• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 31 subscribers
  • Views 218 views
  • Users 0 members are here
Support feedback
Options
Options
Similar topics

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.

IWR1642BOOST: Acquiring and processing data for Point Cloud(heatmap) creation

Ray Vincent Aranzaso
Genius 13515 points
Part Number: IWR1642BOOST
Other Parts Discussed in Thread: IWR6843, IWR1642, IWR1843

Hi,

Good Day. I have a customer who is working with IWR1642BOOST. Please see below his query for your reference. Thank you very much.

We have some issues with acquiring and processing data from an IWR1642BOOST.
Specifically, we are using it to separately detect and track cars and pedestrians on a crosswalk.

Could you, please, give us some tips regarding these questions:

1) How can we acquire the Point Cloud(range-azimuth, range-velocity heatmap frames), using Python (preferably), or any other programming language in real time (10-20 fps)? Can a PC be used for this, or we should run the process on board and transfer the processed data?

2) How to aquire data, related to the classificated objects?

We'd like to get results similar to those presented in the following article on page 5 (figure 2) and page 6 (figure 3)
(https://www.ti.com/lit/wp/spyy002b/spyy002b.pdf?ts=1629662251767&ref_url=https%253A%252F%252Fwww.google.com%252F)

Best Regards,

Ray Vincent

  • 0
    TI__Genius 14285 points

    Hello Ray,

    Is there a specific reason they are using the IWR1642? I think the IWR6843 is usually used for these applications with 60GHz radar, but it can vary. 

    There is an example of reading in the UART output data into python at the following location. 
    C:\ti\mmwave_industrial_toolbox_4_8_0\labs\people_counting\visualizer

    This typically works with the 3D people counting demo which doesn't run on the 1642, but the 6843. The out of box demo output is supported by this visualizer, so you can run the 1642 out of box demo and see an example of how to parse the output in python.

    The traffic monitoring demo can be used with the IWR1843, which will interface well with the visualizer running in matlab. This is the demo running in the above document.  This will also interface with the python demo (select long range people counting parser) but full support is not there. 

    https://dev.ti.com/tirex/explore/node?a=VLyFKFf__4.8.0&node=AFX52y3KwfxdmIN5Nkcfjg__VLyFKFf__4.8.0

    Regards,

    Jackson