vtrackd − compute the distance between two points in image sequences

vtrackd if=infile of=outfile pf=pfile [gf=outgfile] [df=outdfile] [cdf=outcdfile] [sz=pxysize] [xs=pxsize] [ys=pysize] [in=invessel] [h=hsearch] [v=vsearch] [a=alpha] [-norm | -sumdif | -sqdif] [-fast] [-img] [-d] [-v]

Vtrackd is a tracking program which determines the distance of two points through a set of consecutive frames of an image sequence. Initial locations of two points are specified in the file pfile. The current implementation of vtrackd only works when the line connecting the two points is vertical throughout the image sequence. Each new frame is searched to locate the best matching features. The features are square image patches centered on the coordinates of two points. The default size of a patch is 9x9 pixels. The search space in the following frame is constrained to a local region; the default search region size is 30x30 pixels. To find the location of a feature (image patch) in the following image frame, some form of matching metric has to be used. Vtrackd implements a number of different matching metrics. It can be specified by the one of [-norm | -sumdif | -sqdif]; the default metric is sum of squared differences.

Vtrackd can generate three output files. The output file specified by the of= parameter is an annotated image set in which the distance between two points is marked on each frame, and the search space marked with rectangles. The second output format is a vector file (suitable viewing with v3d) specified with the gf= parameter. In this file the temporal trajectories of each feature are stored. The third output format is a distance file specified with the df= parameter. In this file is the distance in pixels for each image frame.

The input images must be of type unsigned byte. Two points has to be aligned vertically throughout the image sequence. When a feature is not located by a match maximum within the search window, it is not tracked further.

if=

Specifies the input file which must be a VisionX image set

of=

Specifies the name of the annotated image set output file.

pf=

specifies an (ASCII) text file which contains the number of features to track and their initial x,y locations in the following format:

N

x1 y1

: :

xN yN

gf=gfile

specifies the vector output file which contains the trajectories of the features.

df=dfile

specifies the distance output file which contains the distance for every frame.

cdf=cdfile

specifies the distance change output file which contains the distance changes between two consecutive frames.

-N

causes the patch to be loaded only once and NOT updated. This is useful when interframe variations are less than one pixel.

sz=

is the size of a square correlation patch matrix. The default size is 9 (i.e., 9x9).

xs= ys=

is the x and y size of a correlation patch matrix. The default size is 9 (i.e., 9x9).

in=

is the portion of the patch to go into the vessel.

h=

specifies the horizontal search size; i.e., the number of pixels to search horizontally. The default is 30.

v=

specifies the vertical search size; i.e., the number of pixels to search vertically. The default is 30.

a=

specifies the alpha. Alpha is a parameter that specifies how the reference patch for next frame is computed. RP = (a)*CP + (1-a)*RP, where RP is reference patch and CF is current patch. RP is initialized to the first patch. With a=0.0, the reference patch is the first patch. With a=1.0, the reference patch is the current patch. The default is 0.5.

-img

use image coordinates; i.e. with the coordinate origin in the top left rather than bottom left corner.

The correlation matching algorithm is specified by one of the following :

-sqdif

sum of squared differences (equivalent to mse) (default)

-sumdif

sum of absolute differences

-norm

normalized correlation

-fast

may be specified to invoke a faster (optimized) algorithm for the matching methods shown above.

-d

specifies that debugging information is to be printed.

-v

specifies verbose mode.

A.P. Reeves, J. Lee