IWR1642BOOST: How to improve the position accuracy of targets in people counting

Hi Michael,

This is going to be highly dependent on your specific scene and what kind of traffic you are likely to see in that scene.

These topics are discussed in the People Counting Customization Guide in the 'docs' folder of the lab. Let me know if you have more questions.


Cheers,
Akash

Hi Akash,

The scene is just as the people count demo shows (refer to mmwave_industrial_toolbox_3_1_1\labs\lab0011-pplcount), and I run the demo in a room of  6x10 meters. I set up the demo environment exactly as the demo guide requires. Basically, I've read all the documents related people counting and many about the radars. As you mentioned, in the pplcount_customization_guide.pdf, it lists several parameters which will impact the target track. But, even if I set the exact or correct parameters, it doesn't improve the track position accuracy. Moreover, according to my understanding about the algorithm process in IWR1642, I think the position data of the points cloud is generated in the DSP, and the tracker algorithm in ARM just utilize that data and output the track info; while, the parameters in customization guide may just refine the target track result.

As it shows in document of People Tracking and Counting Reference Design Using mmWave Radar Sensor.pdf of IWR1642, the WAYPOINT of (1, 4) will be detected at (0.87, 4.23), the error(difference) of which is very large and my demo result also gets the similar errors.  So, my question is how to improve the position accuracy of the target?

Cheers,

Michael

Hi Akash,

The scene is just as the people count demo shows (refer to mmwave_industrial_toolbox_3_1_1\labs\lab0011-pplcount), and I run the demo in a room of 6x10 meters. I set up the demo environment exactly as the demo guide requires. Basically, I've read all the documents related people counting and many about the radars. As you mentioned, in the pplcount_customization_guide.pdf, it lists several parameters which will impact the target track. But, even if I set the exact or correct parameters, it doesn't improve the track position accuracy. Moreover, according to my understanding about the algorithm process in IWR1642, I think the position data of the points cloud is generated in the DSP, and the tracker algorithm in ARM just utilize that data and output the track info; while, the parameters in customization guide may just refine the target track result.

As it shows in document of People Tracking and Counting Reference Design Using mmWave Radar Sensor.pdf of IWR1642, the WAYPOINT of (1, 4) will be detected at (0.87, 4.23), the error(difference) of which is very large and my demo result also gets the similar errors. So, my question is how to improve the position accuracy of the target?

Cheers,
Michael

Hi Akash,
I've noticed the position accuracy of IWR6843 is much better than IWR1642, the WAYPOINT of (0,4) being detected at (0.03, 4.0125). Is this difference between IWR6843 and IWR1642 caused by the algorithm or the hardware? If the algorithm, can the algorithm of IWR6843 be ported to IWR1642?

Regards,
Michael

Yes, OK.
Thanks.