Content
As part of the ‘Connected Urban Twins’ (CUT) project, the City of Leipzig is collaborating with the Centre for Scalable Data Analysis and Artificial Intelligence (ScaDS.AI) to test AI-based methods for analysing parking spaces. Using object recognition, vehicles parked parallel, at an angle or perpendicular to the kerb are identified for each section of road, taking into account the specific characteristics of the road. Based on this information, the prevailing parking behaviour is determined and the associated parking capacity is estimated.
Machine Learning Based Mobile Capacity Estimation for Roadside Parking
This paper introduces a novel computer vision-based method for automatically collecting parking space capacities and parking type information. Our approach combines both street view and aerial imagery, which are recorded by a moving camera source.
Github "roadside-carparking-direction-detection"
This repository contains the code to evaluate street view and True DOP images concerning the parking type of cars to classify the parking type for a street. It requires a PostgreSQL database with PostGIS extension to be installed and linked in the config files. Further needed data is explained below. Currently the street view images need to be by the company 'cyclomedia'. If these are not available the code will also work with orthophotos only, just disable the extraction of streetview images and set image_type to "air". Disclaimer: due to the data coming from German cities, most of the properties are in German language, please excuse this.
Fast Multiclass Vehicle Detection on Aerial Images
K. Liu and G. Mattyus, "Fast Multiclass Vehicle Detection on Aerial Images," in IEEE Geoscience and Remote Sensing Letters, vol. 12, no. 9, pp. 1938-1942, Sept. 2015, doi: 10.1109/LGRS.2015.2439517.
Parkplatzzählung und Parkraumanalysen auf OSM-Basis
OSM-Daten bieten das Potential, präzise Parkplatzzählungen und Parkraumanalysen durchzuführen und damit wertvolles Wissen für Diskussionen rund um Verkehrswende, Stadtentwicklung und Mobilität bereitzustellen. Dieser Vortrag demonstriert das am Beispiel des Berliner Stadtteils Neukölln und teilt Ergebnisse sowie Erfahrungen mit euch.