3D indoor positioning through crowdsourcing

July 4th, 2018, Published in Articles: PositionIT

With the highest concentration of smartphone users residing in urban areas where multi-storey buildings are the norm, accurate 3D prediction is a growing requirement. However, floor-level detection is one of the most challenging goals in indoor positioning. WiFi fingerprinting can be effective in distinguishing floor but requires extensive manual surveying. Similarly, BLE hardware installations can provide good results, but does not tend to be a scalable solution. Sensewhere has spent over two years in R&D work to solve the problem, and recently announced the release of what they call 3D-Grid. The 3D Grid System is an approach to level detection utilising machine learning and device intelligence to build a vertical grid in any building. The system cross-references the crowdsourced grid with known ground level indicators, through entrance and boundary detection. It then successfully tags floors both below and above ground level. When combined with up to date point-of-interest data, floor aware mapping and attribution is now a reality.

Contact Anna Majek, Sensewhere, a.majek@sensewhere.com

Related Articles

  • Economic street level imagery surveys for smaller municipalities
  • Information is nothing without ethical action
  • Setting up a real-time inventory management system
  • GIS software achieves top user ranking
  • High performance IMU for demanding data collection