Building Accessor Identification via Probe Density Deconvolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current crowd-sourced mapping technologies face challenges in accurately identifying building accessors such as entrances and exits due to the limited accuracy of GPS systems, which affects the reliability of map generation and pedestrian navigation assistance.
Innovation Solution
A mapping system that utilizes probe data points from multiple sensors to generate a probe density histogram, applies deconvolution methods like the Maximum Entropy Method to sharpen location data, and distinguishes between entrances and exits based on probe trajectories, effectively identifying statistically significant peaks as accessors on a building's edge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS location data is used to identify building accessors, then crowd-sourced mapping can be performed, but the accuracy is insufficient to determine building accessors due to GPS error margins
Solution Approach 1:
The patent combines multiple probe data points from multiple users and multiple sensors (GPS, cellular tower triangulation, Wi-Fi positioning) to collectively identify building accessors. By merging data from numerous sources, the system overcomes the limitations of individual GPS measurements and achieves reliable accessor identification despite inherent GPS inaccuracies.
Solution Approach 2:
The patent introduces probe data points as intermediary indicators that indirectly reveal building accessor locations. Rather than directly measuring accessor positions, the system uses probe data points from mobile devices as mediators to infer accessor locations through pattern recognition and statistical analysis of aggregated movement data.
2Measurement precision
If manual mapping methods are used, then map accuracy can be maintained, but the updating frequency and effort required are significantly higher
Solution Approach 1:
The patent enables maps to update themselves automatically by utilizing probe data points collected from mobile devices of users naturally moving through the environment. The system processes this crowd-sourced data to automatically identify and update building accessors without requiring manual intervention, thereby maintaining accuracy while dramatically improving updating efficiency.
Solution Approach 2:
The system continuously collects probe data points from mobile devices and uses this feedback to automatically detect changes in building accessor locations. The aggregated probe data provides ongoing feedback that triggers automatic map updates, ensuring maps remain current without manual effort.
3Loss of information
If probe data points are aggregated to identify building accessors, then accessibility information can be obtained, but the data contains noise that reduces identification accuracy
Solution Approach 1:
The patent extracts meaningful accessor location information from noisy probe data by filtering and analyzing patterns in the aggregated data. The system separates signal from noise by identifying consistent spatial patterns in probe data points that correspond to actual building accessors, discarding random variations and errors.
Solution Approach 2:
The system changes parameters such as aggregation thresholds, spatial clustering criteria, and temporal filtering parameters to optimize the extraction of accurate accessor locations from noisy probe data. By adjusting these parameters, the system enhances the signal-to-noise ratio and improves location precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided herein is a method for establishing accessors to a building from probe data. Methods may include: receiving probe data points; determining probe data point candidates for a first edge of a building; determining, for the probe data point candidates, probe data points entering or exiting the building; generating, from the probe data points entering or exiting the building, a probe density histogram for the first edge of the building, where the probe density histogram represents a volume of probe data points at each of a plurality of positions across a width of the first edge of the building; applying a deconvolution method to the probe density histogram to obtain a multi-modal histogram; determining, from the multi-modal histogram, a number of statistically significant peaks, where each statistically significant peak represents an accessor to the building in the first edge of the building; and providing data for navigational assistance based on the computed accessors to the building.