Satellite image based on-street parking availability technology
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 aims to process easily available high resolution satellite images coming, e.g., from Pléiades satellites.
The goals of this project are:
- Geo-referencing of satellite images and 3D modeling for the street space
- Vehicle detection in satellite images
- Classification (vehicles in movement, parking on-street, parking off-street)
- A method for merging these data with map data (streets etc.)
Expected results are a general potential estimation for satellite based technologies in the application field in question, and a set of respective algorithms for geo-referencing, object identification and detection.