• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 98 subscribers
  • Views 331 views
  • Users 0 members are here
Support feedback
Options
Options
Related

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.

CCS/IWR1642BOOST: No reference to functions in RADARDEMO_clusteringDBscan modules in people counting demo

amin merati
Intellectual 470 points
Part Number: IWR1642BOOST
Other Parts Discussed in Thread: IWR1642

Tool/software: Code Composer Studio

Hi there,

I have imported the dss and mss projects for people counting demo of IWR1642BOOST. I built the firmware and load the built firmware into EVM.

The built firmware does not seem to work or detect any cloud points or target whereas the original provided bin file, detects points and track people.

When I was investigating the code I noticed that there are files related to clustering points in folder:

C:\ti\mmwave_industrial_toolbox_3_1_1\labs\lab0011-pplcount\lab0011_pplcount_pjt\radarDemo\modules\clustering\dbscan\src

RADARDEMO_clusteringDBscan.c

RADARDEMO_clusteringDBscan_priv.c, etc.

However, it does not seem that the functions in this files have not been referenced in source code of demo? is that correct?

Is this module or files related to RADARDEMO_clusterTracker_create being used in building the people counting demo firmware (lab0011-pplcount\lab0011_pplcount_quickstart\xwr16xx_pcount_lab.bin)

or they are just left over unsed code?

One of the issues I have noticed is that when I flash the ready provided firmware (lab0011-pplcount\lab0011_pplcount_quickstart\xwr16xx_pcount_lab.bin) into IWR1642, in scenarios where two people walking side by side with a few centimeters gap between them, these two people seen as one big connected cluster of cloud points with no gap between two people and I wondered if using this clustering methods above can break down big cluster of points into two cluster corresponding to each person and get an accurate people count?

Thanks

Amin