Automated Bridge Boundary Detection Using Dual Masking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current three-dimensional reconstruction algorithms face challenges in accurately reconstructing bridges due to the textureless and constantly moving nature of water surfaces, leading to noisy and poorly reconstructed water surfaces, which can result in bridges being misidentified as water and failing to be reconstructed.

Innovation Solution

A method is developed to determine bridge boundaries by using a wide bridge mask and a narrow bridge mask based on road and water masks, followed by line feature detection and oriented bounding box analysis to accurately isolate and extract bridge imagery, which can then be used for three-dimensional modeling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual water mask is used to identify water locations, then water surface reconstruction quality is improved, but mask precision deteriorates due to time-consuming manual creation

Engineering Contradiction:

Improvewater surface reconstruction qualityVSAvoidmask precision

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces manual mechanical mask creation with an automated computer vision system that uses image processing algorithms to generate water masks automatically, eliminating the trade-off between manual effort and precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically generating water masks through algorithmic processing of satellite imagery, without requiring manual intervention while maintaining high precision through automated feature detection

Inventive Principle:

Principle #25Self-service

2Loss of time

If imprecise water mask is used, then processing time is reduced, but bridge reconstruction accuracy deteriorates due to bridges being misidentified as water

Engineering Contradiction:

Improvemask creation timeVSAvoidbridge reconstruction accuracy

Core Design Contradiction:

Loss of timeVSManufacturing precision

Solution Approach 1:

The patent substitutes manual mask creation with automated computer vision algorithms that rapidly generate precise water masks, simultaneously reducing time loss and maintaining high bridge reconstruction accuracy through algorithmic distinction between water and bridge features

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary automated mask generation process that acts as a mediator between raw satellite imagery and bridge reconstruction, using image processing algorithms to accurately distinguish water from bridges before reconstruction occurs

Inventive Principle:

Principle #24Intermediary (Mediator)

3Extent of automation

If road mask intersection with water mask is used to generate bridge mask, then bridge identification is automated, but mask accuracy deteriorates due to lack of road width information and mask inaccuracies

Engineering Contradiction:

Improvebridge identification automationVSAvoidbridge mask accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent performs preliminary action by enhancing road mask data with width information before intersecting with water mask, and by pre-processing satellite imagery to improve feature detection accuracy, thereby improving bridge mask precision before the actual bridge identification automation occurs

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies parameter changes by incorporating road width parameters into the mask generation process and adjusting image processing parameters to enhance feature detection, transforming the insufficient road mask into a more accurate bridge identification tool

Inventive Principle:

Principle #35Parameter changes

4Speed

If traditional reconstruction algorithms are applied to water surfaces, then processing speed is maintained, but reconstruction quality deteriorates due to textureless and moving water surfaces causing large pixel correspondence errors

Engineering Contradiction:

Improvereconstruction processing speedVSAvoidwater surface reconstruction quality

Core Design Contradiction:

SpeedVSManufacturing precision

Solution Approach 1:

The patent extracts water surface regions from the overall scene using automated water mask generation, isolating these problematic areas for special handling or exclusion from standard reconstruction algorithms, thereby preventing them from degrading overall reconstruction quality while maintaining processing speed

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS9196050B2Image-based bridge identification and boundary detection

Publication Date: 2015.11.24 GOOGLE LLC

AI summary

Systems and methods for image-based bridge identification and boundary detection are provided. One example method includes determining, by one or more computing devices, a wide bridge mask and a narrow bridge mask based at least in part on a road mask and a water mask. The method includes selecting, by the one or more computing devices, a portion of an image depicting a bridge based at least in part on the wide bridge mask and the narrow bridge mask. The method includes identifying, by the one or more computing devices, a plurality of line features included in the portion of the image depicting the bridge. The method includes determining, by the one or more computing devices, a bridge boundary in the portion of the image based at least in part on the plurality of line features. One example system includes a bridge image extraction module and a bridge boundary determination module.