Temporal Fusion Based Mutli-scale Semantic Segmentation for Detecting Concealed Baggage Threats

TL;DR

This paper introduces a novel temporal fusion multi-scale neural network for detecting concealed threats in baggage X-ray scans, leveraging sequential imagery to improve accuracy in identifying hidden contraband.

Contribution

It presents a new temporal fusion encoder-decoder architecture that effectively utilizes sequential X-ray images for enhanced detection of concealed objects, a novel approach in baggage security.

Findings

Outperforms existing methods on GDXray dataset

Effectively detects highly concealed contraband

Utilizes temporal information for improved accuracy

Abstract

Detection of illegal and threatening items in baggage is one of the utmost security concern nowadays. Even for experienced security personnel, manual detection is a time-consuming and stressful task. Many academics have created automated frameworks for detecting suspicious and contraband data from X-ray scans of luggage. However, to our knowledge, no framework exists that utilizes temporal baggage X-ray imagery to effectively screen highly concealed and occluded objects which are barely visible even to the naked eye. To address this, we present a novel temporal fusion driven multi-scale residual fashioned encoder-decoder that takes series of consecutive scans as input and fuses them to generate distinct feature representations of the suspicious and non-suspicious baggage content, leading towards a more accurate extraction of the contraband data. The proposed methodology has been thoroughly tested using the publicly accessible GDXray dataset, which is the only dataset containing temporally linked grayscale X-ray scans showcasing extremely concealed contraband data. The proposed framework outperforms its competitors on the GDXray dataset on various metrics.