文献类型：期刊文献

英文题名：FDTNet: Enhancing frequency-aware representation for prohibited object detection from X-ray images via dual-stream transformers

作者：Zhu, Ziming[1];Zhu, Yu[1];Wang, Haoran[1];Wang, Nan[1];Ye, Jiongyao[1];Ling, Xiaofeng[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2024

卷号：113

外文期刊名：ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

收录：;EI(收录号：20240815608391);WOS:【SCI-EXPANDED(收录号:WOS:001187230600001)】；

基金：The authors would like to thank the (anonymous) reviewers for their constructive comments. This work was supported by the Shanghai Automotive Industry Science and Technology Development Foundation, China (2304) .

语种：英文

外文关键词：Prohibited object detection; X-ray image; Frequency feature perception; Dual-stream network; Attention module

摘要：With the extensive application of object detection in intelligent security, the demand for detecting prohibited items in X-ray images has become increasingly stringent. Unlike natural images, X-ray images present unique challenges such as complex backgrounds and mutual occlusion between prohibited and normal items. Consequently, applying traditional detection methods to X-ray images remains a significant challenge. To tackle these challenges, we have developed a unique frequency -aware dual -stream transformers (FDTNet) that is specifically designed for analyzing X-ray images. The FDTNet consists of two streams: one handles the original image, while the other deals with an image that has been enhanced with frequency domain features. In order to achieve precise detection of prohibited items, we introduce a frequency -aware module (FAM) that enhances the representation of prohibited items by utilizing information from the frequency domain. This FAM can be easily integrated into other backbones or detectors as it is a plug -and -play module. Additionally, to enhance the fusion of feature maps from both streams, we utilize a global and channel attention module (GCA) that aggregates texture representations for spatial feature streams. Our evaluation of the proposed FDTNet on the OPIXray datasets and PIDray datasets demonstrates that our detection mAP achieves 88.02 and 68.2, respectively. Extensive experiments conducted on publicly available datasets provide substantial evidence that our proposed network significantly improves the detection of prohibited items compared to state-of-the-art methods.