Computer vision gesture based control of a device
AssigneePointgrab Ltd.
InventorsHaim Perski, Amir Kaplan, Eran Eilat
Life of this patent
Estimating the term…
Abstract
A system and method are provided for controlling a device based on computer vision. Embodiments of the system and method of the invention are based on receiving a sequence of images of a field of view; detecting movement of at least one object in the images; applying a shape recognition algorithm on the at least one moving object; confirming that the object is a user hand by combining information from at least two images of the object; and tracking the object to control the device.
Claims19
A method for computer vision based hand gesture device control, the method comprising
- receiving a sequence of images of a field of view, said images comprising at least one object;
- detecting movement of the at least one object in the images, to define at least one moving object;
- applying a shape recognition algorithm on the at least one moving object in each of at least two of the sequence of images, to obtain shape information;
- performing a first stage determination that the at least one moving object is a user hand by determining that the movement of the at least one object is a movement in a predefined pattern;
- performing a second stage determination that the at least one moving object is a user hand by combining the shape information from each of the at least two of the sequence of images to obtain a combined shape information, and determining that the combined shape information corresponds to a hand shape;
- and
- subject to successful first and second stage determination, tracking the user hand to control the device.
A system for user-device interaction, the system comprising:
- an electronic device, an image sensor and a processor, the processor to:
- receive a sequence of images of a field of view;
- detect a movement of at least one moving object in the images, to define at least one moving object;
- apply a shape recognition algorithm on the at least one moving object in each of at least two of the sequence of images, to obtain shape information;
- perform a first stage determination that the at least one moving object is a user hand by determining that the movement of the at least one object is a movement in a predefined pattern;
- perform a confirmatory second stage determination that the at least one moving object is a user hand by combining the shape information from each of the at least two of the sequence of images to obtain a combined shape information dataset, and comparing the shape information dataset against a reference hand shape information dataset;
- and
- subject to successful first and second stage determination, track the object to control the device.
Dependencies are inferred from the claim text.