Street-Level Imagery Selection via Road Network Graph Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge lies in efficiently organizing and retrieving street-level panoramic views while addressing storage and serving capacity constraints, ensuring that the displayed images cover the entire geographic area and are of high quality, which existing technologies fail to achieve due to the large amount of information collected.
Innovation Solution
The solution involves creating a road network graph where panoramas are attached to specific positions, dividing the graph into selection paths, and prioritizing panoramas for publication based on their quality and location, using a computer-implemented method that selects panoramas for interior road segments and intersections, optimizing the selection process using dynamic programming and Markov Chains to ensure efficient coverage and quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all collected panoramas are stored and served, then complete geographic coverage and best available quality are achieved, but storage and serving capacity constraints are violated
Solution Approach 1:
The patent segments the road network graph into multiple selection paths, allowing independent panorama selection for each path. This segmentation enables efficient storage by selecting only necessary panoramas from each segment rather than storing all collected panoramas, thus resolving the contradiction between complete geographic coverage and storage capacity constraints.
Solution Approach 2:
The patent applies local quality by prioritizing panorama selection based on location-specific criteria. Interior road segment panoramas are selected before intersection panoramas, and selection within each path considers local coverage needs and quality metrics. This localized selection strategy ensures adequate geographic coverage while optimizing storage usage by not uniformly storing all panoramas across the entire dataset.
2Quantity of substance
If a subset of panoramas is chosen to satisfy storage constraints, then storage capacity is maintained, but geographic coverage and image quality deteriorate
Solution Approach 1:
The patent performs preliminary action by pre-dividing the road network graph into selection paths and establishing selection criteria before actual panorama selection. Priority panoramas are identified in advance based on their positions and coverage importance. This preliminary organization ensures that when storage constraints require subset selection, the most geographically significant panoramas are prioritized, maintaining coverage completeness while adhering to storage limits.
Solution Approach 2:
The patent applies partial action by selecting only the necessary subset of panoramas required for adequate geographic coverage rather than storing all collected panoramas. The selection process determines the minimum viable subset that satisfies coverage requirements, avoiding excessive storage while maintaining reliability through strategic selection of high-priority panoramas along each selection path.
3Ease of operation
If panoramas are selected without systematic organization, then selection process is simple, but coverage efficiency and quality optimization are compromised
Solution Approach 1:
The patent segments the complex panorama selection problem into manageable selection paths along the road network. Each path can be processed independently with clear selection rules, making the overall complex task systematically manageable. This segmentation maintains operational simplicity while dramatically improving coverage efficiency compared to unorganized selection methods.
Solution Approach 2:
The patent performs preliminary organization of the road network into selection paths and identifies priority panoramas before the actual selection process. This preliminary structuring creates a systematic framework that guides efficient panorama selection, improving coverage productivity while maintaining operational simplicity through predefined selection criteria and organized data structure.
Data Source
AI summary
A street-level imagery acquisition and selection process identifies which images are published in a street field view. An imagery database includes panoramas each corresponding to a set of images acquired from a single viewpoint. The panoramas are attached to corresponding positions on a road network graph. The graph is divided into a set of selection paths, each of which includes a topologically linear sequence of road segments. Each selection path is evaluated to select a set of panoramas to be published in the path. Panoramas of interior road segments are selected before panoramas at intersections. Selected panorama identifiers for each interior road segment of the selection paths and each intersection correspond to a position along the road network graph. The selected panorama identifiers are then published in the street field view.