Function:TrackFeatures

CUVI Feature tracker tracks input features from frame 1 onto frame 2. The function is ideal for tracking selected number of features through an image sequence or a video stream. This is a custom algorithm and does not use optical flows to estimate motion. Check out Motion Estimate section for more details on Optical Flow based motion tracking.

Function

CuviStatus trackFeatures(CuviImage* previousImage, CuviImage* nextImage, CuviPointValue2D* inputFeatures, CuviPointValue2D** trackedFeatures, Cuvi32s featureCount, CuviTrackingCriteria criteria, CuviStream* stream = NULL);

Parameters

Name	Type	Description
previousImage	CuviImage*	The first image whose features are to be tracked
nextImage	CuviImage*	Second image, in which to look for features of first image
inputFeatures	CuviPointValue2D*	Feature of first image
trackedFeatures	CuviPointValue2D**	Output feature list containing the location of tracked features from first image onto second image
featureCount	Cuvi32s	Number of features to track
criteria	CuviFeaturesCriteria	A structure containing various parameters that affect feature tracking behavior
stream	CuviStream*	GPU stream ID for execution

Image Type Support

Input	Output
8uC1	CuviPointValue2D

Samples

Example

//Create an 8-bit Grays-scale CuviImage CuviImage *gpu_image = new CuviImage(size,img->depth,img->nChannels); //Populate the Image gpu_image->upload(img->imageData,img->widthStep); CuviPointValue2D *features; //Desired number of features int featureCount = 100; //Selecting complete image for the process CuviROI roi = cuviROI(0,0,img->width,img->height); //Setting Feature selection parameters CuviFeaturesCriteria criteria = cuviFeaturesCriteria(CUVI_FEATURES_HARRIS_PETER,0.006f,15,3,-2.0f); //Calling GoodFeaturesToTrack cuvi::computerVision::goodFeaturesToTrack(&gimg,roi,&features,&featureCount,criteria);