Improved YOLOv8n for Concealed Object Detection in Human Body Millimeter Wave Images
This paper, which builds upon the fundamental YOLOv8n architecture, adds the CAFM module to the neck network with the goal of improving detection accuracy and increasing sensitivity of the model to objects in millimeter wave images. This addresses the issue of insufficient detection in millimeter wave images that arises from the difficulty of extracting features of concealed objects. Subsequently, Inner-CIoU is employed as the loss function for bounding box regression, which aims to speed up the convergence of the model. According to experiments, the enhanced YOLOv8n model considerably raises mAP when compared to the baseline model.
Authors
- Jinqiu Dou
- Zhiyong Shen (ORCID: https://orcid.org/0000-0003-4950-2434)
- Jianxin Zhang (ORCID: https://orcid.org/0000-0001-6076-5433)
- Ze Li (ORCID: https://orcid.org/0000-0002-1154-6012)
- Yuxin He (ORCID: https://orcid.org/0009-0004-2869-4523)
- Pingping Huang (ORCID: https://orcid.org/0000-0003-0191-2610)
- Yun Su (ORCID: https://orcid.org/0009-0008-5831-9344)
- Weixian Tan (ORCID: https://orcid.org/0000-0003-0569-5967)
- Yanmin Chen (ORCID: https://orcid.org/0000-0001-7928-5392)
Institutions
- Shenzhen Terahertz Technology Innovation Research Institute (CN)
- Inner Mongolia University of Technology (CN)
Publication Details
- Published
- 2024-11-22
- DOI
- https://doi.org/10.1109/icsidp62679.2024.10868966
- Citations
- 1
- Primary Topic
- Biometric Identification and Security
- Type
- article
- Field-Weighted Citation Impact
- 0.35