Raster Navigational Chart Data Extraction and Region of Interest
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Raster navigational charts (RNCs) are difficult for computers and humans to interpret due to their dense information, necessitating an improved method for extracting relevant data.
Innovation Solution
A method using computer vision algorithms to extract color, text, and symbol data from RNCs or electronic navigational charts (ENCs), creating data vectors that identify geographical features and their locations, allowing for user-defined regions of interest with georeferenced latitude and longitude information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If raster navigational charts contain dense information to provide comprehensive navigational data, then the completeness of navigational information is improved, but the ease of interpretation by computers and humans deteriorates
Solution Approach 1:
The patent segments the dense RNC information into distinct extractable elements (color data, text data, symbol data) and organizes them into structured data vectors. This segmentation transforms the uninterpretable dense chart into organized data components that can be systematically processed by computers while maintaining comprehensive navigational information.
Solution Approach 2:
The patent introduces an intermediary processing layer consisting of computer vision algorithms and data extraction systems. This intermediary converts the dense visual information in RNCs into structured digital data vectors, serving as a bridge between the human-readable chart format and machine-processable data formats, thereby improving interpretability without losing information completeness.
2Extent of automation
If computer vision algorithms extract color, text and symbol data from single-layer RNCs to create machine-readable data vectors, then the machine-readability of navigational charts is improved, but the complexity of data extraction and processing increases
Solution Approach 1:
The patent creates a universal data extraction system that handles multiple data types (color, text, symbols) and multiple chart types (single-layer RNCs, ENCs) through a single integrated framework. The same computer vision algorithms and processing pipeline work across different navigational chart formats, reducing overall system complexity while achieving broad machine-readability.
Solution Approach 2:
The patent transforms the navigational chart data from visual parameters (pixel colors, spatial arrangements) into standardized data vector parameters that represent geographical features. This parameter transformation simplifies the data structure and makes it machine-readable while the extraction process itself remains automated through computer vision techniques.
3Device complexity
If the method extracts data from single-layer RNCs without requiring multiple layers of information, then the simplicity of processing is improved, but the completeness of extracted geographical information may deteriorate
Solution Approach 1:
The patent enables single-layer RNCs to be self-sufficient by extracting all necessary geographical information directly from the single chart layer using computer vision algorithms. The system identifies and extracts color, text, and symbol data that collectively provide complete geographical information without requiring external reference layers or additional data sources, thereby maintaining information completeness while simplifying processing.
Data Source
AI summary
A method for extracting data from a single-layer raster navigational chart (RNC) comprising: using a computer vision algorithm to extract color, text and symbol data from the RNC, storing the color, text, and symbol data in a database, and building an RNC data vector based solely on the color, text, and symbol data of the RNC, wherein the RNC data vector identifies geographical features shown in the RNC and a location of the geographical features' corresponding pixels in the RNC; and drawing a region of interest on the navigational chart based on user input and the RNC data vector, wherein a perimeter of the region of interest is georeferenced with latitude and longitude information.