I am trying to use your software to track a video sequence in ice hockey. As I noticed inconsistencies with the tracked positions and velocities, I made a video of tiles on my office floor to check, wether the software will work correctly here. I layed the perspective grid on one tile, followed to tile's corner's trajectories and tracked two other fixed points on the floor. I also tracked what is probably a piece of dust on the lense. As the camera swayed the fixed points on the floor moved within the picture and the piece of dust stayed at a constant position. Since the origin of my coordinate system, however, lies in one corner of the perspective grid and stays there as the camera moves, the velocity of the fixed points should be zero and their position should remain constant, whereas the piece of dust should change its position (relative to the origin of the coordinate system) and have a certain velocity. When displaying these parameters while watching the sequence, the positions of the fixed points seems to remain constant and the one of the piece of dust changes. This would mean that a point with a fixed position should have a velocity of zero and a point with a changing position should have a certain velocity. However when displaying the velocities, it is the other way around. The fixed points have a velocity while the piece of dust's velocity is zero. Is it possible to calculate speed relative to the cooradinate system`s origin?
Also when exporting the data, the positions in the table are not in accordance with what is displayed while watching the video.
Do you have any suggestions?
- joan
- Admin
- Offline
Hi,
You are correct in your observations. It's a current limitation of the software. You can define a coordinate system based on a grid, and you can track a grid, but both features don't work together. The coordinate system is not updated by the tracking. The points will always be expressed in the coordinate system set at the point the grid was calibrated.
There is currently no work around.