Back to Search
Start Over
Few-shot concealed object detection in sub-THz security images using improved pseudo-annotations
- Source :
- Scientific Reports, Vol 14, Iss 1, Pp 1-9 (2024)
- Publication Year :
- 2024
- Publisher :
- Nature Portfolio, 2024.
-
Abstract
- Abstract In this research, we explore the few-shot object detection application for identifying concealed objects in sub-terahertz security images, using fine-tuning based frameworks. To adapt these machine learning frameworks for the (sub-)terahertz domain, we propose an innovative pseudo-annotation method to augment the object detector by sourcing high-quality training samples from unlabeled images. This approach employs multiple one-class detectors coupled with a fine-grained classifier, trained on supporting thermal-infrared images, to prevent overfitting. Consequently, our approach enhances the model’s ability to detect challenging objects (e.g., 3D-printed guns and ceramic knives) when few-shot training examples are available, especially in the real-world scenario where images of concealed dangerous items are scarce.
Details
- Language :
- English
- ISSN :
- 20452322
- Volume :
- 14
- Issue :
- 1
- Database :
- Directory of Open Access Journals
- Journal :
- Scientific Reports
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.6499663dd260436284837cd7543aba4e
- Document Type :
- article
- Full Text :
- https://doi.org/10.1038/s41598-024-53045-9