We propose a novel extension to traffic accident simulation by means of semantic 3D environment information allowing for a broader view by incorporating the entire close-by environment. In this course, the effect of Advanced Driver Assistance Systems (ADAS) can be simulated, as well as the visibility of objects from people’s perspectives. We present an enclosed pipeline generating 3D objects, their extents and relative positions as well as their semantic class from a combination of photogrammetric recordings and LiDAR (Light Detection And Ranging) scans. By adjusting the desired level of detail, these objects are suitable for both direct integration into the 3D scene reconstruction for use in the accident simulation software PC-Crash, as well as for fine tuning parameters in traffic flow simulations and for convincing visualization and presentation of simulation results, be it in courts or to policy makers in urban planning.
|Title of host publication||Proceedings of 7th Transport Research Arena TRA 2018|
|Publication status||Published - 16 Apr 2018|
Mohr, L., Öttl, M., Haberl, M., Rüther, M., & Bischof, H. (2018). Semantic 3D Models from Real World Scene Recordings for Traffic Accident Simulation. In Proceedings of 7th Transport Research Arena TRA 2018