Image processing method for processing plurality of camera images of ship cleaning robot to generate one image, computer readable recording medium, computer program, and robot control method using same

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing ship cleaning robots face challenges in efficiently identifying and cleaning the hull surface due to limited identification distances and the need for manual control of multiple cameras, leading to operator fatigue and increased cleaning time.

Innovation Solution

An image processing method that merges images from multiple cameras into a single wide top-view image using perspective transformation and correction techniques, along with artificial intelligence for controlling the robot's speed and brush rotation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If one camera is used to cover the entire hull surface, then device complexity is reduced, but identification distance becomes insufficient and cleaning efficiency decreases

Engineering Contradiction:
Improvenumber of camerasVSAvoididentification distance
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The hull surface is divided into multiple regions, each monitored by a dedicated camera. The first camera monitors the first region, the second camera monitors the second region, and so on. This segmentation allows each camera to focus on a specific area, ensuring sufficient identification distance for each region without requiring an excessive number of cameras system-wide.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If multiple cameras are placed at intervals to improve identification distance, then measurement precision improves, but device complexity and operator fatigue increase

Engineering Contradiction:
Improveidentification distanceVSAvoidnumber of cameras
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The monitoring system is segmented into multiple independent camera units, each responsible for a specific region. This allows the system to achieve comprehensive coverage with appropriate identification distances without requiring a single complex multi-camera assembly, thereby reducing overall device complexity while maintaining measurement precision.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-dimensional view (one camera looking at the entire hull) to a multi-dimensional distributed monitoring system. By placing cameras at different positions along the hull, the system creates a spatial distribution of monitoring points, effectively using the longitudinal dimension of the hull to reduce the number of cameras needed while maintaining identification distance.

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

3Measurement precision

If multiple cameras are used to cover the entire hull surface, then identification distance improves, but operator fatigue increases due to controlling multiple cameras

Engineering Contradiction:
Improveidentification distanceVSAvoidoperator fatigue
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

Multiple camera feeds are merged into a single integrated display system. The processor combines the image data from the first camera, second camera, and subsequent cameras into a unified visual representation that the operator can control with a single interface. This merging eliminates the need for the operator to switch between or manually control multiple separate camera views, significantly reducing operator fatigue while maintaining the identification distance benefits of multiple cameras.

Inventive Principle:
Principle #5Merging (Combining)

4Measurement precision

If the cleaning boundary line is positioned near the center camera, then identification distance is sufficient, but cleaning time increases significantly

Engineering Contradiction:
Improveidentification distanceVSAvoidcleaning time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The cleaning process is segmented into multiple parallel operations, with each camera region having its own cleaning boundary line and associated cleaning brush. This allows simultaneous cleaning of multiple hull regions, drastically reducing total cleaning time while each individual camera maintains sufficient identification distance for its assigned region.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically coordinates the movement of multiple cleaning brushes with the monitoring of multiple cameras. As the robot moves along the hull, the cleaning boundary lines and brush positions are dynamically adjusted to match the camera coverage regions, enabling continuous and efficient cleaning without the time loss associated with repositioning a single central camera and brush.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4319152B1Image processing method for processing plurality of camera images of ship cleaning robot to generate one image, computer readable recording medium, computer program, and robot control method using same
Publication Date: 2025.12.24 TAS GLOBAL
  • EP4319152B1 patent drawingFigure 1
  • EP4319152B1 patent drawingFigure 2
  • EP4319152B1 patent drawingFigure 3(a)~3(d)

AI summary

Disclosed is an image processing method of processing a plurality of images into a single image, including: obtaining at least a left image, a center image, and a right image from a plurality of cameras arranged in a row; generating a left top-view image, a center top-view image, and a right top-view image based on the left image, the center image, and the right image, respectively; generating one wide top-view image by merging the left top-view image, the center top-view image, and the right top-view image; and generating and outputting the wide top-view image as a final wide image. Thus, the images from the plurality of cameras are merged into a single image, thereby reducing fatigue of a robot operator.