Creates a new tracker object
tracker = cv.DetectionBasedTracker(mainDetector, trackingDetector)
tracker = cv.DetectionBasedTracker(..., 'OptionName',optionValue, ...)
Input
- mainDetector, trackingDetector detector of the form
{filename, 'key',val, ...} where filename is the name of
the file from which the classifier is loaded. See detection
options below for valid key/value pairs. Currently only one
detector based on cv.CascadeClassifier is supported.
Options
- MaxTrackLifetime must be non-negative. default 5
- MinDetectionPeriod the minimal time between run of the big
object detector (on the whole frame) in msec (1000 mean 1 sec).
default 0
CascadeClassifier detection options
- ScaleFactor Parameter specifying how much the image size
is reduced at each image scale. default 1.1
- MinNeighbors Parameter specifying how many neighbors each
candiate rectangle should have to retain it. default 2
- MinSize Minimum possible object size. Objects smaller than
that are ignored. default
[96,96].
- MaxSize Maximum possible object size. Objects larger than
that are ignored. default
[intmax,intmax].