CPC G06T 7/0012 (2013.01) [G06T 7/40 (2013.01); G06T 7/521 (2017.01); G06T 7/73 (2017.01); G06V 10/46 (2022.01); G06V 10/56 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/30036 (2013.01)] | 11 Claims |
1. A method for generating a three-dimensional image, comprising:
capturing a set of color images of an object, wherein the set of color images is related to color information of the object;
capturing a set of structure images of the object, wherein the set of structure images is related to depth information of the object;
generating a first point cloud according to the set of color images and the set of structure images, wherein the first point cloud is related to a rigid surface and a non-rigid surface of the object;
generating a second point cloud by performing a filtering operation to the first point cloud according to the set of color images, wherein a relativity of the second point cloud and the rigid surface is higher than a relativity of the second point cloud and the non-rigid surface;
selectively performing a pairing operation using the second point cloud and a target point cloud to generate pose information; and
combining the first point cloud and the target point cloud according to the pose information to update the target point cloud to generate the three-dimensional image of the object;
wherein:
capturing the set of structure images of the object, comprises:
projecting a set of light patterns to the object; and
generating the set of structure images according to distribution of the set of light patterns on a surface of the object; and
generating the first point cloud according to the set of color images and the set of structure images, comprises:
processing the set of structure images to generate the depth information of the object;
generating the color information of the object according to the set of color images; and
generating the first point cloud according to the depth information and the color information.
|