I am doing a project for identfication of people using IWR6843ISK. I want the TID,x,y,z,velocity from the point cloud output. How to extract that?
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.
I am doing a project for identfication of people using IWR6843ISK. I want the TID,x,y,z,velocity from the point cloud output. How to extract that?
Hello,
For the 3D people counting demo, those are all part of the UART output data. The UART data format is detailed in the user's guide below.
There is an example of parsing the UART data in the file OOB_parser.py included in the toolbox download below.
"C:\ti\mmwave_industrial_toolbox_4_6_0\labs\people_counting\visualizer"
Regards,
Jackson
Hello,
Is this the output from the people counting visualizer? Can you please list which binary file you have loaded and which cfg file you are using?
The visualizer from toolbox 4.6.0 will only work with the binary and cfg files from that toolbox release. They can be found at the following path,
"C:\ti\mmwave_industrial_toolbox_4_6_0\labs\people_counting\68xx_3D_people_counting"
It looks like the data was not all collected. The points in the point cloud should be listed under the "elev azim doppler range SNR" line. Please try again with the updated binary files.
Regards,
Jackson
I used the same. For voxelising the point cloud I want to take x,y,z and velocity. This is sparse point cloud data, isn't? I have to use this for a neural network
Hello,
The UART data format is detailed in the toolbox link above, in the People Counting Demo user's guide, have you looked at this?
The .csv file created by the visualizer should save the pointcloud data. This data will be in spherical coordinates for the pointcloud so you will need to translate it into cartesian coordinates. You can find this from many different sources online.
Regards,
Jackson