Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

What settings to get good results for Kitti 00? #8

Open
jimmxuu opened this issue Jul 7, 2020 · 3 comments
Open

What settings to get good results for Kitti 00? #8

jimmxuu opened this issue Jul 7, 2020 · 3 comments

Comments

@jimmxuu
Copy link

jimmxuu commented Jul 7, 2020

I am getting nowhere near your results for Kitti path 00. What parameters did you set to get that Kitti 00 figure?

@jimmxuu
Copy link
Author

jimmxuu commented Jul 8, 2020

I changed default settings to match the settings.cpp in the base stereo dso and got matching results.

    setting_desiredImmatureDensity = 1500;   
    setting_desiredPointDensity = 2000;       
    setting_minFrames = 5;
    setting_maxFrames = 7;
    setting_maxOptIterations=6;
    setting_minOptIterations=1;

    setting_kfGlobalWeight=0.3;  
    setting_maxShiftWeightT= 0.04f * (640 + 128);  
    setting_maxShiftWeightR= 0.04f * (640 + 128);  
    setting_maxShiftWeightRT= 0.02f * (640 + 128); 

@LinHuican
Copy link
Owner

Nice to hear you solved the problem!

@jimmxuu
Copy link
Author

jimmxuu commented Jul 11, 2020

Thank you! May I ask how you decided on these settings? The author of Direct Sparse Odometry states that most of his settings.cpp should not be changed, but you did change these settings for different datasets. The comments in his code suggest that they affect keyframe processing, but I do not fully understand. Can you explain? Any help would be greatly appreciated.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants