Work of Camera Calibration (6) : Meeting and Having discussion with Matina (1)

I. Flip the Kinect frames which may cause misalignment of mapping

。'fliplr' and 'flipud' are 2 functions included in the Computer Vision Toolbox in MATLAB

。Result of doing 'fliplr: (the upper one is 'before fliplr'; the lower one is after 'fliplr')

。Results of matching by SIFT feature: (the upper one is 'before fliplr'; the lower one is after 'fliplr')

II. Re-design experiments of checking mapping results between Kinect frames & Hand-held 
     camera frames

。The process should be progressed in these order:  easier cases, normal cases, difficult cases

。Collecting these 4 databases: rotation, scaling, change perspective, affine

。Do matching by using SIFT first, then thinking more additional features which could be included

III. Studying the following literature to get more ideas about useful features in our work

。http://www.robots.ox.ac.uk/~vgg/research/affine/: (especially this work)

    K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir and L. 
    Van Gool, A comparison of affine region detectors. In IJCV 65(1/2):43-72, 
    2005

。'feature matching' is description of functions included in the Computer Vision Toolbox in MATLAB

IV. May be trying to use my proposed method based on feature matching to test our collecting 
      dataset mentioned in 'II'

V. Considering to stitch several Kinect frames into one after checking current results of feature
      mapping is acceptable
   

。Relevant method: http://www.cs.bath.ac.uk/brown/autostitch/autostitch.html