Real-Time Vision-Based Blind Spot Detection and Tracking on a Raspberry Pi Using Lightweight Deep Learning

DOI

10.2991/978-94-6239-707-1_20How to use a DOI?

Keywords

Blind spot detection; advanced driver assistance systems; deep learning; object tracking; Raspberry Pi; embedded vision

Abstract

Blind spot-related accidents remain a significant safety risk, particularly with cost-sensitive Advanced Driver Assistance Systems (ADAS), where expensive sensing solutions may not always be practical. In this research paper, a real-time vision-based system is constructed using Raspberry Pi platform for vehicle detection and tracking in blind spots using lightweight YOLOv4-Tiny object recognition to ensure maximum performance on limited hardware resources. For improved reliability, centroidbased tracking with motion data can be used to identify vehicles entering a blind spot region. Alerts are generated only if vehicles remain within this pre-defined zone for an extended period, helping reduce false warnings. This system uses a Raspberry Pi, camera module, LCD display and buzzer to give drivers visual and auditory feedback. Experimental results obtained in urban traffic scenarios demonstrate that this system can achieve consistent detection and tracking despite computational constraints, without needing additional hardware acceleration. Overall, this approach demonstrates how an effective and affordable blind spot monitoring system can be created using lightweight deep learning techniques on embedded platforms.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - M. Samba Siva Reddy
AU  - R. Keerthi Sai Sanjana
AU  - K. Susmitha
AU  - Ch. Rohith
PY  - 2026
DA  - 2026/06/18
TI  - Real-Time Vision-Based Blind Spot Detection and Tracking on a Raspberry Pi Using Lightweight Deep Learning
BT  - Proceedings of the International Conference on Recent Advances in Intelligent and Sustainable Technologies (RAIST 2026)
PB  - Atlantis Press
SP  - 232
EP  - 242
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-707-1_20
DO  - 10.2991/978-94-6239-707-1_20
ID  - Reddy2026
ER  -