On automatic extraction of on-street parking spaces using park-out events data

TL;DR

This paper presents two automated methods using park-out events data to map on-street parking spaces, achieving over 91% accuracy and discussing future enhancements for data collection and validation.

Contribution

It introduces spatial aggregation and machine learning approaches for automatic parking space detection using park-out events data, with a comparative analysis of their effectiveness.

Findings

Achieved 91.6% classification accuracy on imbalanced data

Compared rasterization and decision tree methods for parking space detection

Discussed potential improvements including more data and manual validation

Abstract

This article proposes two different approaches to automatically create a map for valid on-street car parking spaces. For this, we use car sharing park-out events data. The first one uses spatial aggregation and the second a machine learning algorithm. For the former, we chose rasterization and road sectioning; for the latter we chose decision trees. We compare the results of these approaches and discuss their advantages and disadvantages. Furthermore, we show our results for a neighborhood in the city of Berlin and report a classification accuracy of 91.6\% on the original imbalanced data. Finally, we discuss further work; from gathering more data over a longer period of time to fitting spatial Gaussian densities to the data and the usage of apps for manual validation and annotation of parking spaces to improve ground truth data.