• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 30 subscribers
  • Views 287 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

IWR6843ISK-ODS: Inquiring about the issue of "Surface Classification" training data and range bins

Jeff Yang
Prodigy 80 points
Part Number: IWR6843ISK-ODS

Hello,

In the Surface Classification User Guide (https://dev.ti.com/tirex/explore/node?node=A__APPKM14lbP0fVv74GsLHGw__radar_toolbox__1AslXXD__LATEST&placeholder=true), I saw a chart in the physical setup section.

Due to the height and angle of the setup, the range bin is set from 6 to 31 (26 bins) as the input for the CNN model.

Here, after parsing MMWDEMO_OUTPUT_MSG_RANGE_PROFILE with Python, I obtained 128 values.

So, is the training data composed of values from the 6th to the 31st?

This is important because we will need to adjust the height of the radar in our application scenario, which might change the range of the training data.

Thank you.

Jeff Yang

  • +1
    TI__Mastermind 22297 points

    Hello Jeff,

    That is correct, the base MMWDEMO_OUTPUT_MSG_RANGE_PROFILE will output all 128 range bins, and it is up to the user's software to only take bins 6 through 31 and feed that to the model. The pregenerated model that comes with the Radar Toolbox was trained using only bins 6 through 31, however one could create a model trained from whatever range of bins desired.

    Best Regards,

    Pedrhom