• State TI Thinks Resolved
  • Locked Locked
  • Replies 2 replies
  • Answers 1 answer
  • Subscribers 31 subscribers
  • Views 223 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.

TIDEP-01000: SW setups

Kien
Expert 3520 points
Part Number: TIDEP-01000

Hi team,

Is there any documentation to show how to setup the SW for all the test cases of the ref design?

1. Waypoint localization

2. People Counting Density

3. People Counting Accuracy

4. People counting in a conference room

5. Extending detection range

I have the HW but I don't know how to do all the tests mentioned.

  • 0
    TI__Mastermind 28055 points

    Hi Kien,

    To repeat the tests:

    1. Follow quickstart guide to run the software
    2. Setup a test environment.  With waypoint, we set up cones at the areas we want to measure, then record the GUI as well as have a camera record the person's movement.
    3. Capture a test vector by running the GUI then pressing "Exit" when you are done.  This will create a file call "fHistRT.mat"
    4. Watch the GUI and Ground truth vector to determine in which frame you are standing at a measurement location/waypoint.
    5. Open that frame in the fHist and look at the target List. There is a value called "S", which is a 6xN vector, where N is the number of targets.  For each target the first row is the X coordinate and the second row is the Y coordinate. You can compare these to the real location.

    Our tests are described in the TI Design document - you should be able to repeat them as described, and use the fHist for getting sensor output data.

    Regards,

    Justin

  • 0 in reply to Justin Curewitz
    TI__Expert 3520 points

    Hi Justin,

    Thanks for your prompt reply.

    I will try that.