Class cv::TrackerMIL#

The [17] algorithm trains a classifier in an online manner to separate the object from the background. View details

#include <opencv2/video/tracking.hpp>

Collaboration diagram for cv::TrackerMIL:

cv::TrackerMIL Node1 cv::TrackerMIL   + ~TrackerMIL() + create() # TrackerMIL() Node2 cv::Tracker   + ~Tracker() + getTrackingScore() + init() + update() # Tracker() Node2->Node1

cv::TrackerMIL Node1 cv::TrackerMIL   + ~TrackerMIL() + create() # TrackerMIL() Node2 cv::Tracker   + ~Tracker() + getTrackingScore() + init() + update() # Tracker() Node2->Node1

Public Member Functions#

Public Member Functions inherited from cv::Tracker

Return

Name

Description

~Tracker()

float

getTrackingScore()

Return tracking score.

void

init(
    InputArray image,
    const Rect & boundingBox )

Initialize the tracker with a known bounding box that surrounded the target.

bool

update(
    InputArray image,
    Rect & boundingBox )

Update the tracker, find the new most likely bounding box for the target.

Additional Inherited Members#

Protected Member Functions inherited from cv::Tracker

Return

Name

Description

Tracker()

Detailed Description#

The MIL algorithm trains a classifier in an online manner to separate the object from the background.

Multiple Instance Learning avoids the drift problem for a robust tracking. The implementation is based on MIL .

Original code can be found here http://vision.ucsd.edu/~bbabenko/project_miltrack.shtml

Constructor & Destructor Documentation#

TrackerMIL()#

cv::TrackerMIL::TrackerMIL()

~TrackerMIL()#

cv::TrackerMIL::~TrackerMIL()

Member Function Documentation#

create()#

static Ptr< TrackerMIL > cv::TrackerMIL::create(const TrackerMIL::Params & parameters = TrackerMIL::Params())

Python:

cv.TrackerMIL.create([, parameters]) -> retval

cv.TrackerMIL_create([, parameters]) -> retval

Create [17] tracker instance.

Parameters

Source file#

The documentation for this class was generated from the following file: