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.

Human vs non human classification using doppler effect

Other Parts Discussed in Thread: AWR1642, AWR2243

Hello,

I am trying to develop an application for classification of human vs non-human targets. I build an app that calculates the range and doppler vs distance and I was thinking that it is posible to use the later one for an classification process.

I have 2 questions on this matter:

1. It is possibile to achieve the classification using the doppler effect?

2. If it is possible, are there any public datasets that I can use for my project?

Thanks,

  1. Iulian
  • Hello Iulian,

    1. You can achieve classification using the doppler effect by recognizing similar patterns in doppler when coming from a human vs non-human. An AI trained model looking at range profile or doppler binning can do this.

    2. We at TI do not currently have any public datasets. Any datasets we currently have were made in-house and are private.

    Best Regards,

    Pedrhom Nafisi

  • Hello Pedrhom,

    Thank you for the response. In the meantime I found on github dataset that was done using AWR1642 BOOST. Even if i use a AWR2243 BOOST i do not think that will impose a problem if i set the parameters for my radar as was done in that data gathering.

    Now I will try to do the classification.