Git Product home page Git Product logo

Comments (3)

BAILOOL avatar BAILOOL commented on July 18, 2024 1

@Grungeby52 great question. I assume your ORB keypoints are based on OpenCV.

ORB uses FAST keypoints under the hood and filters them with TopN point selection based on keypoint strength before extracting the ORB descriptor. Several ideas come to mind:

  • In order to use ANMS algorithms in this repo without modifying too much code, you'd need to return many more points from the ORB detector and then apply ANMS on those. This is not practical if speed is important.

  • Disabling TopN filtering would be another option but it would require modifying OpenCV core functionality. Not recommended.

  • The most practical solution is to extract FAST keypoints manually, filter them using ANMS, and extract ORB descriptors for selected keypoints. This is exactly what we did for experiments in the paper (Section 4.5: Application to SLAM)

from anms-codes.

Grungeby52 avatar Grungeby52 commented on July 18, 2024

Hello,

Thanks for quick feedback,
As far as I understand, you are telling me to homogenize the key point I got with FAST in the 3rd recommendation. Did I get it right?

Best Regards,

Onur Güzeldemirci

from anms-codes.

BAILOOL avatar BAILOOL commented on July 18, 2024

@Grungeby52, yeah, I'd recommend using the 3rd option: get FAST points, homogenize them with ANMS, and then extract ORB descriptor for the selected points.

from anms-codes.

Related Issues (11)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.