Ship Identification via Reference Silhouette Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ship identification methods, such as those using quantitative comparison of invariant moments and 3D models, suffer from inaccuracy due to information loss and high construction effort, necessitating a more robust and reliable approach.
Innovation Solution
A method generating a set of reference silhouette images from various viewpoints using perspective projections, normalized image scales, run length encoding, and blurring transitions to enhance matching robustness and speed, implemented in a ship identification system with a camera, storage, and data processing system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If quantitative comparison of invariant moments is used to automate ship identification, then automation is improved, but measurement precision deteriorates due to information loss and perspective deviations
Solution Approach 1:
The patent creates a digital reference manual containing stored silhouette images of reference ships from multiple viewpoints and lighting conditions. Instead of comparing complex invariant moments, the system directly compares the captured ship silhouette against this pre-built image database, preserving all visual information while automating the identification process through pattern matching.
Solution Approach 2:
The reference manual is constructed in advance with silhouette images of various ships from multiple angles and conditions. This preliminary preparation allows the identification system to quickly compare against pre-processed reference data without performing complex real-time analysis, thereby maintaining both automation and precision.
2Measurement precision
If KEOD system with 3D models and contour line comparison is used, then measurement precision is improved, but device complexity increases due to considerable effort in constructing 3D models and databases
Solution Approach 1:
Instead of constructing complex 3D models and databases as in the KEOD system, the patent creates a simpler digital reference manual with 2D silhouette images. This copying approach captures the essential visual characteristics of ships without requiring elaborate 3D reconstruction, thereby maintaining identification precision while significantly reducing system complexity.
Solution Approach 2:
The patent extracts only the essential silhouetted outlines of ships from their full 3D complexity. By focusing solely on the 2D silhouette representation rather than complete 3D models, the system achieves sufficient identification accuracy with much reduced data complexity and processing requirements.
3Reliability
If reference silhouette images from multiple viewpoints are generated, then reliability is improved through robust matching, but loss of time increases due to larger database size
Solution Approach 1:
The patent segments the reference database into multiple viewpoint-specific silhouette image sets. By organizing reference images according to their viewpoint categories, the system can selectively compare only relevant viewpoint matches rather than searching the entire database, thereby maintaining high reliability through multiple viewpoint verification while reducing overall processing time through targeted comparisons.
Data Source
Figure 1~2
Figure 3a~3b
Figure 4
AI summary
Identification of ships from camera images is performed by computing sets of reference silhouette images for respective reference ships for use to match the reference silhouette images with a camera image of an unidentified ship. A computer forms the set of the reference silhouette images for a reference ship is performed automatically by a processing system on the basis of at least one silhouette image of the respective reference ship. The computer generates a three dimensional model of the reference ship that represents distances of an outer surface of the reference ship to a plane on which the captured silhouette image has been mapped, the three dimensional model representing the distances as a function of position in said plane. A deck line of the reference ship is detected based on the camera image. The represented distances to the outer surface are set and/or adapted dependent on position in said plane relative to the detected deck line. The represented distances for positions in said plane below the detected deck line are set and/or adapted convergently toward a bow of the ship in the silhouette image. The reference silhouette images are generated by computing perspective projections of the three dimensional model onto image planes for respective viewpoints in a three dimensional array of viewpoints in ranges of distance relative to the reference ship, horizontal direction from the reference ship to the viewpoint and height relative to the reference ship and in the three dimensional model.