I'm trying to implement this approach for object detection and tracking.

In this approach, the first step is voxelize each frame to construct a 3D tensor, the second step is to append multiple voxels at the time along a new axis to create a 4D tensor.

What I want to understand is how to voxelize multiple frames at the time and append them together.

  • 1
    $\begingroup$ Hi and welcome to this community! Your question is currently too broad. Please, specify which details you have not understood and ask one question. $\endgroup$ – nbro Jul 1 '19 at 9:00
  • 1
    $\begingroup$ @nbro thank you for the clarification but the details are linked and couldn't be put in one question as i want to understand the steps? what do you suggest? thank you $\endgroup$ – OneManArmy Jul 1 '19 at 9:01
  • 2
    $\begingroup$ I suggest that you ask a question regarding the first thing in the paper that doesn't allow you to proceed. Once this is clarified, you can ask another question (in another post). If you ask someone to explain to you the paper, then it will require maybe an answer which is longer than the paper, which is of course too much. $\endgroup$ – nbro Jul 1 '19 at 9:03
  • 1
    $\begingroup$ understood. thank you $\endgroup$ – OneManArmy Jul 1 '19 at 9:07
  • 2
    $\begingroup$ Agreed with nbro here. The question "Can anyone be kind enough to walk me through it" is a problem. It is too much work for most volunteers to write a tutorial for a whole system implementation, and not at all clear which details you need help with. Ask about the first step where you struggle, and give details in the question. Use edit to add them $\endgroup$ – Neil Slater Jul 1 '19 at 10:05

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.