Monitoring System using Artificial Vision and YoloV8 for Accident Prevention in Children

Authors

Johnny Angelino
Facultad de Ingeniería Electrónica y Eléctrica, Universidad Nacional Mayor de San Marcos, Lima, Perú
Andrés Quispe
Facultad de Ingeniería Electrónica y Eléctrica, Universidad Nacional Mayor de San Marcos, Lima, Perú
Ricardo Yauri
Universidad Tecnológica del Perú
DOI: https://doi.org/10.52549/ijeei.v14i3.8043
Download PDF
Published: 30-09-2026 • Issue: Vol. 14 No. 3: September 2026 • Section: Regular paper

Abstract

The increase in student density in educational institutions has generated greater risks to child safety, especially in high-traffic scenarios where manual supervision is limited to prevent accidents. In this context, the need arises to implement non-invasive technologies and systems based on artificial vision, to improve monitoring and support traditional surveillance methods. Previous research describes the use of computer vision techniques and models such as YOLO for safety, monitoring, and their integration into low-cost embedded systems, with limitations in real-time response or accident prevention. This research shows the development of a monitoring system based on artificial vision with a YOLOv8 model trained and deployed on a Raspberry Pi with integration with an ESP32 to detect risk events aimed at preventing accidents in minors. The results indicate that risk classes are detected with confidence levels above 70%, with good performance in metrics such as precision (~0.9), recall (~0.8) and mAP50 (~0.9), without overfitting and with hypothesis validation. In conclusion, the system is a suitable solution for accident detection with metric validation, but it needs to be optimized to work in real-world heterogeneous scenarios.
Keywords: Artificial Vision; Monitoring; Computer Vision; Raspberry Pi; ESP32; Object Detection

References

[1] P. Liu and E. Dastbaravardeh, “Deep Learning‐Driven Assessment of Student Movement and Performance Using Physiological Data in Physical Education Information Systems: An S‐AIoT Solution,” Int. J. Intell. Syst., vol. 2025, no. 1, p. 10, Jan. 2025, doi: 10.1155/int/9479311.

[2] M.-A. Chung, S.-Y. Chai, M.-C. Hsieh, C.-W. Lin, K.-X. Chen, S.-J. Huang, and J.-H. Zhang, “YOLO-LSD: A Lightweight Object Detection Model for Small Targets at Long Distances to Secure Pedestrian Safety,” IEEE Access, vol. 13, no. 1, pp. 83061–83070, 2025, doi: 10.1109/ACCESS.2025.3567843.

[3] A. H. Zinati, M. Sabeti, H. Kamyab, and E. Moradi, “Diagnosis of different types of single suture craniosynostosis in infants with deep learning techniques,” Med. Nov. Technol. Devices, vol. 27, no. 1, p. 100370, Sep. 2025, doi: 10.1016/j.medntd.2025.100370.

[4] K. Choopun, N. Pornsawan, K. Panyawong, and S. Wattanakul, “A Mobile ADHD Screening App for Primary School Children: A Pilot Study in Thai Primary Care,” Int. J. Interact. Mob. Technol., vol. 19, no. 23, pp. 50–67, Dec. 2025, doi: 10.3991/ijim.v19i23.56723.

[5] Risfendra, Aripriharta, Suherman, G. F. Ananda, D. S. Putra, and Fahmi, “Contactless Infant Height Measurement for Enhanced Early Detection of Stunting Using Computer Vision Techniques,” IEEE Access, vol. 13, no. 1, pp. 42364–42376, 2025, doi: 10.1109/ACCESS.2025.3548159.

[6] S. G. Hong, S. M. Park, S. Kwon, H. Sakthivel, S. P. Nagappa, J. W. Leem, S. R. Steinhubl, P. Ngiruwonsanga, J.-L. N. Mangara, C. Twizere, and Y. L. Kim, “Smartphone conjunctiva photography for malaria risk stratification in asymptomatic school age children,” npj Digit. Med., vol. 8, no. 1, p. 151, Mar. 2025, doi: 10.1038/s41746-025-01548-8.

[7] Y. Shang, Y. Shang, and Y. Shang, “Enabled Intelligent Monitoring of Mental Health Indicators During Physical Activity Among Jiangsu Vocational College Students,” Eng. Reports, vol. 8, no. 2, Feb. 2026, doi: 10.1002/eng2.70612.

[8] Q. Lai, “Research on the refinement of college student education management based on artificial intelligence,” Discov. Artif. Intell., vol. 6, no. 1, p. 31, Dec. 2025, doi: 10.1007/s44163-025-00651-9.

[9] K. Gangaraju, Y. H. Kadegowda, and S. Sangani, “Energy- and behavior-aware sensory data collection for ASD monitoring over IoT using unequal clustering and reinforcement learning,” Discov. Internet Things, vol. 6, no. 1, p. 24, Feb. 2026, doi: 10.1007/s43926-026-00287-w.

[10] L. Han, X. Ma, M. Dai, and L. Bai, “A WAD-YOLOv8-based method for classroom student behavior detection,” Sci. Rep., vol. 15, no. 1, p. 9655, Mar. 2025, doi: 10.1038/s41598-025-87661-w.

[11] M. Alotaibi, A. Alruwaythi, S. Alenazi, and M. Alsaedi, “Integrating YOLOv8 and IoT in a Computer Vision System for Child Detection in Smart Cities,” Int. J. Adv. Comput. Sci. Appl., vol. 16, no. 9, pp. 636–644, Sep. 2025, doi: 10.14569/IJACSA.2025.0160960.

[12] A. Guerrero-Blázquez, Á. C. Álvarez-Melcón, J. J. López-Marcos, P. Martín-Casas, A. Arranz-Escudero, and R. M. Ortiz-Gutiérrez, “Validity and Reliability of a Smart Band for Monitoring Cardiorespiratory Parameters in Children and Adolescents with Severe Cerebral Palsy,” Sensors, vol. 26, no. 3, p. 828, Jan. 2026, doi: 10.3390/s26030828.

[13] N. R. Wagh, S. R. Sutar, V. J. Kadam, S. M. Jadhav, A. S. Yadav, and V. S. Pawar, “Evaluation of IoT based smart safety systems for women and children using machine learning techniques,” Sci. Rep., vol. 16, no. 1, p. 87, Nov. 2025, doi: 10.1038/s41598-025-29146-4.

[14] B. J. Tantra and M. Widjaja, “Automatic detection of dress-code surveillance in a university using YOLO algorithm,” IAES Int. J. Artif. Intell., vol. 14, no. 2, p. 1568, Apr. 2025, doi: 10.11591/ijai.v14.i2.pp1568-1575.

[15] S. Peng, X. Zhang, L. Zhou, and P. Wang, “YOLO-CBD: Classroom Behavior Detection Method Based on Behavior Feature Extraction and Aggregation,” Sensors, vol. 25, no. 10, p. 3073, May 2025, doi: 10.3390/s25103073.

[16] Y. Cao, Q. Cao, C. Qian, and D. Chen, “YOLO-AMM: A Real-Time Classroom Behavior Detection Algorithm Based on Multi-Dimensional Feature Optimization,” Sensors, vol. 25, no. 4, p. 1142, Feb. 2025, doi: 10.3390/s25041142.

[17] Ü. Işıkdağ, H. A. Çemrek, S. Sönmez, Y. Aydın, G. Bekdaş, and Z. W. Geem, “A Real-Time Advisory Tool for Supporting the Use of Helmets in Construction Sites,” Information, vol. 16, no. 10, p. 824, Sep. 2025, doi: 10.3390/info16100824.

[18] S. Diop, F. Jouen, J. Bergounioux, and I. Trabelsi, “Fine-Tuned YOLO Model for Monitoring Children Across Medical Scenes Based on a Large-Scale Real-World Dataset for Children Detection,” IEEE Access, vol. 13, pp. 130953–130962, 2025, doi: 10.1109/ACCESS.2025.3588316.

[19] M. Vijayalakshmi, A. J. R. Jose, G. K. Vishal, and N. Vishwanath, “Safety equipment detection using YOLOv8,” Signal, Image Video Process., vol. 19, no. 12, p. 994, Dec. 2025, doi: 10.1007/s11760-025-04583-w.

[20] I. Vernikos and E. Spyrou, “Skeleton Reconstruction Using Generative Adversarial Networks for Human Activity Recognition Under Occlusion,” Sensors, vol. 25, no. 5, p. 1567, Mar. 2025, doi: 10.3390/s25051567.

[21] V. Sanikommu, S. Mummaneni, N. Jacob, E. K.C, B. Kumar, and R. Variam, “Deep Learning-Based Control System for Context-Aware Surveillance Using Skeleton Sequences from IP and Drone Camera video,” Int. Arab J. Inf. Technol., vol. 22, no. 5, pp. 919–929, Sep. 2025, doi: 10.34028/iajit/22/5/6.

[22] E. Oliosi, S. Ferreira, A. P. Giordano, G. Viveiros, J. Parraca, P. Pereira, F. Guede-Fernández, and S. Azevedo, “Evaluation of Smartphone Camera Positioning on Artificial Intelligence Pose Estimation Accuracy for Exercise Detection: Observational Study,” JMIR mHealth uHealth, vol. 14, no. 1, pp. e82412–e82412, Mar. 2026, doi: 10.2196/82412.

[23] A. Alvarez Oviedo, J. F. Mamani Villanueva, G. A. Echaiz Espinoza, J. M. M. Villanueva, A. O. Salazar, and E. R. L. Villarreal, “Design of a System for Driver Drowsiness Detection and Seat Belt Monitoring Using Raspberry Pi 4 and Arduino Nano,” Designs, vol. 9, no. 1, p. 11, Jan. 2025, doi: 10.3390/designs9010011.

[24] S. Liawatimena and N. Isworo, “Annotated drowsiness detection dataset captured using Raspberry Pi 5,” Data Br., vol. 63, no. 1, p. 112211, Dec. 2025, doi: 10.1016/j.dib.2025.112211.

[25] N. Tahilramani, P. Ahir, S. Saxena, V. P. Talreja, and P. Charanarur, “Edge-based AI solution for enhancing urban safety: helmet compliance monitoring with YOLOv9 on Raspberry Pi,” Discov. Internet Things, vol. 5, no. 1, p. 25, Mar. 2025, doi: 10.1007/s43926-025-00113-9.

[26] H. Bodkhe, C. Bilade, D. Naik, O. Deshmukh, A. Bulakh, P. Potdar, K. Shirbavikar, and S. Komble, “Track-Me-Down Emergency Location Service Provider,” in RAiSE-2023, Basel Switzerland: MDPI, Feb. 2024, p. 235. doi: 10.3390/engproc2023059235.

[27] R. Yauri, A. Castro, and R. Espino, “Automatic Leaf Health Monitoring with an IoT Camera System based on Computer Vision and Segmentation for Disease Detection,” WSEAS Trans. Electron., vol. 15, no. 1, pp. 148–156, Dec. 2024, doi: 10.37394/232017.2024.15.17.

[28] D. C. Guevara Tocto, D. N. Ayerve Cari, and J. T. S, “Autonomous Visual Pest Detection System with ESP32-CAM, Zonal Classification, and Notification via Telegram for Agriculture,” Int. J. Electr. Electron. Eng., vol. 13, no. 1, pp. 60–68, Jan. 2026, doi: 10.14445/23488379/IJEEE-V13I1P107.

[29] X. Cao, C. Li, and H. Zhai, “YOLO-AB: A Fusion Algorithm for the Elders’ Falling and Smoking Behavior Detection Based on Improved YOLOv8,” Comput. Mater. Contin., vol. 83, no. 3, pp. 5487–5515, 2025, doi: 10.32604/cmc.2025.061823.

[30] N. Khalil, M. H. Rashid, S. A. Rehman, M. Yasir, and M. Hussain, “Improved Traffic Safety with YOLO-v8 Driven Smart Helmet Detection,” VFAST Trans. Softw. Eng., vol. 13, no. 3, pp. 29–42, Aug. 2025, doi: 10.21015/vtse.v13i3.2184.

[31] S. S. F. A. Elnozahy, S. C. Pari, and L. C. Liang, “Raspberry Pi-Based Face Recognition Door Lock System,” Internet of Things, vol. 6, no. 2, Jun. 2025, doi: 10.3390/IOT6020031.

[32] H. Ma, D. Guo, J. Wang, P. Li, C. Xu, and Y. Wang, “Real-time face recognition algorithm based on lightweight neural network in the field of computer vision,” Discov. Appl. Sci., vol. 8, no. 1, p. 33, Nov. 2025, doi: 10.1007/s42452-025-08004-y.

[33] R. Gholami, H. D. Jahromi, and S. Sedaghat, “Design and Implementation of a Near Real-Time Human Detection Robot Using YOLO Framework and IoT Technologies,” IEEE Access, vol. 13, no. 1, pp. 175960–175983, 2025, doi: 10.1109/ACCESS.2025.3618302.

[34] D. Díaz-Delgado, S. M. Vigil-Ramírez, L. J. Acho-Cachay, B. R. Tuanama-Chávez, and L. A. Rojas-Puerta, “IoT-Based Smart Lock with Real-Time Person Detection Using YOLOv5 and Mobile App Integration,” Rev. Científica Sist. e Informática, vol. 5, no. 2, p. e1005, Jul. 2025, doi: 10.51252/rcsi.v5i2.1005.

How to Cite

[1]
J. Angelino, A. Quispe, and R. Yauri, “Monitoring System using Artificial Vision and YoloV8 for Accident Prevention in Children”, IJEEI, vol. 14, no. 3, pp. 935–846, Sep. 2026, doi: 10.52549/ijeei.v14i3.8043.