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.

IWRL6432: Discrepancies between Object Tracking and Presence Detection

Part Number: IWRL6432

Tool/software:

Hi IWRL6432 Champ !

My customer successfully tested changing the sensor's cfg settings to output Presence Detection results in addition to Object Tracking and Classification. 

Here is what they have analyzed so far
1. Object Tracking : Need to set “boundaryBox”, “StaticBoundaryBox” parameter in cfg file
2. Presence Detection: Need to set “mpdBoundaryBox” parameter in cfg file
3. After setting each parameter separately, it works well in individual feature tests.

However, when “boundaryBox”, “StaticBoundaryBox”, and “mpdBoundaryBox” are all set and executed to test the integration of the two functions, there is a difference between the tracked position and the position of Presence.

Configure the test (Set up the integration area for Object Tracking and separate the integration area into two areas for Presence Detection)
1. configure “boundaryBox”, “StaticBoundaryBox” as follows
boundaryBox -3.5 3.5 0 4 0 3
StaticBoundaryBox -3.5 3.5 0 4 0 3
2. configure the “mpdBoundaryBox” as follows
Zone I : mpdBoundaryBox 1 -3.5 3.5 0 2 0 3
Zone II : mpdBoundaryBox 2 -3.5 3.5 2 4 0 3
3. Test Results
Object Tracking's resultant locations are in Zone II, but Presence locations are in Zone I or cannot be extracted.

Object Tracking: Located in Zone I 

Presence : Aware of being in Zone I (yellow line) 

Object Tracking: Located in Zone II

Presence : Not aware of location (no line color change)

After testing, it appears that the boundaryBox, a parameter for Object Tracking, affects Presence.

Can you please check Inconsistency issues btw Object Tracking and Presence Detection on IWRL6432 BOOSTEVM?

Thanks.

Regards, 

Jack

  • Hi 

    They are doing further testing on the following issue.

    The tests in the previous email were performed using the Industrial Visualizer built using the cfg file with the default settings.

    In further testing, we have been comparing the cfg files of the IWRL6432 EVM with the cfg files of the IWRL6432AOP EVM and found the main differences in the following.

    IWRL6432 EVM  chirpCommCfg 16 0 0 128 4 28 0
    IWRL6432AOP EVM  chirpCommCfg 15 0 0 128 1 28 2

    After checking, it seems to be a difference in the BPM/TDM mode, so I changed the mode from TDM(1) to BPM(4) and tested it, and I saw a big improvement over the previous contrast, although some of the tracking data does not follow the point cloud.

    However, after running the program and loading the cfg, I noticed that there is a WARNING in the log like below.
    Warning! BPM is not supported on this device

    It's hard to tell if the improvement is due to the change to BPM mode. Or is there something else going on?

    Please check this out.


    Also, the inconsistency between Object Tracking and Presence that I asked about before seems to be improved in IWRL6432AOP EVM (I don't know if there is anything specially handled...).

    Please confirm this as well.

    Thanks.

    Best Regards, 

    Jack 

  • Hi Jack,

    Does zone 2 show presence in the boundary box is set to a different location?

    boundaryBox -4 4 0 5 0 3
    StaticBoundaryBox -4 4 0 5 0 3

    I wonder if the issue is with displaying the color change when the boxes are on top of each other.

    Does it show presence in zone 2 when boundaryBox and StaticBoundaryBox are removed?

    Best,

    Nate

  • Hi Nathan

    They did a test regarding the above,
    When they modified the position of the boundaryBox to the above values, there was no significant difference in the results.

    And when they did it with the boundaryBox, StaticBoundaryBox removed, they found that the Presence position came out correctly.

    Thanks.

    Regards, 

    Jack

  • Hi Nathan

    Sorry customoer found the reasone of the issue.
    Regarding the issue, they did a fresh load to initialize the binary and it seems to have resolved the issue.

    Thanks.

    Best Regards, 

    Jack

  • Thank you Jack. I am closing this thread.

    Best,

    Nate