Object Detection

モジュール
	C API

クラス
class	cv::SimilarRects
struct	cv::DefaultDeleter< CvHaarClassifierCascade >
class	cv::BaseCascadeClassifier
class	cv::CascadeClassifier
	オブジェクト検出用のカスケード分類器クラス．[【詳解】（英語］
struct	cv::DetectionROI
	関心領域(ROI)検出用構造体[【詳解】（英語］
struct	cv::HOGDescriptor
	HOG（Histogram of Oriented Gradients）記述子とオブジェクト検出器の実装．[【詳解】（英語］
class	cv::QRCodeDetector
class	cv::DetectionBasedTracker

列挙型
enum	{ CASCADE_DO_CANNY_PRUNING = 1 , CASCADE_SCALE_IMAGE = 2 , CASCADE_FIND_BIGGEST_OBJECT = 4 , CASCADE_DO_ROUGH_SEARCH = 8 }

関数
CV_EXPORTS void	cv::groupRectangles (std::vector< Rect > &rectList, int groupThreshold, double eps=0.2)
	オブジェクト候補の長方形をグループ化します。[【詳解】（英語］
CV_EXPORTS_W void	cv::groupRectangles (CV_IN_OUT std::vector< Rect > &rectList, CV_OUT std::vector< int > &weights, int groupThreshold, double eps=0.2)
CV_EXPORTS void	cv::groupRectangles (std::vector< Rect > &rectList, int groupThreshold, double eps, std::vector< int > *weights, std::vector< double > *levelWeights)
CV_EXPORTS void	cv::groupRectangles (std::vector< Rect > &rectList, std::vector< int > &rejectLevels, std::vector< double > &levelWeights, int groupThreshold, double eps=0.2)
CV_EXPORTS void	cv::groupRectangles_meanshift (std::vector< Rect > &rectList, std::vector< double > &foundWeights, std::vector< double > &foundScales, double detectThreshold=0.0, Size winDetSize=Size(64, 128))
CV_EXPORTS Ptr< BaseCascadeClassifier::MaskGenerator >	cv::createFaceDetectionMaskGenerator ()

詳解

Haar Feature-based Cascade Classifier for Object Detection

The object detector described below has been initially proposed by Paul Viola [Viola01] and improved by Rainer Lienhart [Lienhart02] .

First, a classifier (namely a cascade of boosted classifiers working with haar-like features) is trained with a few hundred sample views of a particular object (i.e., a face or a car), called positive examples, that are scaled to the same size (say, 20x20), and negative examples - arbitrary images of the same size.

After a classifier is trained, it can be applied to a region of interest (of the same size as used during the training) in an input image. The classifier outputs a "1" if the region is likely to show the object (i.e., face/car), and "0" otherwise. To search for the object in the whole image one can move the search window across the image and check every location using the classifier. The classifier is designed so that it can be easily "resized" in order to be able to find the objects of interest at different sizes, which is more efficient than resizing the image itself. So, to find an object of an unknown size in the image the scan procedure should be done several times at different scales.

The word "cascade" in the classifier name means that the resultant classifier consists of several simpler classifiers (stages) that are applied subsequently to a region of interest until at some stage the candidate is rejected or all the stages are passed. The word "boosted" means that the classifiers at every stage of the cascade are complex themselves and they are built out of basic classifiers using one of four different boosting techniques (weighted voting). Currently Discrete Adaboost, Real Adaboost, Gentle Adaboost and Logitboost are supported. The basic classifiers are decision-tree classifiers with at least 2 leaves. Haar-like features are the input to the basic classifiers, and are calculated as described below. The current algorithm uses the following Haar-like features:

The feature used in a particular classifier is specified by its shape (1a, 2b etc.), position within the region of interest and the scale (this scale is not the same as the scale used at the detection stage, though these two scales are multiplied). For example, in the case of the third line feature (2c) the response is calculated as the difference between the sum of image pixels under the rectangle covering the whole feature (including the two white stripes and the black stripe in the middle) and the sum of the image pixels under the black stripe multiplied by 3 in order to compensate for the differences in the size of areas. The sums of pixel values over a rectangular regions are calculated rapidly using integral images (see below and the integral description).

To see the object detector at work, have a look at the facedetect demo: https://github.com/opencv/opencv/tree/master/samples/cpp/dbt_face_detection.cpp

The following reference is for the detection part only. There is a separate application called opencv_traincascade that can train a cascade of boosted classifiers from a set of samples.

覚え書き

In the new C++ interface it is also possible to use LBP (local binary pattern) features in addition to Haar-like features. .. [Viola01] Paul Viola and Michael J. Jones. Rapid Object Detection using a Boosted Cascade of Simple Features. IEEE CVPR, 2001. The paper is available online at http://research.microsoft.com/en-us/um/people/viola/Pubs/Detect/violaJones_CVPR2001.pdf

関数詳解

groupRectangles() [1/4]

CV_EXPORTS_W void cv::groupRectangles	(	CV_IN_OUT std::vector< Rect > &	rectList,
		CV_OUT std::vector< int > &	weights,
		int	groupThreshold,
		double	eps = 0.2
	)

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。

groupRectangles() [2/4]

CV_EXPORTS void cv::groupRectangles	(	std::vector< Rect > &	rectList,
		int	groupThreshold,
		double	eps,
		std::vector< int > *	weights,
		std::vector< double > *	levelWeights
	)

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。

groupRectangles() [3/4]

CV_EXPORTS void cv::groupRectangles	(	std::vector< Rect > &	rectList,
		int	groupThreshold,
		double	eps = 0.2
	)

オブジェクト候補の長方形をグループ化します。

引数

rectList	矩形の入力・出力ベクトル。出力ベクトルには，保持された矩形とグループ化された矩形が含まれます．(Pythonのリストはその場では変更されません。)
groupThreshold	最小限可能な矩形の数から1を引いた値。しきい値は，矩形を保持するためにグループ化された矩形で利用されます．
eps	矩形の辺同士の相対的な差を利用して，矩形をグループにまとめることができます．

この関数は，汎用関数 partition のラッパーです．これは，類似したサイズと類似した位置にある矩形を結合する矩形の等価性基準を用いて，すべての入力矩形をクラスタリングします．この類似性は， eps によって定義されます．eps=0 の場合，クラスタリングは全く行われません．もしの場合，すべての矩形が1つのクラスタに入れられます．そして，groupThreshold以下の矩形を含む小さなクラスタは拒否されます．その他のクラスタでは，平均的な矩形が計算され，出力矩形リストに格納されます．

groupRectangles() [4/4]

CV_EXPORTS void cv::groupRectangles	(	std::vector< Rect > &	rectList,
		std::vector< int > &	rejectLevels,
		std::vector< double > &	levelWeights,
		int	groupThreshold,
		double	eps = 0.2
	)

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。

groupRectangles_meanshift()

CV_EXPORTS void cv::groupRectangles_meanshift	(	std::vector< Rect > &	rectList,
		std::vector< double > &	foundWeights,
		std::vector< double > &	foundScales,
		double	detectThreshold = 0.0,
		Size	winDetSize = Size(64, 128)
	)

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。