Starting point / motivation
Finding a free parking spot in a city is tiring. It also costs a lot of time, money and nerves, and, last but not least, causes a lot of unnecessary emission. Top notch parking navigation software systems are still not able to ease these pains, as options to collect data about parking occupancy or availability are extremely limited, and these data are necessary to train models that can release the pain from drivers.
Today, Parking space analysis specialist Parkbob uses a range of data to feed its software. However, as these data aren’t available everywhere, Parkbob now considers to process easily available high resolution satellite images coming, e.g., from Pléiades satellites.
Contents and goals
To cope with the challenges of these new data sources, especially with the relatively low resolution of 50cm (in comparison to size of an average car), and to make the data usable for a next level software, the company seeks to develop new methods together with two institutes of the Technological University Vienna, the Research Group Photogrammetry at the Department of Geodesy and Geoinformation and the Computer Vision Lab.
The goals of this project:
- Development of a new set of methods and algorithms for geo-referencing, detection and classification of objects, especially vehicles in movement, parking on-street or parking off-street, for merging these data with map data and delivering informational output on parking availability.
- Evaluation of the research results by setting up a software prototype and testing it in a pilot area
- Estimation of the application potential and preparation of the application of all research results by developing use cases and estimating economic, environmental and societal value.
Expected results are a general potential estimation for satellite based technologies in the application field in question, a set of respective algorithms for geo-referencing, object identification and detection, map matching and analyzing parking space availability in real-time – integrated in a software prototype; plus new insights in all technologies involved, that can also be used for other satellite image based applications in the future.
- Computer Vision Lab, TU Vienna
- TU Vienna, Department of Geodesy and Geoinformation, Research Group Photogrammetry
Mag. Christian Adelsberger