Graphic Model Generation for Navigation Databases

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The collection and processing of geographic data for navigation systems are time-consuming and intricate, requiring efficient methods to expedite the development of graphic models of geographic objects like road signs and path features.

Innovation Solution

A method involving the reception of images, performing scale-invariant feature transforms, matching components with a data library, and generating graphic models by retrieving symbols and text data from navigation databases, with optional steps including image segmentation, optical character recognition, and binary matching to enhance the model's accuracy and completeness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional manual methods are used to collect and process geographic data for navigation systems, then the accuracy and completeness of graphic models can be maintained through human review, but the process becomes time-consuming and intricate

Engineering Contradiction:
Improvedata processing speedVSAvoidprocessing complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the geographic object into multiple scale-invariant components through scale-invariant feature transform. Each component can be independently processed, matched with reference components, and assembled into a graphic model. This segmentation enables parallel processing of different components, significantly improving processing speed while maintaining systematic organization to manage complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates graphic models as simplified copies of actual geographic objects by matching scale-invariant components with reference components from a library. Instead of processing entire complex images, the system works with extracted feature components that capture essential characteristics, reducing processing complexity while preserving key identifying features for accurate representation in navigation databases.

Inventive Principle:
Principle #26Copying

2Measurement precision

If scale-invariant feature transform is performed on geographic objects, then the graphic models become more accurate and usable for navigation, but the processing time and computational complexity increase

Engineering Contradiction:
Improvefeature matching accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs scale-invariant feature transform to extract components before the matching process. By pre-processing the geographic object to identify and extract scale-invariant components in advance, the system prepares data structures that facilitate faster comparison and matching with reference components, reducing the time required during the actual model construction phase while maintaining high matching accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent transforms geographic object features into scale-invariant parameters that remain consistent across different scales. This parameter transformation allows for efficient comparison and matching operations, as the scale-invariant parameters reduce the dimensionality of the search space while preserving discriminative features, thereby improving accuracy without proportionally increasing processing time.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If multiple processing steps including image segmentation and optical character recognition are implemented, then the completeness of geographic data is improved, but the intricacy and computational requirements increase

Engineering Contradiction:
Improvedata completenessVSAvoidsystem intricacy
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges multiple processing functions into a unified scale-invariant feature transform framework. Image segmentation, feature extraction, and component identification are integrated into a single coherent process that operates on scale-invariant parameters. This merging reduces system intricacy by eliminating the need for separate processing pipelines while maintaining comprehensive data extraction for complete geographic models.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP2273337B1Generating a graphic model of a geographic object and systems thereof
Publication Date: 2018.04.18 HERE GLOBAL BV
  • EP2273337B1 patent drawingFigure 1
  • EP2273337B1 patent drawingFigure 2~3
  • EP2273337B1 patent drawingFigure 4

AI summary

Systems, devices, features, and methods for constructing a graphic model of a geographic object, such as a road sign or features thereof, from an image, such as, for example, to develop a navigation database are disclosed. For example, one method comprises receiving a plurality of images of regions, such as of roads or paths. An image of the plurality of images is identified. A process to determine scale-invariant components of a geographic object in the identified image may be performed. Other processes, such as generating a dictionary to facilitate optical character recognition may be performed. A graphic model of the geographic object is generated based on the scale-invariant components and/or the optical character recognition. The generated graphic model may be associated with a navigation or map database.