Coder Social home page Coder Social logo

icp's People

Contributors

richardos avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

icp's Issues

using the transformation history

I have two arrays of different sizes .Array A (N2) and Array B(N2) . i am giving the points in these two arrays to your icp where i know that these points are corresponding to each other and the algorithm is aligning them correctly as well. i then get a transformation history of (N23) and i convert it to one (2*3) array by multiplying all of them together but when i apply this transformation matrix to the points i want to be aligned (array b). the mapping isnt taking place . thankyou

Would be nice if I could give it an initial transformation

Somehow the algorithm thinks it has aligned the two scans, but when I plot them they are far from aligned, I wonder if there is a way to input an initial transformation that the algorithm could work from. The function arguments do not seem to have such an argument.

From how much I understand ICP (which is very little), it still needs an initial estimate. But your algorithm does not seem to need that. Though I did not peek inside the hood too much, so i am not sure if this was a trivial thing on my side.

Return total transformation instead of list of transformations

What?

Replace the transformation_history return value of the icp()-function with transformation.
While the list of transformations might be interesting to investigate the convergence, the total transformation would be a more interesting return value for most applications.

Why?

For instance, it can be helpful when the point cloud has been created by processing a 2D image, which also might be transformed.

Help: How do you determine the distance threshold and point pairs!

Hi, i hope you can help me understand this better.

How do you determine the how much values the distance threshold and point pairs should be?

I had tried running it with 2 different distance threshold, 20 and 40. For 2 point clouds that only differs in rotation and translation, i am able to get a acceptable convergence (see below).

image

However, when i were to use point clouds that has a different size, rotation and translation the ICP convergence is unacceptable for a distance threshold of 40 compared to distance threshold of 20.

Distance Threshold - 20
image

Distance Threshold - 40
image

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.