Estimation of the Free Space in Front of a Moving Vehicle
2009 (English)Report (Other academic)
There are more and more systems emerging making use of measurements from a forward looking radar and a forward looking camera. It is by now well known how to exploit this data in order to compute estimates of the road geometry, tracking leading vehicles, etc. However, there is valuable information present in the radar concerning stationary targets, that is typically not used. The present work shows how radar measurements of stationary targets can be used to provide a reliable estimate of the drivable space in front of a moving vehicle.
In the present paper three conceptually different methods to estimate stationary objects or road borders are presented and compared. The first method considered is occupancy grid mapping, which discretizes the map surrounding the ego vehicle and the probability of occupancy is estimated for each grid cell. The second method applies a constrained quadratic program in order to estimate the road borders. The problem is stated as a constrained curve fitting problem. The third method associates the radar measurements to extended stationary objects and tracks them as extended targets.
The required sensors, besides the standard proprioceptive sensors of a modern car, are a forward looking long range radar and a forward looking camera. Hence, there is no need to introduce any new sensors, it is just a matter of making better use of the sensor information that is already present in a modern car. The approach has been evaluated and tested on real data from highways and rural roads in Sweden and the results are very promising.
Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2009. , 47 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2892
Road geometry, Weighted least squares, Quadratic program, Road borders, Free space estimation, Automotive radar, Road mapping
IdentifiersURN: urn:nbn:se:liu:diva-56197ISRN: LiTH-ISY-R-2892OAI: oai:DiVA.org:liu-56197DiVA: diva2:317013