A Low-Cost Passive Thermal IR Imaging System for Automated Hidden Object Detection Using AI
This paper presents a low-cost and AI-based automated solution for detecting hidden objects using thermal infrared imaging. We developed an affordable IR imaging setup and collected a comprehensive dataset of thermal images with different objects hidden under clothing. To overcome the challenges of low-resolution IR sensors, we implemented innovative signal processing techniques to enhance image quality, making it suitable for accurate object detection with AI. Meanwhile, a large dataset of over 1100 IR images with hidden objects was provided to train object detection algorithms, specifically YOLOv9 and RCNN. The average detection rate is close to $95 \%$, which is higher than that of the similar work. Furthermore, we investigated the physics of thermal IR radiation, analyzing the temperature behavior of various concealed objects over time.
Authors
- Majid Sarmad (ORCID: https://orcid.org/0000-0003-2960-1291)
- Mohammad Javad Amiri (ORCID: https://orcid.org/0000-0002-2633-0572)
- Mohammad Fakharzadeh (ORCID: https://orcid.org/0000-0002-5508-6193)
- Shokoufe Ghazanfari (ORCID: https://orcid.org/0000-0001-9366-089X)
Institutions
- Sharif University of Technology (IR)
Publication Details
- Published
- 2024-10-09
- DOI
- https://doi.org/10.1109/ist64061.2024.10843428
- Primary Topic
- Infrared Target Detection Methodologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00