Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling

TL;DR

This paper introduces an occlusion-aware segmentation method for prohibited items in security X-ray images, utilizing SAM and explicit occlusion modeling to improve detection accuracy in complex overlapping scenarios.

Contribution

The paper presents a novel occlusion-aware bilayer model and occlusion-annotated datasets for improved prohibited item segmentation in X-ray images.

Findings

Effective occlusion modeling improves segmentation accuracy.

Integration of SAM enhances generalization to various prohibited items.

New datasets facilitate research on occlusion in X-ray image segmentation.

Abstract

Instance segmentation of prohibited items in security X-ray images is a critical yet challenging task. This is mainly caused by the significant appearance gap between prohibited items in X-ray images and natural objects, as well as the severe overlapping among objects in X-ray images. To address these issues, we propose an occlusion-aware instance segmentation pipeline designed to identify prohibited items in X-ray images. Specifically, to bridge the representation gap, we integrate the Segment Anything Model (SAM) into our pipeline, taking advantage of its rich priors and zero-shot generalization capabilities. To address the overlap between prohibited items, we design an occlusion-aware bilayer mask decoder module that explicitly models the occlusion relationships. To supervise occlusion estimation, we manually annotated occlusion areas of prohibited items in two large-scale X-ray image segmentation datasets, PIDray and PIXray. We then reorganized these additional annotations together with the original information as two occlusion-annotated datasets, PIDray-A and PIXray-A. Extensive experimental results on these occlusion-annotated datasets demonstrate the effectiveness of our proposed method. The datasets and codes are available at: https://github.com/Ryh1218/Occ