Power Line Extraction Using Reference Data Constraints

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing power line extraction systems face inefficiencies due to the need for extensive computational resources and human error in identifying accurate locations of power lines from inaccurate reference data, leading to costly on-site inspections and potential vegetation interaction risks.

Innovation Solution

A computer-implemented method that uses reference data to constrain the analysis of point cloud data, focusing on candidate data points that form a line parallel to the power line, employing techniques like the Hough Transform and RANSAC to efficiently extract and georectify power line segments, reducing computational costs and improving accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional power line extraction systems analyze all point cloud data without constraints, then comprehensive power line detection is achieved, but computational resources and processing time are excessively consumed

Engineering Contradiction:

Improvepower line location accuracyVSAvoidcomputational efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary actions by using reference data to pre-determine candidate regions and orientation angles before the main extraction process. The Hough Transform is applied to reference data first to obtain candidate orientation angles, which then constrain the subsequent analysis of point cloud data, reducing the search space and computational load while maintaining detection accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention applies local quality by focusing computational resources only on relevant regions of the point cloud data. By using reference data to identify candidate regions and by constraining analysis to specific orientation angles derived from reference data, the system processes only the necessary local portions of the data rather than analyzing the entire point cloud uniformly

Inventive Principle:

Principle #3Local quality

2Reliability

If reference data with inaccurate locations is used directly, then existing power line positions are obtained, but the locations are inaccurate leading to potential vegetation interaction risks

Engineering Contradiction:

Improvepower line location reliabilityVSAvoidvegetation interaction risk

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system changes parameters by using reference data to extract orientation angles and candidate regions, then applying these as constraints to find updated power line positions in the point cloud data. The Hough Transform parameters (orientation angles) derived from reference data are used to guide the extraction process, transforming inaccurate location data into useful directional constraints that lead to accurate position determination

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The invention uses the Hough Transform and candidate orientation angles as intermediaries between the inaccurate reference data and the final accurate power line positions. The reference data serves as an intermediary that provides orientation information, which then mediates the extraction process to find precise locations in the point cloud, bridging the gap between inaccurate reference positions and accurate current positions

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If on-site inspections are conducted to verify power line locations, then accurate locations are obtained, but the process is expensive and time-consuming

Engineering Contradiction:

Improvepower line location accuracyVSAvoidinspection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The invention replaces the mechanical system of on-site physical inspections with a computational system. By using point cloud data processing combined with Hough Transform and reference data constraints, the system achieves accurate power line location determination through automated computational methods, eliminating the need for time-consuming and expensive field inspections while maintaining high accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11308656B1Power line extraction using reference data

Publication Date: 2022.04.19 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Aspects of the invention include receiving a point cloud data set describing a target area. Receiving a first parameter describing a power line segment at an original location within the target area. Using the processor to extract from the point cloud data set a power line segment at an updated location distinct from the original location, wherein analysis of each candidate data point of the point cloud data set is constrained by the first parameter, and wherein the first parameter causes the power line segment at the updated location to be parallel with the power line segment at the original location. Generating a vector describing the updated location of the power line segment with respect to geospatial coordinates of the target area.