Active Terahertz Imaging Dataset for Concealed Object Detection
This addresses the need for public security and counter-terrorism by providing a benchmark for detecting concealed objects, though it is incremental as it focuses on dataset creation and evaluation of existing methods.
The authors tackled concealed object detection in Terahertz imaging by creating the first public dataset for evaluating multi-object detection algorithms, with RetinaNet achieving the highest mAP of 0.75 on this challenging dataset.
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.