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

Consultation about the parameter values setting of getPointCloudPolarInd() #13

Open
Dr-Yongqiang opened this issue Aug 20, 2023 · 2 comments

Comments

@Dr-Yongqiang
Copy link

Hello, the codebase you've developed is truly excellent! May I kindly inquire about the recommended settings for the parameters "peakDistance" and "peakProminence" when using the function getPointCloudPolarInd()?

@Samleo8
Copy link
Owner

Samleo8 commented Jan 17, 2024

Hi, sorry for the late reply. These are parameters come from, and are described in more detail in the original paper: https://arxiv.org/pdf/2104.05347.pdf

I believe choosing them requires a little bit of trial-and-error, and would be related to the configurations/parameters specific to your radar sensor. Of course, you can tune the algorithm to be more or less sensitive to peaks by changing this params, but it is environment specific.

@atomicapple0
Copy link
Collaborator

For getPointCloudPolarInd, we never actually ever pass in non None values for peakDistance or peakProminence in our code base. That function calls scipy.signal.find_peaks(azimuthReading, distance=peakDistance, prominence=peakProminence) so we just use the default scipy value. As @Samleo8 said, you may want to play around with various parameters based on your specific dataset.

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

3 participants