OpenCV  4.10.0-dev
Open Source Computer Vision
Loading...
Searching...
No Matches
Public Member Functions | Public Attributes | List of all members
cv::detail::tracking::tbm::TrackerParams Struct Reference

The TrackerParams struct stores parameters of TrackerByMatching. More...

#include <opencv2/tracking/tracking_by_matching.hpp>

Collaboration diagram for cv::detail::tracking::tbm::TrackerParams:

Public Member Functions

 TrackerParams ()
 

Public Attributes

float aff_thr_fast
 
float aff_thr_strong
 
cv::Vec2f bbox_aspect_ratios_range
 Bounding box aspect ratios range.
 
cv::Vec2f bbox_heights_range
 Bounding box heights range.
 
bool drop_forgotten_tracks
 
size_t forget_delay
 
int max_num_objects_in_track
 
float min_det_conf
 Min confidence of detection.
 
size_t min_track_duration
 Min track duration in milliseconds.
 
float motion_affinity_w
 Motion affinity weight.
 
int predict
 
float reid_thr
 Affinity threshold for re-identification.
 
float shape_affinity_w
 Shape affinity weight.
 
float strong_affinity_thr
 of lost track.
 
float time_affinity_w
 Time affinity weight.
 

Detailed Description

The TrackerParams struct stores parameters of TrackerByMatching.

Constructor & Destructor Documentation

◆ TrackerParams()

cv::detail::tracking::tbm::TrackerParams::TrackerParams ( )

Default constructor.

Member Data Documentation

◆ aff_thr_fast

float cv::detail::tracking::tbm::TrackerParams::aff_thr_fast

Affinity threshold which is used to determine if tracklet and detection should be combined (fast descriptor is used).

◆ aff_thr_strong

float cv::detail::tracking::tbm::TrackerParams::aff_thr_strong

Affinity threshold which is used to determine if tracklet and detection should be combined(strong descriptor is used).

◆ bbox_aspect_ratios_range

cv::Vec2f cv::detail::tracking::tbm::TrackerParams::bbox_aspect_ratios_range

Bounding box aspect ratios range.

◆ bbox_heights_range

cv::Vec2f cv::detail::tracking::tbm::TrackerParams::bbox_heights_range

Bounding box heights range.

◆ drop_forgotten_tracks

bool cv::detail::tracking::tbm::TrackerParams::drop_forgotten_tracks

Drop forgotten tracks. If it's enabled it disables an ability to get detection log.

◆ forget_delay

size_t cv::detail::tracking::tbm::TrackerParams::forget_delay

Forget about track if the last bounding box in track was detected more than specified number of frames ago.

◆ max_num_objects_in_track

int cv::detail::tracking::tbm::TrackerParams::max_num_objects_in_track

The number of objects in track is restricted by this parameter. If it is negative or zero, the max number of objects in track is not restricted.

◆ min_det_conf

float cv::detail::tracking::tbm::TrackerParams::min_det_conf

Min confidence of detection.

◆ min_track_duration

size_t cv::detail::tracking::tbm::TrackerParams::min_track_duration

Min track duration in milliseconds.

◆ motion_affinity_w

float cv::detail::tracking::tbm::TrackerParams::motion_affinity_w

Motion affinity weight.

◆ predict

int cv::detail::tracking::tbm::TrackerParams::predict

How many frames are used to predict bounding box in case

◆ reid_thr

float cv::detail::tracking::tbm::TrackerParams::reid_thr

Affinity threshold for re-identification.

◆ shape_affinity_w

float cv::detail::tracking::tbm::TrackerParams::shape_affinity_w

Shape affinity weight.

◆ strong_affinity_thr

float cv::detail::tracking::tbm::TrackerParams::strong_affinity_thr

of lost track.

If 'fast' confidence is greater than this threshold then 'strong' Re-ID approach is used.

◆ time_affinity_w

float cv::detail::tracking::tbm::TrackerParams::time_affinity_w

Time affinity weight.


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