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.

AWR1642BOOST-ODS: How to capture the point cloud data using matlab or python

Part Number: AWR1642BOOST-ODS
Other Parts Discussed in Thread: AWR1642, DCA1000EVM

I successfully run the people counting lab from industrial tool 4.0 using MATLAB. However, I couldn't find any way to capture the real-time time and like to save the data in .npy or .csv files. if anyone has an idea about this, kindly help me solve this issue. it would be a great


  • Hi Nagendra,

    So in general when we capture the data from the AWR1642, we use the DCA1000 for the raw data capture.
    Then there is a python parser script that is provided in the mmwave SDK 3.5.
    This can be found under the directory
    Under this in section 3.3.2 you will find more details about this python script.

    Saswat Kumar

  • Hi,

    Thanks for your reply. currently, we don't have DCA 1000 EVM to capture the data. is there any way to capture the data?

  • Hi,

    I have assigned this thread to the team that supports People Counting Demo.

    Thank you


  • Hi,

    To be clear, you do not need to use the DCA1000EVM in order to capture point cloud data, only if you want to capture the Raw ADC data. In order to capture the demo output, there are a few different ways to do it. In general, I would say there are 2 different formats which may be helpful.

    1. Capture the output UART data stream from the device, which can then be parsed to get the output data.

    2. Parse the UART stream live, and then output the information which you want to a CSV file or similar.

    I typically recommend option 1, as it is easier and it ensures that you capture ALL output data, in case you change your mind on which pieces of the output that you want. If you want to do option 1, you can simply connect to the device via a serial terminal and enable logging on the data port (ensure it is logging using binary data format). I recommend using Teraterm for this, but i'm sure other serial terminal programs offer similar functionality.

    For option 2, you would likely want to modify the visualizer/parser script which is included with the demo to write the information which you want to the csv format or similar. I'm not sure exactly how you would want to format your output, so my guidance is a bit more limited here. However, you should be able to find many examples online of how to write data to CSV files or similar in Matlab or Python.

    Best Regards,