OpenCV453
公開メンバ関数 | 全メンバ一覧
cv::legacy::tracking::MultiTrackerTLD クラス

Multi Object Tracker for TLD. [詳解]

#include <tracking_legacy.hpp>

cv::legacy::tracking::MultiTracker_Altを継承しています。

公開メンバ関数

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% [詳解]
 
- 基底クラス cv::legacy::tracking::MultiTracker_Alt に属する継承公開メンバ関数
 MultiTracker_Alt ()
 Constructor for Multitracker
 
bool addTarget (InputArray image, const Rect2d &boundingBox, Ptr< legacy::Tracker > tracker_algorithm)
 Add a new target to a tracking-list and initialize the tracker with a known bounding box that surrounded the target [詳解]
 
bool update (InputArray image)
 Update all trackers from the tracking-list, find a new most likely bounding boxes for the targets [詳解]
 

その他の継承メンバ

- 基底クラス cv::legacy::tracking::MultiTracker_Alt に属する継承公開変数類
int targetNum
 Current number of targets in tracking-list
 
std::vector< Ptr< Tracker > > trackers
 Trackers list for Multi-Object-Tracker
 
std::vector< Rect2dboundingBoxes
 Bounding Boxes list for Multi-Object-Tracker
 
std::vector< Scalarcolors
 List of randomly generated colors for bounding boxes display
 

詳解

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 [TLD] .

The Median Flow algorithm (see cv::TrackerMedianFlow) was chosen as a tracking component in this implementation, following authors. The tracker is supposed to be able to handle rapid motions, partial occlusions, object absence etc.

参照
Tracker, MultiTracker, TrackerTLD

関数詳解

◆ update_opt()

bool cv::legacy::tracking::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%

引数
imageThe current frame.
戻り値
True means that all targets were located and false means that tracker couldn't locate one of the targets in current frame. Note, that latter does not imply that tracker has failed, maybe target is indeed missing from the frame (say, out of sight)

このクラス詳解は次のファイルから抽出されました: