Vehicle Trajectory Analysis for Interstation Parking Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The sparsity of sensor stations in road traffic sensor networks makes it impossible to determine detailed information on a vehicle's behavior, such as identifying parking locations, between two consecutive stations.

Innovation Solution

A framework that collects and processes vehicle trajectory data from a sensor network to generate a tracking table, analyzing it to determine interstation parking areas within a convex hull surrounding the sensor stations based on user input parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If sensor stations are sparsely distributed in the sensor network, then cost is reduced, but the ability to determine detailed vehicle behavior information between stations is lost

Engineering Contradiction:

ImprovecostVSAvoidvehicle behavior information

Core Design Contradiction:

Ease of manufactureVSLoss of information

Solution Approach 1:

The system pre-processes vehicle trajectory data by creating tracking tables that store vehicle identification, sensor station identification, and capture time information before analysis is needed. This preliminary organization of data enables subsequent identification of parking areas and vehicle behaviors without requiring additional sensor deployments.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system transitions from analyzing discrete sensor station data to analyzing continuous trajectory data by processing vehicle movement patterns across multiple stations over time. This dimensional transformation from point-based sensor readings to path-based trajectory analysis enables detection of intermediate behaviors like parking areas between sparsely distributed stations.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Device complexity

If sensor stations are sparsely distributed, then device complexity is reduced, but measurement precision of vehicle trajectory details deteriorates

Engineering Contradiction:

Improvesensor network complexityVSAvoidvehicle trajectory precision

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system segments vehicle trajectory analysis into discrete events by identifying specific behaviors such as parking areas, acceleration zones, and deceleration zones along the vehicle path. By dividing the continuous trajectory into meaningful segments based on behavioral patterns, the system achieves detailed measurement precision without requiring dense sensor coverage.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces trajectory data records as an intermediary between sensor stations, capturing vehicle information at each station and using these intermediate records to reconstruct detailed vehicle behavior. The tracking table serves as a mediator that bridges the gap between sparsely distributed sensors by organizing sequential observation points into coherent vehicle paths.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9607509B2Identification of vehicle parking using data from vehicle sensor network

Publication Date: 2017.03.28 SAP SE

AI summary

A framework for identifying parking areas from vehicle trajectory data is described herein. Vehicle trajectory data collected from a sensor network having a plurality of sensor stations for detecting vehicles is provided. The vehicle trajectory data is pre-processed to generate a tracking table of vehicles and analyzed to determine an interstation parking area between first and second sensor stations of interest based on input parameters from a user.