Finger detection in 3D point cloud

摘要

Techniques are described for detecting the presence and positions of fingers using depth information. For each of multiple target points represented by a depth image, an evaluation is performed using a region of points surrounding the pixel. The region has an inner zone and side zones. Multiple iterations are performed for each target pixel, with different sizes and orientations of the region being used in the different iterations. An average depth and an average surface normal direction are determined for each zone. The average depth and average surface normal direction of the inner zone are compared to the average depths and the average surface normal directions of the side zones to determine whether the target pixel is part of a finger.

主权项

1. A system comprising:
one or more processors; a depth sensor configured to capture a depth image, wherein the depth image indicates a depth for each of a plurality of surface points; one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
selecting a target surface point of the plurality of surface points;selecting a circular region of surface points surrounding the target surface point, wherein the circular region has a first side zone and a second side zone that are opposite each other and an inner zone between the first side zone and the second side zone;averaging depths of surface points within the first side zone to determine an average depth of the first side zone, averaging depths of surface points within the second side zone to determine an average depth of the second side zone, and averaging depths of surface points within the inner zone to determine an average depth of the inner zone;averaging surface normal directions of surface points within the first side zone to determine an average surface normal direction of the first side zone, averaging surface normal directions of surface points within the second side zone to determine an average surface normal direction of the second side zone, and averaging surface normal directions of surface points within the inner zone to determine an average surface normal direction of the inner zone;determining that a first difference between the average depth of the inner zone and the average depth of the first zone is greater than a first threshold;determining that a second difference between the average depth of the inner zone and the average depth of the second zone is greater than the first threshold;determining that a third difference between the average surface normal direction of the inner zone and the average surface normal direction of the first zone is greater than a second threshold;determining that a fourth difference between the average surface normal direction of the inner zone and the average surface normal direction of the second zone is greater than the second threshold; anddetermining that the target surface point corresponds to a finger surface.