Difference between revisions of "Projects:Improve tracking of individual markers and marker patterns"
m |
m (→Overview) |
||
| Line 1: | Line 1: | ||
== Overview == | == Overview == | ||
| − | + | The raw output of the Vicon system is a set of 3D point detections in every frame. On the individuals, the markers are arranged to form unique patterns on a 2D planar surface (think of a bunch of markers glued in a particular way onto a billboard). | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| + | The Vicon Nexus software detects these patterns within the point cloud on a per frame basis, while an additional tracker software assembles the per-frame detections into tracks, correcting some of the mistakes in per-frame detection. (TODO: is this indeed how it works? please explain). However, this process is not free of errors, and we thus would like to improve it. | ||
== Contact == | == Contact == | ||
Revision as of 18:57, 20 May 2019
Contents
Overview
The raw output of the Vicon system is a set of 3D point detections in every frame. On the individuals, the markers are arranged to form unique patterns on a 2D planar surface (think of a bunch of markers glued in a particular way onto a billboard).
The Vicon Nexus software detects these patterns within the point cloud on a per frame basis, while an additional tracker software assembles the per-frame detections into tracks, correcting some of the mistakes in per-frame detection. (TODO: is this indeed how it works? please explain). However, this process is not free of errors, and we thus would like to improve it.
Contact
- Mate Nagy, mnagy@orn.mpg.de
- Hemal Naik, hnaik@orn.mpg.de
Aims
List the aims of your project, or what you expect anyone taking up the project is supposed to hopefully achieve. The more specific, the better.
Estimated level of difficulty
If you have an estimate, classify level of difficulty according to the description of the CCU in the cluster proposal into
- Standard problems which just require applying existing methods (Hiwi level)
- Elaborate problems which require substantial adaptation or extension of existing methods (Master student level)
- Special problems which require research of entirely new methods and might lead to a paper or two (Ph.D. student level)
Maybe add a short clarification of what you believe are the main difficulties, and why you believe this is the right classification.
Provided data
See Vicon:Data format documentation.
Suggested/tested approaches
- Possible approach:
A. Backpack points can be transferred to coordinate system of VICON using output of tracker (6DOF pose transformation between VICON and Backpack coordinate system). Tracker has better optimization techniques than nexus therefore trajectories are more complete. The result is compared with 3D points given by Nexus and a combined dataset can be created. B. Results from A is compared with .csv of unlabeled points (Tracker output of 3D all detections) to label all detected 3D points and remove ghost points. C. The combined result from A and B can be used then to identify random flips in angles, positions and IDs.
