Giter VIP home page Giter VIP logo

Comments (6)

TixiaoShan avatar TixiaoShan commented on July 1, 2024 1

@kinggreat24
Unfortunately, I didn't get good results using the KITTI dataset. One thing that might improve the recall is to relieve some of the parameters, for example,

min_loop_feature_num: 15 # minimum feature number threshold
and
min_loop_bow_th: 0.015 # BOW search threshold
. Or, increase the number of features to be detected.

from imaging_lidar_place_recognition.

kinggreat24 avatar kinggreat24 commented on July 1, 2024

@TixiaoShan
Hi, thanks for your help, I have tried your suggestion and it does work.

from imaging_lidar_place_recognition.

kinggreat24 avatar kinggreat24 commented on July 1, 2024

In fact, this article turns the lidar data into a range image, and then uses the features to be extracted from the image to perform feature matching, loop closure detection, and relative transformation calculations. Therefore, I changed velodyne's lidar into range image and then used the author's method to test, so that different types of lidars can do the same thing. The difference lies in the sparseness of the lidar. The author also mentioned the sparseness Lidar, such as VLP-16, may not work well with this method.

from imaging_lidar_place_recognition.

Grandzxw avatar Grandzxw commented on July 1, 2024

lidar

In fact, this article turns the lidar data into a range image, and then uses the features to be extracted from the image to perform feature matching, loop closure detection, and relative transformation calculations. Therefore, I changed velodyne's lidar into range image and then used the author's method to test, so that different types of lidars can do the same thing. The difference lies in the sparseness of the lidar. The author also mentioned the sparseness Lidar, such as VLP-16, may not work well with this method.

In factor, the author turn the lidar data into intensity image. So do you mean that you turn it to range image? And in kitti data, it lack many intensity data.

from imaging_lidar_place_recognition.

0ontheroad avatar 0ontheroad commented on July 1, 2024

Hi, @TixiaoShan Thanks for sharing your great work, I have test the method using KITTI dataset. The results show that reverse visiting detection performance is not well while the forward direction is pretty good, do you have any ideas about improving the reverse visiting recall?

Screenshot from 2021-04-23 16-02-10 Screenshot from 2021-04-23 15-55-25

Hi:
To run the code in KITTI dataset, how do I modify the code. Thanks a lot!!!!

from imaging_lidar_place_recognition.

0ontheroad avatar 0ontheroad commented on July 1, 2024

@kinggreat24
Hi:
To run the code in KITTI dataset, how do I modify the code. Thanks a lot!!!!

from imaging_lidar_place_recognition.

Related Issues (8)

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.