static Ptr<ORB> cv::ORB::create (
int nfeatures = 500,
float scaleFactor = 1.2f,
int nlevels = 8,
int edgeThreshold = 31,
int firstLevel = 0,
int WTA_K = 2,
int scoreType = ORB::HARRIS_SCORE,
int patchSize = 31,
int fastThreshold = 20
)
nfeatures:表示取的特征點數量
float scaleFactor = 1.2f :表示每一層與上一層的比例關系
int nlevels = 8,:圖像金字塔的層數
edgeThreshold = 31,預設吧,看不懂解釋
firstLevel = 0, 預設吧,看不懂解釋
int WTA_K = 2, 表示描述符随機數的範圍,2表示描述符的數字随機取0,1。3表示随機取0,1,2。一般都是2
scoreType = ORB::HARRIS_SCORE,這表示用harris特征來給定分數。一般預設用這個。
patchSize = 31,預設吧,看不懂解釋
fastThreshold = 20預設吧,看不懂解釋
英文詳解:
https://docs.opencv.org/3.2.0/db/d95/classcv_1_1ORB.html#adc371099dc902a9674bd98936e79739c