At the moment in the research world there is a lot of activity around ground based LiDAR data capture with a number of companies mounting rigs onto vans and driving around cities. While LiDAR per se does have a lot of potential, it also can't be denied that the data output is overwhelming and it is limited to high end hardware. Working from that angle, the University of North Carolina, Chapel Hill and University of Kentucky have been working on techniques to develop 3D Models direct from video, thus negating the need for a LiDAR rig. Although it is early days yet, the results are encouraging. The video below showcases a model created of the Capel Campus using the technique.
According to Jan-Micael Fraham, Research Assistant Professor on the project, the research aims at developing a system for automatic, geo-registered, real-time 3D reconstruction from video of urban scenes. From 2005-2007 the team developed a system that collects video streams, as well as GPS and inertia measurements in order to place the reconstructed models in geo-registered coordinates. It is designed using current state of the art real-time modules for all processing steps employing commodity graphics hardware and standard CPU's to achieve real-time performance.The second video embedded below provides an overview of the process and is extremely interesting.
The system extends existing algorithms to meet the robustness and variability necessary to operate out of the lab. To account for the large dynamic range of outdoor videos the processing pipeline estimates global camera gain changes in the feature tracking stage and efficiently compensates for these in stereo estimation without impacting the real-time performance. The required accuracy for many applications is achieved with a two-step stereo reconstruction process exploiting the redundancy across frames.
Check the UrbanScape website for more details, it is well worth a visit as this is one of the most interesting and genuinely innovative urban modelling projects coming from academia I have seen in months!
No comments:
Post a Comment