Freight Container Damage Detection Using Multi-Angle Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Freight containers often go undetected for damages during handling in large terminals due to inefficiencies in manual inspection processes, posing safety risks and potential hazards from structural deformations or cargo shifts during transportation.

Innovation Solution

A system utilizing multiple image capturing units positioned at different angles to capture images of freight container parts, combining images to visualize damages from various viewing angles, including those deviating from and perpendicular to the container's structure, with image analysis units to detect and display damage information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection is used to detect damages in freight containers, then inspection accuracy can be maintained, but inspection efficiency and productivity deteriorate due to the enormous number of containers and incessant demands

Engineering Contradiction:
Improvedamage detection accuracyVSAvoidinspection efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual mechanical inspection with an automated image-based detection system. Image capturing units take photographs of containers, and image analysis units process these images to automatically detect damages such as deformations, holes, and rust. This substitution of mechanical human inspection with automated optical and computational systems dramatically improves productivity while maintaining or enhancing detection accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates visual copies (images) of the container surfaces and analyzes these copies to detect damages. Instead of physically examining each container, the system captures images and processes them computationally, enabling rapid inspection of numerous containers without sacrificing detection capability.

Inventive Principle:
Principle #26Copying

2Device complexity

If images are captured only from perpendicular direction, then device complexity is reduced, but measurement precision deteriorates as damages detectable only from angled views are missed

Engineering Contradiction:
Improvenumber of image capturing unitsVSAvoiddamage detection completeness
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent transitions from single-direction (perpendicular only) imaging to multi-directional imaging by adding image capturing units positioned at different angles. This dimensional expansion in the imaging approach allows the system to detect damages that are invisible from a single perpendicular viewpoint, such as surface deformations and structural issues that manifest only at oblique angles.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The inspection system is segmented into multiple image capturing units, each responsible for capturing images from specific angles and positions. This segmentation allows comprehensive coverage of the container surface from multiple perspectives simultaneously, ensuring that damages visible only from certain angles are not missed.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20230005121A1Method and system for detecting damages in freight container
Publication Date: 2023.01.05 VISY
  • US20230005121A1 patent drawing
  • US20230005121A1 patent drawing
  • US20230005121A1 patent drawing

AI summary

A method of detecting damages in a freight container, comprising capturing a first image of a part of the freight container at an angle deviating from a perpendicular direction in respect of the part of the container, capturing a second image of the same part of the container at an angle substantially perpendicular in respect of the same part of the container, analysing the first and second images for detecting a damage in the part of the container, and in response to detecting the damage in the part of the container providing a damage information image regarding to the part of the container, the damage information image being an image based on the second image regarding to the respective part of the container and including damages detected in at least one of the respective first image or this second image.Also, a system for detecting damages in a freight container.