Prof. Fang Guangyou and his research team from the Aerospace Information Research Institute and Chinese Academy of Sciences used human image data obtained by passive terahertz sensors, and they trained and tested a potential detector based on deep residual networks. The suggested approach can be utilized to identify concealed items in terahertz pictures in real-time.

Figure 1: Accurate human image data obtained by passive terahertz sensors.

Figure 1 shows that with the worldwide anti-terrorist measures being strengthened, it is becoming more vital to undertake security checks in public locations to discover concealed items on the human body.

Past research has shown that deep learning may assist in identifying hidden items in passive terahertz images. However, real-time tagging with high accuracy and performance remains a challenge. [1]

To lessen the complexity of network training, the research team replaced the backbone network of the Single Shot MultiBox Detector (SSD) algorithm with a more representative residual network to reduce the difficulty of network training.

Aiming at the problems of repeated detection and missed detection of small targets, a feature fusion-based terahertz image target detection algorithm was proposed.

Furthermore, they introduced a hybrid attention mechanism in SSD to improve the algorithm's ability to acquire object details and location information. [2]

The research team also compared the proposed model with other mainstream detection methods on the terahertz human security image dataset. The results showed that the proposed method achieves improved detection accuracy in comparison with the original SSD algorithm when the speed is only slightly reduced.

The improved SSD algorithm addresses the issue of missed detection while also enhancing detection confidence. Therefore, it can meet the real-time detection needs of security inspection scenarios. [3]

References:

1. https://www.marktechpost.com/2022/07/28/latest-deep-learning-based-research-provides-more-rapid-and-accurate-terahertz-security-inspections-using-human-image-data/
2. http://ein.iconnect007.com/index.php/article/132813/deep-learning-technology-enables-faster-more-accurate-terahertz-security-inspection/132816/?skin=ein
3. https://techxplore.com/news/2022-07-deep-technology-enables-faster-accurate.html

Cite this article:

Sri Vasagi K (2022), New Deep Learning Research Provides Rapid Terahertz Security Inspections, Anatechmaz, pp.140