Patents by Inventor Eran Guendelman
Eran Guendelman has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 9460339Abstract: A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.Type: GrantFiled: June 15, 2014Date of Patent: October 4, 2016Assignee: APPLE INC.Inventors: Shai Litvak, Tomer Yanir, Eran Guendelman
-
Patent number: 9196045Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: GrantFiled: July 27, 2014Date of Patent: November 24, 2015Assignee: APPLE INC.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Publication number: 20140333626Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: ApplicationFiled: July 27, 2014Publication date: November 13, 2014Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Publication number: 20140294237Abstract: A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.Type: ApplicationFiled: June 15, 2014Publication date: October 2, 2014Inventors: Shai Litvak, Tomer Yanir, Eran Guendelman
-
Patent number: 8824737Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: GrantFiled: April 21, 2013Date of Patent: September 2, 2014Assignee: Primesense Ltd.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Patent number: 8787663Abstract: A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.Type: GrantFiled: February 28, 2011Date of Patent: July 22, 2014Assignee: Primesense Ltd.Inventors: Shai Litvak, Tomer Yanir, Eran Guendelman
-
Patent number: 8781217Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: GrantFiled: April 21, 2013Date of Patent: July 15, 2014Assignee: Primesense Ltd.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Patent number: 8594425Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: GrantFiled: August 11, 2010Date of Patent: November 26, 2013Assignee: Primesense Ltd.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Publication number: 20130283213Abstract: A method, including receiving, by a computer, a two-dimensional image (2D) containing at least a physical surface and segmenting the physical surface into one or more physical regions. A functionality is assigned to each of the one or more physical regions, each of the functionalities corresponding to a tactile input device, and a sequence of three-dimensional (3D) maps is received, the sequence of 3D maps containing at least a hand of a user of the computer, the hand positioned on one of the physical regions. The 3D maps are analyzed to detect a gesture performed by the user, and based on the gesture, an input is simulated for the tactile input device corresponding to the one of the physical regions.Type: ApplicationFiled: March 24, 2013Publication date: October 24, 2013Inventors: Eran Guendelman, Ofir Or, Eyal Bychkov, Oren Brezner, Adi Berenson
-
Publication number: 20130230234Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: ApplicationFiled: April 21, 2013Publication date: September 5, 2013Applicant: PRIMESENSE LTD.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Publication number: 20130230215Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: ApplicationFiled: April 21, 2013Publication date: September 5, 2013Applicant: PRIMESENSE LTD.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Publication number: 20120204133Abstract: A user interface method, including capturing, by a computer, a sequence of images over time of at least a part of a body of a human subject, and processing the images in order to detect a gesture, selected from a group of gestures consisting of a grab gesture, a push gesture, a pull gesture, and a circular hand motion. A software application is controlled responsively to the detected gesture.Type: ApplicationFiled: March 19, 2012Publication date: August 9, 2012Applicant: PRIMESENSE LTD.Inventors: Eran Guendelman, Aviad Maizels, Tamir Berliner, Jonathan Pokrass
-
Patent number: 8166421Abstract: A user interface method includes defining an interaction surface containing an interaction region in space. A sequence of depth maps is captured over time of at least a part of a body of a human subject. The depth maps are processed in order to detect a direction and speed of movement of the part of the body as the part of the body passes through the interaction surface. A computer application is controlled responsively to the detected direction and speed.Type: GrantFiled: January 13, 2009Date of Patent: April 24, 2012Assignee: Primesense Ltd.Inventors: Oz Magal, Eran Guendelman, Sergio Golman, Ziv Hendel, Aviad Maizels, Tamir Berliner, Jonathan Pokras
-
Publication number: 20110292036Abstract: A method for processing data includes receiving a depth map of a scene containing a body of a humanoid subject. The depth map includes a matrix of pixels, each pixel corresponding to a respective location in the scene and having a respective pixel depth value indicative of a distance from a reference plane to the respective location. The depth map is processed in a digital processor to extract a skeleton of at least a part of the body, the skeleton including multiple joints having respective coordinates. An application program interface (API) indicates at least the coordinates of the joints.Type: ApplicationFiled: May 2, 2011Publication date: December 1, 2011Applicant: PRIMESENSE LTD.Inventors: Erez Sali, Tomer Yanir, Eran Guendelman, Amiad Gurman
-
Publication number: 20110293137Abstract: A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.Type: ApplicationFiled: August 11, 2010Publication date: December 1, 2011Applicant: PRIMESENSE LTD.Inventors: Amiad Gurman, Tomer Yanir, Michael Brand, Eran Guendelman
-
Publication number: 20110211754Abstract: A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.Type: ApplicationFiled: February 28, 2011Publication date: September 1, 2011Applicant: PRIMESENSE LTD.Inventors: Shai Litvak, Tomer Yanir, Eran Guendelman
-
Publication number: 20090183125Abstract: A user interface method includes defining an interaction surface containing an interaction region in space. A sequence of depth maps is captured over time of at least a part of a body of a human subject. The depth maps are processed in order to detect a direction and speed of movement of the part of the body as the part of the body passes through the interaction surface. A computer application is controlled responsively to the detected direction and speed.Type: ApplicationFiled: January 13, 2009Publication date: July 16, 2009Applicant: PRIME SENSE LTD.Inventors: Oz Magal, Eran Guendelman, Sergio Golman, Ziv Hendel, Aviad Maizels, Tamir Berliner, Jonathan Pokras