What features are in the works for future versions of trackR?Īt the moment, I am considering including the following features in future iterations of trackR: If you run into an issue, please report it at. This being said, it will work fine in most cases and is certainly usable for most tracking projects. This is version 0.5 of the software, there is still a long way to go before it is a fully finished program. Will something break? Can I use trackR in ‘production’ mode?
However, we believe that trackR’s object segmentation and separation algorithms are generally more robust and should therefore be capable of handling a wider variety of situations. It will most likely provide tracking reliability equivalent to these excellent programs.
OPEN SOURCE MOTION TRACKING SOFTWARE SOFTWARE
TrackR is more similar in spirit to tracking software such as Ctrax, tracktor, and the sadly defunct SwisTrack. The downside is that trackR’s tracking reliability is inferior to the more advanced software (in particular when the objects cross paths) the upside is that it is fast and does not require a beast of a computer to run. trackR does not include (for now) any fancy machine learning methods like those that can be found in the fantastic idtracker.ai for instance. It relies on good ol’ fashion image processing, robust cross-entropy clustering, and simple, yet efficient, assignment algorithms (the Hungarian method in this case). TrackR belongs to the category of the ‘classical’ tracking programs. How does trackR compare to other video tracking solutions? Did we really need another one? TrackR also allows users to exclude parts of the image by using masks that can be easily created and customized directly within the app.įinally, trackR provides several convenience apps to correct common errors that occurs during video recording, to manually inspect and fix tracking errors, and to export publication-ready videos showing the moving objects with their track overlaid on top of them. Most of the tracking parameters can be automatically estimated by trackR or can be set manually by the user. Overlapping objects are then separated using cross-entropy clustering, an automated classification method that provides good computing performance while being able to handle various types of object shapes (see the CEC package for R for more information on cross-entropy clustering). A background image can be provided by the user or can be computed by trackR automatically in most situations. TrackR uses RGB-channel-specific background subtraction to segment objects in a video. It provides an easy-to-use (or so we think) graphical interface allowing users to perform multi-object video tracking in a range of conditions while maintaining individual identities. TrackR is an object tracker for R based on OpenCV.
0 kommentar(er)
