Back to results
US 12,482,125 B1Granted
System and method for box segmentation and measurement
Assignee4DMobile, LLC
InventorsMatthew D. Miller, Josh Berry, Mark Boyer, Craig M. Miller
Life of this patent
Estimating the term…
Abstract
A mobile device is capable of being carried by a user and directed at a target object. The mobile device may implement a system to dimension the target object. The system, by way of the mobile device, may image the target object to and receive a 3D image stream, including one or more frames. Each frame may include a plurality of points, where each point has an associated depth value. Based on the depth value of the plurality of points, the system, by way of the mobile device, may determine one or more dimensions of the target object.
Claims18
A volume dimensioning system, comprising:
- an image sensor configured to capture imaging data associated with a target object positioned on a surface, the imaging data comprising a sequence of frames, each frame comprising a depth map with two-dimensional (2D) pixel coordinates and a plurality of depth values;
- and
- one or more processors in communication with the image sensor, the one or more processors configured to:
- identify an origin point within the plurality of depth values;
- wherein the origin point is associated with a top corner of the target object;
- wherein the origin point is a local minimum of the depth values within a cursor of the imaging data;
- wherein the one or more processors are configured to examine the depth values for the local minimum to identify the origin point;
- crawl from the origin point along a first edge to a first corner, along a second edge to a second corner, and along a third edge to a third corner of the target object to detect the first edge, the first corner, the second edge, the second corner, the third edge, and the third corner;
- deproject the depth map into three-dimensional (3D) points;
- construct a first edge vector representing the first edge from the origin point to the first corner, a second edge vector representing the second edge from the origin point to the second corner point, and a third edge vector representing the third edge from the origin point to the third corner point using the 3D points;
- determine the target object is a cuboid by examining a first angle between the first edge vector and the second edge vector, a second angle between the first edge vector and the third edge vector, and a third angle between the second edge vector and the third edge vector;
- and
- estimate a first distance of the first edge using the first edge vector, a second distance of the second edge using the second edge vector, and a third distance of the third edge using the third edge vector.
10 more elements
A method comprising:
- obtaining, via an image sensor of a mobile device, imaging data associated with a target object positioned on a surface, the imaging data comprising a sequence of frames, each frame comprising a depth map with two-dimensional (2D) pixel coordinates and a plurality of depth values;
- identifying, via a volume dimensioning system, an origin point within the plurality of depth values, wherein the origin point is associated with a top corner of the target object;
- wherein identifying the origin point includes identifying a local minimum of the depth values within a cursor of the imaging data;
- wherein the depth values are examined for the local minimum to identify the origin point;
- crawling, via the volume dimensioning system, from the origin point along a first edge to a first corner, along a second edge to a second corner, and along a third edge to a third corner of the target object to detect the first edge, the first corner, the second edge, the second corner, the third edge, and the third corner;
- deprojecting, via the volume dimensioning system, the depth map into three-dimensional (3D) points;
- constructing, via the volume dimensioning system, a first edge vector representing the first edge from the origin point to the first corner, a second edge vector representing the second edge from the origin point to the second corner point, and a third edge vector representing the third edge from the origin point to the third corner point using the 3D points;
- determining, via the volume dimensioning system, that the target object is a cuboid by examining a first angle between the first edge vector and the second edge vector, a second angle between the first edge vector and the third edge vector, and a third angle between the second edge vector and the third edge vector;
- and
- estimating, via the volume dimensioning system, a first distance of the first edge using the first edge vector, a second distance of the second edge using the second edge vector, and a third distance of the third edge using the third edge vector.
7 more elements
Dependencies are inferred from the claim text.