Trajectory Management and Analysis : Différence entre versions
De Transport
| Ligne 9 : | Ligne 9 : | ||
* Python bindings: inspiration from OpenCV? | * Python bindings: inspiration from OpenCV? | ||
* Representation of clusters, motion patterns: prototypes, paths, Gaussian processes | * Representation of clusters, motion patterns: prototypes, paths, Gaussian processes | ||
| + | * Use of Catch for tests (https://github.com/philsquared/Catch): [https://raw.github.com/philsquared/Catch/master/single_include/catch.hpp header] only | ||
==Data Sources== | ==Data Sources== | ||
Version du 21 juin 2012 à 23:40
- Data structure for trajectories?
- dimention: 2D, 3D?
- time dimension: constant sampling rate?
- Application data:
- GPS: potentially different sampling rate
- case of fixed point detection (BT)
- tracking from video data: potential missing points (occlusion)
- Exceptions ??
- Python bindings: inspiration from OpenCV?
- Representation of clusters, motion patterns: prototypes, paths, Gaussian processes
- Use of Catch for tests (https://github.com/philsquared/Catch): header only
Data Sources
- http://www.rtreeportal.org/
- http://crawdad.cs.dartmouth.edu/data.php, eg http://crawdad.cs.dartmouth.edu/epfl/mobility
- http://research.microsoft.com/en-us/downloads/b16d359d-d164-469e-9fd4-daa38f2b2e13/default.aspx
