Why not using OpenCV's ORB extractor? about orb_slam2 HOT 2 CLOSED

Thanks for your answer. I can understand it now :) @Ashwinning

from orb_slam2.

According to the readme :

the extraction of ORB is slightly different (trying to improve the dispersion on the image)

I see that the method signatures are different as well, with the new minThFAST variable in ORB_SLAM2

ORB_SLAM's ORBextractor.cc

ORBextractor::ORBextractor(int _nfeatures, float _scaleFactor, int _nlevels, 
         int _scoreType, int _fastTh):
    nfeatures(_nfeatures), scaleFactor(_scaleFactor), nlevels(_nlevels),
    scoreType(_scoreType), fastTh(_fastTh)

ORB_SLAM2's ORBextractor.cc

ORBextractor::ORBextractor(int _nfeatures, float _scaleFactor, int _nlevels,
         int _iniThFAST, int _minThFAST):
    nfeatures(_nfeatures), scaleFactor(_scaleFactor), nlevels(_nlevels),
    iniThFAST(_iniThFAST), minThFAST(_minThFAST)

From the example yaml file :

ORB Extractor: Fast threshold
Image is divided in a grid. At each cell FAST are extracted imposing a minimum response.
Firstly we impose iniThFAST. If no corners are detected we impose a lower value minThFAST
You can lower these values if your images have low contrast

from orb_slam2.