AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection

TL;DR

AO-DETR introduces novel strategies to improve prohibited item detection in overlapping X-ray images by enhancing feature extraction and localization accuracy, outperforming existing detectors on standard datasets.

Contribution

The paper proposes AO-DETR with CSA and LFD strategies, addressing overlapping issues in X-ray prohibited item detection, and demonstrates superior performance over state-of-the-art methods.

Findings

Outperforms existing detectors on PIXray and OPIXray datasets

Enhances feature extraction for overlapping objects

Improves localization of blurry edges in X-ray images

Abstract

Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an Anti-Overlapping DETR (AO-DETR) based on one of the state-of-the-art general object detectors, DINO. Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the Category-Specific One-to-One Assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground-background features. To address the edge blurring problem caused by overlapping phenomena, we propose the Look Forward Densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray and OPIXray datasets demonstrate that the proposed method surpasses the state-of-the-art object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be released at https://github.com/Limingyuan001/AO-DETR-test.