3D CT Security Inspection Target Positioning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing security inspection systems using three-dimensional CT images face challenges in quickly marking suspected objects, as current methods are inefficient for human operators to identify and select targets in these complex images.

Innovation Solution

A method and system that display a three-dimensional CT image, allow user selection of areas, generate sets of objects in a depth direction, and determine the target object based on point cloud information, such as the object with the greatest number of points or closest to the viewpoint, facilitating quick identification of suspected objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a human operator manually marks a suspected object on a three-dimensional CT image, then the inspection can be performed, but the process is time-consuming and inefficient

Engineering Contradiction:

Improveinspection efficiencyVSAvoidtime for marking suspected object

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system enables automatic target object determination through point cloud information processing. The data processor automatically separates point cloud information, identifies candidate objects, and determines the target object based on predetermined criteria without requiring manual marking by operators, thus significantly improving inspection efficiency

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical marking process with an automated computational system. The data processor uses point cloud separation algorithms and automated object identification to substitute the human operator's manual marking action, reducing time consumption while maintaining inspection capability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If the system processes complex three-dimensional CT images, then accurate object identification is achieved, but the complexity of the process increases

Engineering Contradiction:

Improveaccuracy of target object identificationVSAvoidcomplexity of image processing process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex three-dimensional CT image processing into distinct modular steps: point cloud information recording during rendering, point cloud separation to identify different objects, candidate object determination, and target object selection based on predetermined criteria. This segmentation simplifies the overall complex process while maintaining accurate object identification

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces point cloud information as an intermediary representation between the raw three-dimensional CT image data and the final target object identification. This intermediary form simplifies the processing by converting complex image data into discrete point cloud clusters that are easier to separate and analyze automatically

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10297050B2Methods for positioning a target in a three-dimensional CT image and CT systems for security inspection

Publication Date: 2019.05.21 NUCTECH CO LTD

AI summary

Disclosed is a method for positioning a target in a three-dimensional CT image and a CT system for security inspection. The method includes: displaying a three-dimensional CT image; receiving a selection by a user of at least one area of the three-dimensional CT image at a viewing angle; generating at least one set of three-dimensional objects in a depth direction based on the selection; and determining a target object from the set. With the above technical solutions, the user may be facilitated in marking a suspected object in a CT image in a quick manner.