Changes between Version 27 and Version 28 of GsocDSMGenerationToolForOSSIM


Ignore:
Timestamp:
Aug 8, 2014, 2:05:19 PM (10 years ago)
Author:
martidi
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • GsocDSMGenerationToolForOSSIM

    v27 v28  
    426426WHAT I GET DONE THIS WEEK:
    427427
    428 For a better selection of TPs, beside to the 3 sigma test, I have implemented a preliminary screening  for the points found with the Orb Feature Detector: the filter selects the better 2% of TPs which have the highest values of Brief descriptors.
    429 
    430 I have tested the 3 sigma test implemented last week and, as can be seen from the images attached, it is a good filter for outliers removal.
     428Beside to the 3 sigma test, I have implemented a preliminary screening  for the points found with the Orb Feature Detector: the filter selects the better 2% of TPs which have the highest values of Brief descriptors.
     429
     430I have tested the 3 sigma test implemented last week and, as can be seen from the images attached, it works well for outliers removal.
    431431
    432432[[Image(TP matched_no_filtered.jpg)]]
     
    435435I have solved the “radiometric” issue due to the conversion from raw images to opencv images used for the Disparity Map creation. I have noticed that different image equalization strongly change the SGM result.   
    436436
    437 Moreover, I have improved the Disparity Map generated manually refining the SGM parameters (i.e. ndisparities and minDisparities values).
     437Moreover, I have improved the Disparity Map generated (sede attached) by manually refining the SGM parameters (i.e. ndisparities and minDisparities values).
     438
     439[[Image(Disparity.jpg)]]
    438440
    439441I have uploaded the update code in the repository (https://github.com/martidi/OSSIM-GSoC-2014).
     
    441443[[BR]]
    442444WHAT I PLAN ON DOING NEXT WEEK:
     445
     446To solve the problem on which I am stuck.
     447
     448To investigate the influence that the change of the SGM parameters have on the quality of the Disparity Map generated.
     449
     450To automate the correct search of SGM parameters in relation to the different input images.
     451
     452To work on the conversion from the disparity map into a geocoded DSM.
     453
     454To test and control implementation efficacy – discuss results with mentors.
     455
     456[[BR]]
     457SOMETHING ON WHICH I AM BLOCKED:
     458
     459
     460
     461
     462
     463