Approaches for object tracking
AssigneeAmazon Technologies, Inc.
InventorSharadh Ramaswamy
Life of this patent
Estimating the term…
Abstract
The location of a user's head, for purposes such as head tracking or motion input, can be determined using a two-step process. In a first step, at least one image is captured including a representation of at least a portion of the person, such as a head portion of the person. In a second step, a contour of the head portion can be determined, and a two-dimensional model, for example, an ellipse or other similar shape can be used to approximate the head portion of the person represented in the image. The ellipse, for example, can be modeled using a number of shapes, such as rectangles, and the portion of the person can be tracked by locating an ellipse that bounds a maximum intensity gradient of pixel values in each one of a series of images.
Claims21
A computing device, comprising:
- at least one processor;
- a camera;
- and
- memory including instructions that, when executed by the at least one processor, cause the computing device to:
- acquire a first image by the camera, the first image including a first representation of a head of a person;
- determine a contour of the first representation;
- determine a center point of the contour using at least one centroid calculation;
- determine a group of rectangles approximating the contour of the first representation, each rectangle of the group abutting at least one adjacent rectangle of the group;
- acquire a second image by the camera, the second image including a second representation of the head;
- determine a gradient image of the second image;
- compute a cost function to determine an area within a region of head tracking interest of the gradient image where an average intensity value of pixels confined within the group is a maximum relative to other positions in the first image;
- and
- determine a location of the center point based at least in part on the cost function.
A computer-implemented method, comprising:
- determining, in a first image, a first representation of an object;
- determining a contour of the first representation;
- determining geometric shapes approximating the contour, each geometric shape of the geometric shapes abutting at least one adjacent geometric shape of the geometric shapes;
- determining, in a gradient image of a second image, an area where an average intensity value of pixels confined within the geometric shapes is a maximum relative to other positions in the first image;
- and
- determining a location of a second representation of the object in the area.
A computing device, comprising:
- at least one processor;
- and
- memory including instructions that, when executed by the at least one processor, cause the computing device to:
- determine, in a first image, a first representation of an object;
- determine a contour of the first representation;
- determine geometric shapes approximating the contour, each geometric shape of the geometric shapes abutting at least one adjacent geometric shape of the geometric shapes;
- determine, in a gradient image of a second image, an area where an average intensity value of pixels confined within the geometric shapes is a maximum relative to other positions in the first image;
- and
- determine a location of a second representation of the object in the area.
Dependencies are inferred from the claim text.