Intelligent reconnaissance 2012-2015: Final report


  • Fredrik Näsström
  • Erika Bilock
  • Fredrik Bissmarck
  • Viktor Deleskog
  • Robert Forsgren
  • Hans Habberstad
  • Fredrik Hemström
  • Gustaf Hendeby
  • Jörgen Karlholm
  • Jonas Nordlöf
  • Jonas Nygårds
  • Joakim Rydell
  • Jonas Allvar

Publish date: 2016-02-05

Report number: FOI-R--4148--SE

Pages: 50

Written in: Swedish


  • detection
  • target tracking
  • collaboration
  • fusion
  • sensor control
  • positioning
  • machine learning


This report presents the work carried out in within the project Intelligent reconnaissance. In the project research has been conducted with the aim to make future sensor systems more intelligent. By being more intelligent, future sensor systems provide sensor operators with better situational awareness, higher system confidence, reduced risk of human errors and low mental workload. The project has conducted research on algorithms for automatic detection, tracking, collaboration, fusion, sensor management and positioning. An effective detection algorithm has been developed for detection of people. The developed detection algorithm is very good at detecting people in complex environments, and have a low probability of false alarms. The algorithm is based on machine learning technology, which means that it can be taught to detect also other items such as vehicles, vessels, helicopters etc. A tracking algorithm is developed to associate the detection over time and create target tracks. This gives the opportunity to estimate the targets position and movement, even if they are not observed. The research project has shown that reconnaissance with cooperating steerable sensors can be used to increase coverage and improve tracking performance. The research has also shown that positioning of the own platform can be determined through the use of collaborative sensors. This has been found to be computationally possible in real time. The project's research has shown how information from detection and target tracking system can be distributed to a Battle Management Systems (BMS), which automatically updates the situational awareness in real time. The information to the BMS is distributed thru a NFFI coupling (NATO Friendly Force Information). The management system SWECCIS (SWEdish Command and Control Information System) can be updated in the same way. The ability to automatically update a situational picture can be used for many platforms in the Swedish Armed Forces such as vehicles, surveillance systems, helicopters, aircraft, UAVs etc.