Visual Impaired Assistance for Object and Distance Detection Using Convolutional Neural Networks

Jumadi Mabe Parenreng; Andi Baso Kaswar; Ibnu Fikrie Syahputra

doi:10.29207/resti.v8i1.5491

Jumadi Mabe Parenreng Universitas Negeri Makassar
Andi Baso Kaswar Universitas Negeri Makassar
Ibnu Fikrie Syahputra Universitas Negeri Makassar

DOI: https://doi.org/10.29207/resti.v8i1.5491

Keywords: model, machine learning, vision

Abstract

Vision is a very valuable gift from God; Most aspects of human needs in the body are dominated by vision. Based on data from the World Health Organization (WHO) there are around 180 million people in the world experiencing visual impairment, while the prevalence of blindness in Indonesia reaches 3 million people (1.5% of Indonesia's population), so we designed a system in the form of a prototype that could detect objects around the user and convey data in the form of sound to the user. This research discusses the application of a machine learning model using the Convolutional Neural Network method to detect objects optimally. The objects that have been collected will be trained on machine learning and produce a model to be embedded in the system's main machine, namely the Raspberry PI 4B. The training of the machine learning model was carried out several times by changing the compositions of several layers until a model with optimal accuracy was obtained; however, the size of the resulting model was quite large, so the researchers carried out SSDMobileNetV2 transfer learning to obtain the optimal model. The optimal model was obtained with a model precision of 92% and a model size of 18 MB. Object detection tests carried out under 3 test conditions resulted in an average object detection accuracy of 84.3%, and distance detection tests carried out under 10 conditions resulted in an average distance detection error of 2.1 cm. The results show that the system was accurate and effective.

Downloads

Download data is not yet available.

References

.[1] M. Z. Ritonga, “Level of Knowledge of Student in Sma Muhammadiyah 01 Medan To Decreased Visual Activity,” Jimki, vol. 8, no. 3, pp. 35–40, 2021.

A. A. Rosenbloom, “Low vision,” Optom. Vis. Sci., vol. 50, no. 3, p. 257, 2020, doi: 10.1097/00006324-197303000-00014.

R. dr. S. Tirtonegoro, “Penyakit Mata Penyebab Utama Kebutaan Di Indonesia,” rsupsoeradji.id, Nov. 13, 2019. https://rsupsoeradji.id/penyakit-mata-penyebab-utama-kebutaan-di-indonesia/ (accessed Apr. 19, 2022).

R. Agarwal et al., “Low cost ultrasonic smart glasses for blind,” 2018 9th IEEE Annu. Inf. Technol. Electron. Mob. Commun. Conf. IEMCON 2018, pp. 210–213, 2018, doi: 10.1109/IEMCON.2017.8117194.

J. Bai, S. Lian, Z. Liu, K. Wang, and D. Liu, “Virtual-Blind-Road Following-Based Wearable Navigation Device for Blind People,” IEEE Trans. Consum. Electron., vol. 64, no. 1, pp. 136–143, 2018, doi: 10.1109/TCE.2018.2812498.

J. H. Kim, S. K. Kim, T. M. Lee, Y. J. Lim, and J. Lim, “Smart glasses using deep learning and stereo camera,” 2019 IEEE 8th Glob. Conf. Consum. Electron. GCCE 2019, vol. 2, pp. 294–295, 2019, doi: 10.1109/GCCE46687.2019.9015357.

M. Cabanillas-Carbonell, A. A. Chávez, and J. B. Barrientos, “Glasses connected to Google vision that inform blind people about what is in front of them,” 2020 8th E-Health Bioeng. Conf. EHB 2020, 2020, doi: 10.1109/EHB50910.2020.9280268.

L. A. I. Cabrera-Sosa, L. E. Lopez-Garcia, A. Diaz-Sanchez, J. M. Rocha-Perez, V. H. Carbajal-Gomez, and G. Zamora-Mejia, “Design and Implementation of a White-Cane Based on the Vibration-Distance Sensing Technique for Blind People,” 2020 IEEE Int. Conf. Eng. Veracruz, ICEV 2020, 2020, doi: 10.1109/ICEV50249.2020.9289667.

F. B. Setiawan, H. W. Kusuma, S. Riyadi, and leonardo H. Pratomo, “Penerapan PI Cam Menggunakan Program Berbasis Raspberry PI 4,” Cyclotr. J. Tek. Elektro, vol. 5, no. 2, pp. 51–56, 2022.

F.- Puspasari, I.- Fahrurrozi, T. P. Satya, G.- Setyawan, M. R. Al Fauzan, and E. M. D. Admoko, “Sensor Ultrasonik HCSR04 Berbasis Arduino Due Untuk Sistem Monitoring Ketinggian,” J. Fis. dan Apl., vol. 15, no. 2, p. 36, 2019, doi: 10.12962/j24604682.v15i2.4393.

Yuhandri, Musli Yanto, and Eka Naufaldi Novri, “Application of Object Mask Detection Using the Convolution Neural Network (CNN),” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 4, pp. 922–929, 2023, doi: 10.29207/resti.v7i4.5059.

M. M. Saufi, M. A. Zamanhuri, N. Mohammad, and Z. Ibrahim, “Deep learning for Roman handwritten character recognition,” Indones. J. Electr. Eng. Comput. Sci., vol. 12, no. 2, pp. 455–460, 2018, doi: 10.11591/ijeecs.v12.i2.pp455-460.

K. Zakka, “CS231n Convolutional Neural Networks for Visual Recognition,” Stanford Univ., pp. 1–18, 2021, Accessed: Apr. 19, 2022. [Online]. Available: https://cs231n.github.io/convolutional-networks/.

V. Tatan, “Understanding CNN (Convolutional Neural Network) | by Vincent Tatan | Towards Data Science,” Dec. 23, 2019. https://towardsdatascience.com/understanding-cnn-convolutional-neural-network-69fd626ee7d4 (accessed Apr. 19, 2022).

Irene S. Walingkas Meicsy E.I. Najoan Brave A. Sugiarso, “Irene S. Walingkas,” J. Tek. Elektro dan Komput., vol. Vol.8, no. Vol. 8 No. 3 (2019): Jurnal Teknik Elektro dan Komputer, pp. 121–131, 2019.

Buyut Khoirul Umri and V. Delica, “Penerapan transfer learning pada convolutional neural networks dalam deteksi covid-19.,” Jnanaloka, pp. 9–17, 2021, doi: 10.36802/jnanaloka.2021.v2-no2-9-17.

Achmad Naila Muna Ramadhani, Galuh Wilujeng Saraswati, Rama Tri Agung, and Heru Agus Santoso, “Performance Comparison of Convolutional Neural Network and MobileNetV2 for Chili Diseases Classification,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 4, pp. 940–946, 2023, doi: 10.29207/resti.v7i4.5028.

F. NURSULISTIO, “Deteksi Objek Masker Menggunakan Object Detection API dan TensorFlow Lite Model Maker,” 2022, [Online]. Available: https://dspace.uii.ac.id/handle/123456789/41754%0Ahttps://dspace.uii.ac.id/bitstream/handle/123456789/41754/18523149.pdf?sequence=1&isAllowed=y.