Active Terahertz Imaging Dataset for Concealed Object Detection

TL;DR

This paper introduces the first public active Terahertz imaging dataset for concealed object detection, evaluates popular detectors on it, and analyzes factors affecting detection accuracy in security applications.

Contribution

Provides a novel public Terahertz imaging dataset for object detection, enabling benchmarking and evaluation of detection algorithms in challenging imaging conditions.

Findings

RetinaNet achieves the highest mAP among tested detectors.

Detection accuracy varies with object location on the human body.

The dataset presents more challenging conditions than standard datasets.

Abstract

Concealed object detection in Terahertz imaging is an urgent need for public security and counter-terrorism. In this paper, we provide a public dataset for evaluating multi-object detection algorithms in active Terahertz imaging resolution 5 mm by 5 mm. To the best of our knowledge, this is the first public Terahertz imaging dataset prepared to evaluate object detection algorithms. Object detection on this dataset is much more difficult than on those standard public object detection datasets due to its inferior imaging quality. Facing the problem of imbalanced samples in object detection and hard training samples, we evaluate four popular detectors: YOLOv3, YOLOv4, FRCN-OHEM, and RetinaNet on this dataset. Experimental results indicate that the RetinaNet achieves the highest mAP. In addition, we demonstrate that hiding objects in different parts of the human body affect detection accuracy. The dataset is available at https://github.com/LingLIx/THz_Dataset.