Closed xiaojing-19 closed 4 years ago
First, traverse the character element to obtain the element name and thus the ID. Then traverse the camera. Since the character has many sub-components, the position of the sub-component in the specified camera can be obtained through the “camera.WorldToScreenPoint(child.position)“ function. Thereby, the ID and key point position of the current character are obtained.
With the keypoints recorded, bbox can be obtained using the method described in the paper.
Thanks for your reply, I will try it. In the past few days, I tried to use the camera to render different layer and found that it consumes too much memory. Thanks again.
Hi, Recently, I also want to use unity to generate some data. I want to know how you annotate the id and the bbox, because there are multi-camera and multi-person.