Automated Pole Extraction From Optical Imagery With 3D Triangulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mapping and navigation service providers face challenges in determining the geolocations and attributes of poles and other objects across large geographic areas due to their ubiquity and large numbers, which traditional methods are labor and time-intensive.
Innovation Solution
A system utilizing machine learning models to process optical imagery, detect pole-like objects through bounding boxes and semantic keypoints, and apply photogrammetric triangulation to determine three-dimensional coordinates and attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual methods are used to determine geolocations and attributes of poles, then measurement precision can be maintained, but productivity is significantly reduced and loss of time increases
Solution Approach 1:
The patent replaces manual mechanical inspection methods with an automated machine learning system that processes optical imagery. The system uses trained models to automatically detect, classify, and extract geolocation data of poles from images, substituting human labor with computational algorithms that operate continuously without fatigue, thereby dramatically increasing productivity and reducing processing time
Solution Approach 2:
The patent creates digital copies of pole objects from optical imagery through automated detection and 3D coordinate generation. The machine learning model generates synthetic representations and geospatial data that replicate the physical pole's location and attributes, enabling rapid extraction and mapping without physical measurement, thus improving efficiency while maintaining accuracy
2Productivity
If manual extraction methods are used, then measurement precision can be maintained, but device complexity remains low, however productivity decreases
Solution Approach 1:
The patent implements a universal machine learning platform that can detect and extract multiple types of cartographic features (poles, buildings, vegetation, roads) from optical imagery using a single integrated system. The machine learning model is trained to recognize diverse object classes and performs multiple functions including detection, classification, and geolocation, eliminating the need for separate specialized tools for each feature type, thereby increasing productivity despite the inherent complexity of the multi-functional system
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Automates the extraction of pole geolocations and attributes, reducing resource intensity and enhancing mapping efficiency across large areas.
Implementation Method 1
processing a plurality of images using a machine learning model to generate a plurality of redundant observations of a pole-like object (or other object) respectively depicted in the plurality of images
Implementation Method 2
performing a photogrammetric triangulation of the plurality of redundant observations to determine three-dimensional coordinate data of the pole-like object
Data Source
AI summary
An approach is provided for pole extraction from optical imagery. The approach involves, for instance, processing a plurality of images using a machine learning model to generate a plurality of redundant observations of a pole-like object and/or their semantic keypoints respectively depicted in the plurality of images. The approach also involves performing a photogrammetric triangulation of the plurality of redundant observations to determine three-dimensional coordinate data of the pole-like object and/or their semantic keypoints. The approach further involves providing the three-dimensional coordinate data of the pole-like object as an output.