DEF-YOLO: Leveraging YOLO for Concealed Weapon Detection in Thermal Imagin

2025-10-15

AI Summary

To address the lack of benchmark datasets and high-accuracy real-time models for concealed weapon detection in thermal imaging, this paper proposes DEF-YOLO—a YOLOv8-based detector incorporating deformable convolutions into the SPPF module, backbone, and neck to enhance multi-scale feature extraction, alongside focal loss to mitigate class imbalance. We also introduce TICW, the first large-scale thermal imaging concealed weapon dataset, comprising over 12,000 annotated samples. Experiments demonstrate that DEF-YOLO significantly improves localization accuracy for small objects under thermally uniform and low-contrast conditions, achieving an mAP@0.5 of 68.3%—a 9.7% gain over the baseline—while maintaining real-time inference at 32 FPS. This work establishes a new benchmark and provides a practical, privacy-preserving, all-weather, and cost-effective solution for concealed weapon detection.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Hardware-aware ML
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Concealed weapon detection aims at detecting weapons hidden beneath a person's clothing or luggage. Various imaging modalities like Millimeter Wave, Microwave, Terahertz, Infrared, etc., are exploited for the concealed weapon detection task. These imaging modalities have their own limitations, such as poor resolution in microwave imaging, privacy concerns in millimeter wave imaging, etc. To provide a real-time, 24 x 7 surveillance, low-cost, and privacy-preserved solution, we opted for thermal imaging in spite of the lack of availability of a benchmark dataset. We propose a novel approach and a dataset for concealed weapon detection in thermal imagery. Our YOLO-based architecture, DEF-YOLO, is built with key enhancements in YOLOv8 tailored to the unique challenges of concealed weapon detection in thermal vision. We adopt deformable convolutions at the SPPF layer to exploit multi-scale features; backbone and neck layers to extract low, mid, and high-level features, enabling DEF-YOLO to adaptively focus on localization around the objects in thermal homogeneous regions, without sacrificing much of the speed and throughput. In addition to these simple yet effective key architectural changes, we introduce a new, large-scale Thermal Imaging Concealed Weapon dataset, TICW, featuring a diverse set of concealed weapons and capturing a wide range of scenarios. To the best of our knowledge, this is the first large-scale contributed dataset for this task. We also incorporate focal loss to address the significant class imbalance inherent in the concealed weapon detection task. The efficacy of the proposed work establishes a new benchmark through extensive experimentation for concealed weapon detection in thermal imagery.

Problem

• Detecting concealed weapons in thermal imagery using YOLO
• Addressing class imbalance and multi-scale feature extraction
• Providing a large-scale dataset for thermal weapon detection

Innovation

• Deformable convolutions adaptively focus on thermal objects
• Focal loss addresses class imbalance in weapon detection
• Large-scale thermal dataset enables robust concealed weapon detection