Bridge Location Detection via Side Barrier Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual evaluation of bridge start and end locations from image data is prone to errors, time-consuming, and inefficient, making it unsuitable for accurate and consistent determination in mapping and navigation systems.

Innovation Solution

A computer-implemented method that identifies side barrier segments in image data, such as satellite or LiDAR data, to determine the start and end locations of bridges by analyzing characteristic differences, enabling precise location determination for mapping and navigation systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual evaluation is used to determine bridge start and end locations, then human judgment can be applied to complex image data, but the process is time-consuming and error-prone

Engineering Contradiction:

Improveaccuracy of bridge location determinationVSAvoidtime required for manual evaluation

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual human evaluation with an automated computer vision system that uses image segmentation algorithms to detect side barrier segments and determine bridge locations. The system processes satellite or aerial imagery automatically, eliminating the need for manual analysis while maintaining or improving detection accuracy through algorithmic processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the image data itself to provide the information needed for bridge location determination through automated analysis. The computer vision system independently processes the imagery, identifies side barrier characteristics, and outputs bridge start and end locations without requiring human intervention or expert judgment.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual evaluation is used to determine bridge start and end locations, then contextual understanding can be applied, but the process is inefficient and inconsistent

Engineering Contradiction:

Improveconsistency of bridge location determinationVSAvoidefficiency of bridge location determination

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces manual evaluation with automated computer vision algorithms that consistently apply the same detection criteria across all image data. The image segmentation system processes multiple images systematically, ensuring uniform and reproducible results that improve consistency while increasing productivity through automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated detection is used to determine bridge start and end locations, then processing speed increases, but detection accuracy may decrease due to algorithm limitations

Engineering Contradiction:

Improvespeed of bridge location determinationVSAvoidprecision of bridge start and end location

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies image segmentation to divide the complex imagery into distinct regions and identify specific side barrier segments. By segmenting the images and analyzing individual barrier segments' characteristics, the system maintains high measurement precision while achieving automated processing speed. The segmentation allows detailed analysis of each segment's properties to accurately determine bridge boundaries.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system detects bridge locations by identifying characteristic color or visual changes in side barrier segments across the image data. These color or appearance changes serve as reliable indicators for determining bridge start and end points, enabling automated detection to achieve both speed and precision by relying on distinct visual signatures rather than complex algorithmic inference.

Inventive Principle:

Principle #32Color changes

Data Source

PatentUS11610332B2Method and apparatus for detecting a start location and end location of a bridge

Publication Date: 2023.03.21 HERE GLOBAL BV

AI summary

A method, apparatus and computer program product for detecting a start location and an end location of a bridge are described herein. In the context of a method, one or more sequences of images, at least one sequence of images corresponding with a side barrier portion of the bridge, may be identified from image data corresponding with a probable location of the bridge. Each side barrier portion may comprise a plurality of side barrier segments. The method may identify one or more characteristics of the plurality of side barrier segments. The method may determine the start location and the end location of the bridge based at least in part by identifying characteristic differences of the plurality of side barrier segments. The method may cause transmission of information corresponding with the start location and the end location of the bridge for updating a mapping or navigation system.