Open Access Open Access  Restricted Access Subscription or Fee Access

Flying Faces: An Automated Recognition System using Raspberry Pi and Drone



Facial recognition technology has gained populari- ty in recent years and is used in various applications, such as security and surveillance. However, traditional facial recogni- tion systems are limited in their ability to capture images from different angles and perspectives. In this paper, facial recogni- tion system is presented that utilizes drone technology to cap- ture images from multiple angles for better accuracy. The sys- tem consists of a Raspberry Pi board, a high-resolution cam- era, OpenCV for face detection, and a deep learning model trained with TensorFlow for face recognition. The system is integrated with a drone for aerial surveillance and the results of the facial recognition algorithms are transmitted back to the drone for further action. The proposed system has the poten- tial to be used in a variety of applications, such as law en- forcement, border security, search and rescue operations, and crowd monitoring. The use of drone technology allows the sys- tem to capture images from hard-to-reach areas and provide real-time surveillance. The deep learning model used for face recognition is trained on a large dataset of faces, which im- proves the accuracy of the system. The system can also be cus- tomized to meet specific needs, such as identifying individuals on a watchlist or monitoring specific areas. Overall, the facial recognition system with drone technology presented in this paper provides an innovative solution to im- prove the accuracy and efficiency of facial recognition systems. With its ability to capture high-resolution images in real-time, the system can aid in law enforcement activities, search and rescue operations, and crowd monitoring, among others. The system's integration with drone technology enables it to access hard-to-reach or dangerous areas, providing a safe and effi- cient way to monitor large crowds or search for missing indi- viduals.


facial recognition, drone, Raspberry Pi, OpenCV, deep learning, IoT, TensorFlow, aerial surveillance, security, surveillance, real-time

Full Text:



Luo, J., Wu, X., Li, Y., Li, J., & Zhang, H. (2020). A review on aerial surveillance systems: Advancements, challenges, and opportunities. IEEE Access, 8, 26277-26294.

Sun, Y., Yan, X., Guan, J., & Yang, J. (2018). Multi-view face recognition from unmanned aerial vehicle. Multimedia Tools and Applications, 77(1), 1083-1101.

Jia, X., Li, Y., Fan, B., Li, L., & Wu, F. (2020). A novel 3D face recognition system based on drones. Journal of Real-Time Image Processing, 17(4), 1109-1124.

Hossain, M. S., Muhammad, G., & Farooq, O. (2019). Computer Vision based Real-Time Object Detection on Raspberry Pi. Journal of King Saud University-Computer and Information Sciences, 31(4), 453-462.

Bradski, G., & Kaehler, A. (2017). Learning OpenCV 3: Computer vision in C++ with the OpenCV library. O'Reilly Media, Inc.

Sánchez-Matilla, R., Kyrkou, C., & Pattichis, C. S. (2019). An IoT- based platform for drone-based surveillance and face recognition. IEEE Internet of Things Journal, 6(2), 1526-1535.

Smart Surveillance System using Raspberry Pi and Drone" by R. K. Mohapatra, S. K. Panda, and P. K. Sahu.

Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).

M. G. Chung, J. H. Chung, and J. K. Park, "Real-Time Face Detection and Recognition System Using Drone," Sensors, vol. 21, no. 7, p. 2242, Mar. 2021.

Aksay, A., & Kocak, T. (2020). Raspberry Pi-based facial recognition system with deep learning. International Journal of Advanced Computer Science and Applications, 11(11), 423-429.

Paudel, P., & Lee, D. H. (2019). Raspberry Pi based real-time object detection and tracking. International Journal of Advanced Science and Technology, 28(14), 409-416.

Gupta, S., Singla, S., & Mittal, A. (2020). Comparative analysis of deep learning models for face recognition. International Journal of Advanced Research in Computer Science, 11(1), 27-31.

Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.



  • There are currently no refbacks.