-
公开(公告)号：US11532127B2
公开(公告)日：2022-12-20
申请号：US17196664
申请日：2021-03-09
Inventor： Qingyue Meng , Chen Zhao
Abstract: The present application discloses a virtual object driving method, an apparatus, an electronic device and a readable storage medium, which relate to technical fields of artificial intelligence and deep learning. A specific implementing solution is as follows: obtaining a target image of a real object acquired by a camera when the real object makes a limb movement; inputting the target image into a coordinate acquisition model to obtain coordinates of a plurality of key points on a limb of the real object; determining a posture of the limb of the real object according to coordinates of each key point; driving, according to the posture of the real object, a virtual object displayed on a screen to present the limb movement of the real object. The method greatly reduces operation complexity and cost consumption when driving a virtual image.
Search Results
1
records
(took 0.014 seconds)
