Oblique Image Validation for Map Data Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map generation technologies face challenges in accurately validating and correcting errors in map data due to limitations in top-down orthographic aerial imagery, which cannot capture three-dimensional attributes like altitude and occluding structure positioning, making it difficult to identify inaccuracies without ground truth.
Innovation Solution
The use of oblique images taken at angles other than straight down, which provide a wide field of view and capture three-dimensional features, allowing for the analysis of pixel statistics to detect and correct errors in vector data, digital elevation maps, and three-dimensional model data through learning algorithms and classifiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If top-down orthographic aerial imagery is used for map validation, then the validation process is simple and efficient, but three-dimensional attributes like altitude and building heights cannot be captured
Solution Approach 1:
The patent transitions from two-dimensional orthographic aerial imagery to three-dimensional oblique imagery captured by UAVs. This dimensional change enables the capture of altitude, building heights, and occluding structure positioning while maintaining validation efficiency through automated processing of the additional dimensional data.
2Measurement precision
If oblique images are used to capture three-dimensional attributes, then altitude and building height accuracy improve, but the complexity of data processing increases
Solution Approach 1:
The patent replaces complex manual measurement and validation processes with automated machine learning algorithms that process oblique imagery. The system uses computer vision and deep learning models to automatically extract three-dimensional attributes, measure building heights, and validate map data, substituting mechanical measurement methods with intelligent automated processing.
3Measurement precision
If ground truth data is available for validation, then map data accuracy can be verified, but ground truth is often unavailable in most mapping scenarios
Solution Approach 1:
The patent implements a self-validation system where the oblique imagery itself serves as the ground truth for validating map data. The system extracts three-dimensional information directly from the oblique images and uses this extracted information to verify and correct map data, eliminating the need for external ground truth data sources.
Data Source
AI summary
Technologies are described herein for validating and correcting map data using oblique images or aerial photographs taken at oblique angles to the earth's surface. Pixels within oblique images can be analyzed to detect, validate, and correct other sources of data used in generating maps such as vector data, elevation maps, projection parameters, and three-dimensional model data. Visibility and occlusion information in oblique views may be analyzed to reduce errors in either occluding or occluded entities. Occlusion of road segments due to foliage, z-ordering of freeways, tunnels, bridges, buildings, and other geospatial entities may be determined, validated, and corrected. A learning algorithm can be trained with image-based descriptors that encode visible data consistencies. After training, the algorithm can classify errors and inconsistencies using combinations of different descriptors such as color, texture, image-gradients, and filter responses.