CT Shape Feature Extraction for Security Inspection False Alarm Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current security inspection methods using Dual Energy Computed Tomography (DECT) struggle with false alarms due to overlapping perspective structures and metal interference, limiting the effective detection of explosives or suspicious objects.
Innovation Solution
The method involves extracting shape features from 3D volume data in a CT system by calculating depth projection images and symmetry metrics, generating a shape feature parameter, and combining it with physical property information to improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If material property-based detection is used in DECT, then detection capability for explosives is improved, but false alarm rate increases due to artifacts, metal interference, and non-suspicious objects
Solution Approach 1:
The detection process is segmented into two independent stages: shape feature extraction (using symmetry metrics and depth projection) and material property analysis. This segmentation allows shape-based pre-screening to filter out false alarms before material property analysis, resolving the contradiction by separating the functions that cause interference from those that detect explosives
Solution Approach 2:
The invention transitions from 2D DR image analysis to 3D CT volume analysis by computing depth projection images and symmetry metrics in three-dimensional space. This dimensional change enables the system to distinguish objects based on their 3D shape characteristics, adding a new detection dimension that reduces false alarms while maintaining detection accuracy
2Measurement precision
If 3D volume data processing is performed, then shape feature extraction accuracy is improved, but computational complexity increases
Solution Approach 1:
The invention extracts only the essential shape features (symmetry metrics and depth projection images) from the 3D volume data, rather than processing the entire 3D dataset. By taking out and analyzing only the critical geometric characteristics, the system achieves accurate shape feature extraction while significantly reducing computational complexity compared to full 3D analysis
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces the false alarm rate by utilizing shape features to differentiate between suspicious and non-suspicious objects, enhancing the detection of explosives and improving the overall accuracy of security inspections.
Implementation Method 1
acquiring slice data of luggage under inspection with the CT system
Implementation Method 2
generating, from the slice data, 3-dimensional (3D) volume data of at least one object in the luggage
Data Source
AI summary
Methods for extracting a shape feature of an object and security inspection methods and apparatuses. Use is made of CT's capability of obtaining a 3D structure. The shape of an object in an inspected luggage is used as a feature of a suspicious object in combination with a material property of the object. For example, a false alarm rate in detection of suspicious explosives may be reduced.