|
Description
The estimation algorithm offers a full automatic and robust solution to estimate camera parameters for video sequences. The results are useful for many applications like film production, 3D reconstruction, or video coding. The estimated parameters can be exported to the 3D animation packages: 3D Studio Max, Blender, Lightwave, Maya, and Softimage.
The Voodoo Camera Tracker works very alike to commercial available camera trackers (also called match movers), e.g. 3D-Equalizer by Science-D-Visions, boujou by 2d3, Matchmover by RealViz , PFTrack by The Pixel Farm, SynthEyes by Andersson Technologies, or VooCAT by Scenespector Systems. Please consider buying a commercial product, if you need a camera tracker with professional support.
The estimation method consist of five processing steps:
* Automatic detection of feature points
* Automatic correspondence analysis
* Outlier elimination
* Robust incremental estimation of the camera parameters
* Final refinement of the camera parameters
1) Automatic detection of feature points
The feature points are detected with sub-pixel accuracy using a corner detector. The detected feature points in the current image are marked with green crosses. Feature points that are detected as outliers during the processing are marked with red crosses.
2) Automatic correspondence analysis
The points can be matched from one image to the next by choosing matches which have the highest cross-correlation of image intensity for regions surrounding the points. The paths of the feature points are drawn in yellow here.
3) Outlier elimination
Due to misalignments or moving object in the scene some of the correspondences may be incorrect. To achieve a robust matching, a random sampling algorithm is employed to detect bad correspondences, called outliers.
4) Robust estimation of camera parameters
The camera parameters are estimated in an incremental fashion by using optimization technique applied to the good correspondences, called inlier.
5) Final refinement of the camera parameters
Finally, a refinement step is applied to all camera parameters of the sequence. This step tries to distribute the estimation error evenly over the sequence. Afterwards, virtual objects can be integrated into the real image sequence.
|
