Pedestrian Probe Data Extraction via Speed and Sinuosity Metrics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Mobile navigation and mapping applications face challenges in distinguishing between pedestrian and vehicle probe data from mix-mode probe data, which are typically collected by users switching between different modes of travel, making it difficult to develop targeted navigation and mapping services.

Innovation Solution

A method and system that process probe trajectories to determine speed values and sinuosity, calculating a pedestrian probe detection metric (PDM) to classify and rank trajectories as either pedestrian or vehicle-based, allowing for the extraction and separation of pedestrian-specific data from mix-mode data without resource-intensive map-matching processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If map-matching processes are used to distinguish pedestrian and vehicle probe data, then classification accuracy is improved, but resource consumption and processing time increase

Engineering Contradiction:

Improveclassification accuracyVSAvoidresource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts and removes the resource-intensive map-matching process from the classification system. Instead of using map-matching to distinguish pedestrian and vehicle probe data, the invention directly computes the pedestrian probe detection metric from raw probe data using speed and sinuosity calculations, thereby eliminating the harmful resource consumption while maintaining classification capability

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical map-matching process with a computational metric-based system. Rather than geospatially matching probes to map features, the invention substitutes this with direct calculation of speed and sinuosity metrics from probe trajectories, achieving classification through mathematical computation instead of geometric processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If map-matching processes are used to distinguish pedestrian and vehicle probe data, then classification accuracy is improved, but processing time increases

Engineering Contradiction:

Improveclassification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts and removes the time-consuming map-matching process from the classification system. Instead of using map-matching to distinguish pedestrian and vehicle probe data, the invention directly computes the pedestrian probe detection metric from raw probe data using speed and sinuosity calculations, thereby eliminating the harmful processing time delay while maintaining classification capability

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent performs preliminary computation of speed and sinuosity metrics directly from probe data before any classification decision is made. By pre-computing these fundamental motion characteristics, the system avoids the need for subsequent map-matching operations, thereby reducing overall processing time while maintaining accurate classification

Inventive Principle:

Principle #10Preliminary action

3Quantity of substance

If mix-mode probe data is used for navigation services, then data quantity is improved, but service targeting accuracy deteriorates

Engineering Contradiction:

Improvedata quantityVSAvoidservice targeting accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent applies local quality by making the probe data classification metric-specific rather than treating all probe data uniformly. The pedestrian probe detection metric computes different characteristics (speed, sinuosity) that are locally optimized for pedestrian detection, allowing the system to process mix-mode data while accurately identifying pedestrian-specific patterns for targeted service delivery

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent changes the parameters used for probe data analysis from general geospatial coordinates to specific motion characteristics (speed and sinuosity). This parameter transformation enables the system to process large quantities of mix-mode probe data while accurately distinguishing pedestrian from vehicle modes, thereby maintaining service targeting accuracy despite the diversity of input data

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11341512B2Distinguishing between pedestrian and vehicle travel modes by mining mix-mode trajectory probe data

Publication Date: 2022.05.24 HERE GLOBAL BV

AI summary

An approach is provided for mining pedestrian probe data from mix-mode probe data. The approach involves, for example, receiving a probe trajectory including a vehicle mode of travel, a pedestrian mode of travel, or a combination thereof. The approach also involves processing the probe trajectory to determine at least one speed value and at least one sinuosity value. The approach further involves determining a pedestrian probe detection metric based on the at least one speed value and the at least one sinuosity value. The approach further involves ranking the probe trajectory among a plurality of probe trajectories based on the pedestrian probe detection metric and/or classifying the probe trajectory as either a vehicle probe trajectory or a pedestrian probe trajectory based on the pedestrian probe detection metric.