• State TI Thinks Resolved
  • Locked Locked
  • Replies 3 replies
  • Answers 2 answers
  • Subscribers 31 subscribers
  • Views 485 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.

RTOS/TIDEP-01000: Sensitivity and Processing power of mmWave Radar Sensor

Jeongdai Kim
Intellectual 400 points
Part Number: TIDEP-01000

Tool/software: TI-RTOS

Is this part sensitive enough to count the leaves on a tree? Is this part capable of processing video frames to detect very little movements -- does it have enough sensitivity and processing power to go through movement of leaves, and count them accurately if it is combined with other parts? 

  • 0
    TI__Mastermind 28055 points

    Hi Jeongdai,

    The device is sensitive enough to see the leaves of the tree move. However, it will not be able to count the leaves with the current implementation of the signal processing chain.  You may be able to count the leaves with an advanced algorithm, but we are not currently supporting this use case.

    Regards,

    Justin

  • 0 in reply to Justin Curewitz
    Intellectual 400 points

    Thank you for the response.  How about counting the number of people who are in a small space? Their bodies are overlapping with each other, and, in some cases, heads are not visible, but some body parts.  Is this use case supported? For instance, in a rock concert, where people are moving and dancing, can this device count dynamic objects with partial visibility?  Does it depend on algorithms user can develop within the device or, is it limited by the capacity of the device?  

  • 0 in reply to Jeongdai Kim
    TI__Mastermind 28055 points

    Hi Jeongdai,

    Please see our people counting demo for an example of counting people.  The radar sensor will sense many detected points in a scene, then a high level algorithm clusters and tracks these points.  This works with people because each person will create multiple detection points, so they appear as a cluster to the device.

    Regards,

    Justin