0
$\begingroup$

When talking about lane detection in a road, usually robotic computer vision system give lines in an image.

For detecting obstacles, those system give Bounding Boxes.

My question is, for pedestrian (human) pose detection, in which format are the results given usually?

$\endgroup$
1
  • 1
    $\begingroup$ probably bounding boxes ... after all, a pedestrian is an obstacle $\endgroup$
    – jsotola
    Oct 31 '21 at 17:29
1
$\begingroup$

Typically any detected object would be reported with a bounding box. Then you have information for those objects, like heading, speed, etc., and you can project the bounding box's location into the future given its size and the path information.

$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.