the KCF (Kernelized Correlation Filter) tracker [詳解]

#include <tracking.hpp>

cv::Trackerを継承しています。

公開型
enum	MODE { GRAY = (1 << 0) , CN = (1 << 1) , CUSTOM = (1 << 2) }
	Feature type to be used in the tracking grayscale, colornames, compressed color-names The modes available now: [詳解]

typedef void(*	FeatureExtractorCallbackFN) (const Mat, const Rect, Mat &)

公開メンバ関数
virtual void	setFeatureExtractor (FeatureExtractorCallbackFN callback, bool pca_func=false)=0

基底クラス cv::Tracker に属する継承公開メンバ関数
virtual CV_WRAP void	init (InputArray image, const Rect &boundingBox)=0
	Initialize the tracker with a known bounding box that surrounded the target [詳解]

virtual CV_WRAP bool	update (InputArray image, CV_OUT Rect &boundingBox)=0
	Update the tracker, find the new most likely bounding box for the target [詳解]

静的公開メンバ関数
static CV_WRAP Ptr< TrackerKCF >	create (const TrackerKCF::Params &parameters=TrackerKCF::Params())
	Create KCF tracker instance [詳解]

詳解

the KCF (Kernelized Correlation Filter) tracker

KCF is a novel tracking framework that utilizes properties of circulant matrix to enhance the processing speed. This tracking method is an implementation of [KCF_ECCV] which is extended to KCF with color-names features ([KCF_CN]). The original paper of KCF is available at http://www.robots.ox.ac.uk/~joao/publications/henriques_tpami2015.pdf as well as the matlab implementation. For more information about KCF with color-names features, please refer to http://www.cvl.isy.liu.se/research/objrec/visualtracking/colvistrack/index.html.

列挙型メンバ詳解

Feature type to be used in the tracking grayscale, colornames, compressed color-names The modes available now:

static CV_WRAP Ptr< TrackerKCF > cv::tracking::TrackerKCF::create ( const TrackerKCF::Params & parameters = TrackerKCF::Params() )

static

Create KCF tracker instance

引数

parameters KCF parameters TrackerKCF::Params

このクラス詳解は次のファイルから抽出されました: