Proceedings of the International Conference on Recent Trends in Intelligent Computing, Manufacturing, and Electronics (rTIME 2025)

<Previous Article In Volume
Next Article In Volume>

AI-Enhanced FPGA: License Plate Detection for Accident Evidence Collection

Authors
Anushk Gupta1, Syed Sadique Anwer Askari2, *, Madhu Kumari3, Gufran Ahmad1
1Dept. of Electrical Engg., Dayalbagh Educatinal Institute, Agra, UP, India
2Dept. of Electronics & Comm., Manipal University Jaipur, Jaipur, India
3Dept. of Electronics and Computer Engg., National Institute of Advanced Manufacturing Technology, Ranchi, India
*Corresponding author. Email: Syed.askari@jaipur.manipal.edu Email: anwer.ism@gmail.com
Corresponding Author
Syed Sadique Anwer Askari
Available Online 31 March 2026.
DOI
10.2991/978-94-6239-628-9_27How to use a DOI?
Keywords
Accident evidence collection; license plate detection; PYNQ-Z2 FPGA; Haar cascade classifier; optical character recognition (OCR); real-time processing; circular storage system; embedded vision system
Abstract

This paper demonstrate the design and implementation of a lightweight, real-time Accident Evidence Collection System (AECS) using the PYNQ-Z2 FPGA technology. The main objective is to capture and evaluate vehicle surroundings through a live video stream for the detection and storage of license plate information, especially in accident situation. To achieve computational efficiency on a resource-constrained embedded platform, the system employs a Haar Cascade classifier for license plate detection, followed by Optical Character Recognition (OCR) using Tesseract. Frames are extracted at 2 frames per second and temporarily stored using a circular storage strategy to control memory limitations. The system is capable of operating continuously for up to six days before recycling old data, ensuring long-term usability in mobile environments. A contrast between Haar Cascade and YOLOv4 models display’s that Haar Cascade offers significantly lower latency and memory usage, making it more applicable for real-time deployment on edge devices. The presented technique provides a proven and efficient framework for automated evidence collection, demonstrating promising results in terms of speed, accuracy, and system scalability.

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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Recent Trends in Intelligent Computing, Manufacturing, and Electronics (rTIME 2025)
Series
Advances in Engineering Research
Publication Date
31 March 2026
ISBN
978-94-6239-628-9
ISSN
2352-5401
DOI
10.2991/978-94-6239-628-9_27How to use a DOI?
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.

Cite this article

risenwbib
TY  - CONF
AU  - Anushk Gupta
AU  - Syed Sadique Anwer Askari
AU  - Madhu Kumari
AU  - Gufran Ahmad
PY  - 2026
DA  - 2026/03/31
TI  - AI-Enhanced FPGA: License Plate Detection for Accident Evidence Collection
BT  - Proceedings of the International Conference on Recent Trends in Intelligent Computing, Manufacturing, and Electronics (rTIME 2025)
PB  - Atlantis Press
SP  - 297
EP  - 307
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-628-9_27
DO  - 10.2991/978-94-6239-628-9_27
ID  - Gupta2026
ER  -