OpenCV
4.0.0
Open Source Computer Vision
|
Multi Object Tracker for TLD. TLD is a novel tracking framework that explicitly decomposes the long-term tracking task into tracking, learning and detection. More...
#include "tracker.hpp"
Public Member Functions | |
bool | update_opt (InputArray image) |
Update all trackers from the tracking-list, find a new most likely bounding boxes for the targets by optimized update method using some techniques to speedup calculations specifically for MO TLD. The only limitation is that all target bounding boxes should have approximately same aspect ratios. Speed boost is around 20%. More... | |
Public Member Functions inherited from cv::MultiTracker_Alt | |
MultiTracker_Alt () | |
Constructor for Multitracker. More... | |
bool | addTarget (InputArray image, const Rect2d &boundingBox, Ptr< Tracker > tracker_algorithm) |
Add a new target to a tracking-list and initialize the tracker with a known bounding box that surrounded the target. More... | |
bool | update (InputArray image) |
Update all trackers from the tracking-list, find a new most likely bounding boxes for the targets. More... | |
Additional Inherited Members | |
Public Attributes inherited from cv::MultiTracker_Alt | |
std::vector< Rect2d > | boundingBoxes |
Bounding Boxes list for Multi-Object-Tracker. More... | |
std::vector< Scalar > | colors |
List of randomly generated colors for bounding boxes display. More... | |
int | targetNum |
Current number of targets in tracking-list. More... | |
std::vector< Ptr< Tracker > > | trackers |
Trackers list for Multi-Object-Tracker. More... | |
Multi Object Tracker for TLD. TLD is a novel tracking framework that explicitly decomposes the long-term tracking task into tracking, learning and detection.
The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates detector's errors and updates it to avoid these errors in the future. The implementation is based on [100] .
The Median Flow algorithm (see cv::TrackerMedianFlow) was chosen as a tracking component in this implementation, following authors. Tracker is supposed to be able to handle rapid motions, partial occlusions, object absence etc.
bool cv::MultiTrackerTLD::update_opt | ( | InputArray | image | ) |
Update all trackers from the tracking-list, find a new most likely bounding boxes for the targets by optimized update method using some techniques to speedup calculations specifically for MO TLD. The only limitation is that all target bounding boxes should have approximately same aspect ratios. Speed boost is around 20%.
image | The current frame. |