Back to results
US 12,749,263 B2Granted
Method and system of multi-view image processing with accurate skeleton reconstruction
AssigneeIntel Corporation
InventorsLongwei Fang, Yikai Fang, Hongzhi Tao, Qiang Li, Hang Zheng
Life of this patent
Estimating the term…
Abstract
A method and system of multi-view image processing with accurate skeleton reconstruction uses joint confidence values.
Claims17
A computer-implemented system comprising:
- memory to store a plurality of sequences of images of a plurality of perspectives of a same scene;
- instructions;
- and
- at least one processor circuit to be programmed based on the instructions to:
- generate a three-dimensional (3D) skeleton with joint points at respective joint locations of the skeleton based on the images;
- increment a joint error indicator based on a connection to at least one of the joint points not meeting a criterion, the criterion based on one or more datasets of measured skeletons of people;
- refine one or more distances from one or more of the joint locations to at least one other of the joint locations of the skeleton based on the joint error indicator and comparison of the one or more distances to information in the one or more datasets of measured skeletons of people;
- and
- modify, based on the refined one or more distances, one or more of the joint locations associated with at least one connection that does not pass the criterion.
6 more elements
At least one non-transitory machine-readable medium comprising instructions to cause at least one processor circuit to at least:
- determine joint clusters of candidate three-dimensional (3D) points based on images of a plurality of perspectives of a scene, the joint clusters corresponding to respective different joints on a 3D skeleton of a person in the scene;
- determine whether distances between pairs of candidate 3D points of two clusters of the skeleton satisfy a first criterion, the first criterion based on measured joint distances of people, the two clusters including a first cluster and a second cluster;
- increment a joint confidence value of a first candidate 3D point of the first cluster based on a point of the second cluster having a distance to the first candidate 3D point that satisfies the first criterion, the increment being a fraction of one over a number of points in the second cluster, wherein a total confidence value of the first candidate 3D point of the first cluster is to represent a proportion of the points of the second cluster that satisfy the first criterion;
- generate joint points of the skeleton based on the candidate 3D points that satisfy the first criterion;
- and
- refine locations of the joint points of the skeleton based on a second criterion.
3 more elements
A method comprising:
- obtaining joint clusters of candidate three-dimensional (3D) points based on images of video sequences of a same scene, the joint clusters corresponding respectively to different joints on a 3D skeleton;
- determining whether a first joint confidence value representative of distances between pairs of the candidate 3D points of two of the joint clusters passes at least one criterion, the at least one criterion based on a dataset, the dataset based on measured joint distances of human beings;
- generating a second joint confidence value for an individual candidate 3D point in a first joint cluster of the joint clusters, the second joint confidence value to indicate how many points in a second joint cluster of the joint clusters are a distance from the individual candidate 3D point that passes the at least one criterion;
- and
- keeping the individual candidate 3D point in the first joint cluster based on the second joint confidence value passing at least another criterion.
2 more elements
Dependencies are inferred from the claim text.