GstTracker: GstDispTEC Object Tracker with GStreamer Pipelines
GstDispTEC object tracker is a GStreamer element which integrates DispTEC library's algorithms for object tracking. This makes it possible to incorporate their functionalities into GStreamer pipelines, such as showing where the object is located on a frame.
Object tracking is implemented based on Kernelized Correlation Filters (KCF). Each tracker element is initialized with the coordinates of the object in the current frame, snipping the object from the frame and taking it as a template.
Afterwards, the tracker element updates the filter every tie that there is an object hit, adapting itself to the possible changes which an object might have during the video. In turn, this makes it robust enough to cope with potential perspective changes.
Key GstTracker Features
Non-stationary camera resilient.
Tolerates object scaling, rotation and transformation.
Resilient to changes in colour and light.
Possibility of tracker cascading.
Tracker reinitialization at run-time.
Visual feedback of object position overlaid to frames.
Note: RidgeRun assumes that there are no hardware issues that would delay the development process (and increase costs). In case of problems with your hardware, RidgeRun will bill up to 20 hours of engineering services for the time needed to inform you of what is wrong.