OpenCV各个detector/descriptor/matcher的创建和使用

OpenCV里有很多的feature，建立和使用方法也比较杂，现在整理一下避免以后用到。

1、detector 

统一的定义方式：

Ptr  detector= FeatureDetector::create("STAR");

"FAST" – FastFeatureDetector

"STAR" – StarFeatureDetector

"SIFT" – SIFT (nonfree module)

"SURF" – SURF (nonfree module)

"ORB" – ORB

"BRISK" – BRISK

"MSER" – MSER

"GFTT" – GoodFeaturesToTrackDetector

"HARRIS" – GoodFeaturesToTrackDetector with Harris detectorenabled

"Dense" – DenseFeatureDetector

"SimpleBlob" – SimpleBlobDetector

除了统一定义方式之外，有的可以用它自己的feature名字定义，比如

SurfFeatureDetector detector；

SiftFeatureDetector detector;

FastFeatureDetector detector;

STARFeatureDetector detector;

还有一种统一定义方式：

cv::Ptr  detector2= cv::Algorithm::create("BRISK");

其中cv::可以去掉。

动态的特征点定义方式：

Ptr detector =

           newDynamicAdaptedFeatureDetector(

          AdjusterAdapter::create("SURF"), 100, 500, 5);

2、Descriptorextractor

统一定义方式：  Ptrextractor=DescriptorExtractor::create("SURF");

"SIFT" – SIFT

"SURF" – SURF

"BRIEF" – BriefDescriptorExtractor

"BRISK" – BRISK

"ORB" – ORB

"FREAK" – FREAK

个别定义方式：Ptr extractor=new SiftDescriptorExtractor;

Ptrextractor =newSurfDescriptorExtractor;

Ptrextractor =newBriefDescriptorExtractor;

其他定义方式：

 SurfDescriptorExtractor extractor;

SiftDescriptorExtractor extractor;

BriefDescriptorExtractor extractor;

其他的一些特征可以直接定义对象并用来detect和extract特征

http://docs.opencv.org/modules/features2d/doc/feature_detection_and_description.html?highlight=brisk#BRISK: public Feature2D

比方说 BRISK  BRISKD(60,4,1.0f);

  BRISKD.create("BRISK");

  BRISKD.detect(object,kp_object);

  BRISKD.compute(object,kp_object,des_object);

3、matcher

统一定义方式 Ptr matcher =DescriptorMatcher::create("FlannBased");

BruteForce (it uses L2 )

BruteForce-L1

BruteForce-Hamming

BruteForce-Hamming(2)

FlannBased

其他定义方式：

BFMatcher matcher(type);

normType – One of NORM_L1, NORM_L2, NORM_HAMMING,NORM_HAMMING2. L1 and L2 norms are preferable choices for SIFT andSURF descriptors, NORM_HAMMING should be used with ORB, BRISK andBRIEF, NORM_HAMMING2 should be used with ORB when WTA_K==3 or 4(see ORB::ORB constructor description).

FlannBasedMatcher matcher;