektro dan Teknologi Informasi, vol. 9, no. 4, 2020, doi: 10.22146/jnteti.v9i4.539.
P. Hatta and C. W. Budiyanto, “Alleviate the contending issues in network operating system courses: Psychomotor and troubleshooting skill development with Raspberry Pi,” Open Engineering, vol. 11, no. 1, 2021, doi: 10.1515/eng-2021-0076.
G. Hollingworth, “Introducing Raspberry Pi Imager, our new imaging utility - Raspberry Pi,” 5 Mar, 2020.
M. Manfaluthy, S. Wilyanti, and Y. Lasito, “Face Recognition Berbasis Raspberry Pi Pada Keamanan Pintu Otomatis,” Prosiding Seminar Nasional Teknoka, vol. 4, 2020, doi: 10.22236/teknoka.v4i0.4274.
K. M. Hosny, A. Magdi, A. Salah, O. El-Komy, and N. A. Lashin, “Internet of things applications using Raspberry-Pi: a survey,” International Journal of Electrical and Computer Engineering, vol. 13, no. 1, 2023, doi: 10.11591/ijece.v13i1.pp902-910.
T. V. Sai, B. Aditya, A. M. Reddy, and Dr. Y. Srinivasulu, “Real Time Object Detection Using Raspberry Pi,” Int J Res Appl Sci Eng Technol, vol. 11, no. 1, 2023, doi: 10.22214/ijraset.2023.48549.
S. Patil, “Real time object detection on a Raspberry Pi,” Electronicwings, vol. V, no. Vi, 2017.
A. Gunnarsson, “Real time object detection on a Raspberry Pi,” Electronicwings, vol. V, no. Vi, 2019.
S. Bantun, A. Ashari, and R. Karim, “Analisis Kinerja Raspberry Pi Sebagai SIP Server Untuk Aplikasi Video Phone,” Techno.Com, vol. 19, no. 2, 2020, doi: 10.33633/tc.v19i2.3220.
H. Yenni and M. A. Ardianto, “ALAT DIGITAL PENCETAK KUE BAWANG MENGGUNAKAN RASPBERRY PI 3 MODEL B BERBASIS ANDROID,” JTT (Jurnal Teknologi Terapan), vol. 6, no. 1, 2020, doi: 10.31884/jtt.v6i1.246.
T. Maya Kadarina, “Otomatisasi Perekaman Foto Intraoral Gigi untuk Rekam Medis Elektronik Menggunakan Internet of Things,” Jurnal Teknologi Elektro, vol. 11, no. 1, 2020, doi: 10.22441/jte.2020.v11i1.008.
M. Data, W. Yahya, and A. Kurniawan, “Implementasi Teknologi Virtualisasi Berbasis Kontainer untuk Perangkat Internet of Things pada Pertanian Presisi,” CYBERNETICS, vol. 3, no. 01, 2020, doi: 10.29406/cbn.v3i01.1448.
S. Bramasto, “Tensorflow Lite Pada Perangkat Bergerak Guna Prediksi Waktu Panen pada Operasi Pertanian Vertikal,” Technopex-2020, 2020.
S. Li, “TensorFlow Lite: On-Device Machine Learning Framework,” Jisuanji Yanjiu yu Fazhan/Computer Research and Development, vol. 57, no. 9, 2020, doi: 10.7544/issn1000-1239.2020.20200291.
Google, “TensorFlow Lite guide,” TensorFlow, 2020.
A. Taufiq, M. Pratama, and A. R. Pratama, “Rancang Bangun Aplikasi Android ‘Kuliah Apa?’ Berbasis Flutter dan TensorFlow Lite,” Automata, vol. 2, no. 1, 2021.
E. Manor and S. Greenberg, “Custom Hardware Inference Accelerator for TensorFlow Lite for Microcontrollers,” IEEE Access, vol. 10, 2022, doi: 10.1109/ACCESS.2022.3189776.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Pengembangan Real-Time Object Detection System pada Perangkat Single-Board Computer
ARTICLE HISTORY
Issue
Section
Copyright (c) 2023 Riyadhul Fajri, Sriwinar, Firzha Fitria
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).
