Patents by Inventor Zsolt Mathe
Zsolt Mathe 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: 8855415Abstract: A method of compressing a digital image defined by a plurality of pixel values in each of one or more channels includes adjusting each pixel value in each of the one or more channels by an average pixel value for that channel. The method further includes splitting each adjusted channel into one or more image blocks, and converting each image block into a frequency block that is a frequency-domain representation of that image block.Type: GrantFiled: May 2, 2013Date of Patent: October 7, 2014Assignee: Microsoft CorporationInventor: Zsolt Mathe
-
Patent number: 8660310Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device and a model of a user in the depth image may be generated. The background of a received depth image may be removed to isolate a human target in the received depth image. A model may then be adjusted to fit within the isolated human target in the received depth image. To adjust the model, a joint or a bone may be magnetized to the closest pixel of the isolated human target. The joint or the bone may then be refined such that the joint or the bone may be further adjusted to a pixel equidistant between two edges the body part of the isolated human target where the joint or bone may have been magnetized.Type: GrantFiled: December 13, 2012Date of Patent: February 25, 2014Assignee: Microsoft CorporationInventor: Zsolt Mathe
-
Publication number: 20140043438Abstract: A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.Type: ApplicationFiled: August 5, 2013Publication date: February 13, 2014Applicant: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais
-
Publication number: 20130243316Abstract: A method of compressing a digital image defined by a plurality of pixel values in each of one or more channels includes adjusting each pixel value in each of the one or more channels by an average pixel value for that channel. The method further includes splitting each adjusted channel into one or more image blocks, and converting each image block into a frequency block that is a frequency-domain representation of that image block.Type: ApplicationFiled: May 2, 2013Publication date: September 19, 2013Applicant: Microsoft CorporationInventor: Zsolt Mathe
-
Patent number: 8503766Abstract: A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.Type: GrantFiled: December 13, 2012Date of Patent: August 6, 2013Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais
-
Patent number: 8467574Abstract: A depth image of a scene may be received, observed, or captured by a device. The depth image may then be analyzed to determine whether the depth image includes a human target. For example, the depth image may include one or more targets including a human target and non-human targets. Each of the targets may be flood filled and compared to a pattern to determine whether the target may be a human target. If one or more of the targets in the depth image includes a human target, the human target may be scanned. A skeletal model of the human target may then be generated based on the scan.Type: GrantFiled: October 28, 2010Date of Patent: June 18, 2013Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais, Ryan Michael Geiss
-
Patent number: 8457396Abstract: A method of compressing a digital image defined by a plurality of pixel values in each of one or more channels includes adjusting each pixel value in each of the one or more channels by an average pixel value for that channel. The method further includes splitting each adjusted channel into one or more image blocks, and converting each image block into a frequency block that is a frequency-domain representation of that image block.Type: GrantFiled: August 11, 2009Date of Patent: June 4, 2013Assignee: Microsoft CorporationInventor: Zsolt Mathe
-
Publication number: 20130077820Abstract: A virtual skeleton includes a plurality of joints and provides a machine readable representation of a human subject observed with a sensor such as a depth camera. A gesture detection module is trained via machine learning to identify one or more features of a virtual skeleton and indicate if the feature(s) collectively indicate a particular gesture.Type: ApplicationFiled: September 26, 2011Publication date: March 28, 2013Applicant: MICROSOFT CORPORATIONInventors: Charles Claudius Marais, Zsolt Mathe, Mark Seminatore, Ivan Nevraev
-
Patent number: 8379101Abstract: A depth image of a scene may be observed or captured by a capture device. The depth image may include a human target and an environment. One or more pixels of the depth image may be analyzed to determine whether the pixels in the depth image are associated with the environment of the depth image. The one or more pixels associated with the environment may then be discarded to isolate the human target and the depth image with the isolated human target may be processed.Type: GrantFiled: May 29, 2009Date of Patent: February 19, 2013Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais
-
Patent number: 8351652Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device and a model of a user in the depth image may be generated. The background of a received depth image may be removed to isolate a human target in the received depth image. A model may then be adjusted to fit within the isolated human target in the received depth image. To adjust the model, a joint or a bone may be magnetized to the closest pixel of the isolated human target. The joint or the bone may then be refined such that the joint or the bone may be further adjusted to a pixel equidistant between two edges the body part of the isolated human target where the joint or bone may have been magnetized.Type: GrantFiled: February 2, 2012Date of Patent: January 8, 2013Assignee: Microsoft CorporationInventor: Zsolt Mathe
-
Patent number: 8340432Abstract: A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.Type: GrantFiled: June 16, 2009Date of Patent: December 25, 2012Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais
-
Patent number: 8320619Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device and a model of a user in the depth image may be generated. The background of a received depth image may be removed to isolate a human target in the received depth image. A model may then be adjusted to fit with in the isolated human target in the received depth image. To adjust the model, a joint or a bone may be magnetized to the closest pixel of the isolated human target. The joint or the bone may then be refined such that the joint or the bone may be further adjusted to a pixels equidistant between two edges the body part of the isolated human target where the joint or bone may have been magnetized.Type: GrantFiled: June 15, 2009Date of Patent: November 27, 2012Assignee: Microsoft CorporationInventor: Zsolt Mathe
-
Publication number: 20120287038Abstract: A depth image of a scene may be received, observed, or captured by a device. The depth image may then be analyzed to determine whether the depth image includes a human target. For example, the depth image may include one or more targets including a human target and non-human targets. Each of the targets may be flood filled and compared to a pattern to determine whether the target may be a human target. If one or more of the targets in the depth image includes a human target, the human target may be scanned. A skeletal model of the human target may then be generated based on the scan.Type: ApplicationFiled: July 18, 2012Publication date: November 15, 2012Applicant: MICROSOFT CORPORATIONInventors: Zsolt Mathe, Charles Claudius Marais, Ryan Michael Geiss
-
Patent number: 8294767Abstract: A depth image of a scene may be received, observed, or captured by a device. The depth image may then be analyzed to determine whether the depth image includes a human target. For example, the depth image may include one or more targets including a human target and non-human targets. Each of the targets may be flood filled and compared to a pattern to determine whether the target may be a human target. If one or more of the targets in the depth image includes a human target, the human target may be scanned. A skeletal model of the human target may then be generated based on the scan.Type: GrantFiled: January 30, 2009Date of Patent: October 23, 2012Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais, Ryan Michael Geiss
-
Patent number: 8290249Abstract: A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.Type: GrantFiled: March 6, 2012Date of Patent: October 16, 2012Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais
-
Publication number: 20120163669Abstract: A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.Type: ApplicationFiled: March 6, 2012Publication date: June 28, 2012Applicant: MICROSOFT CORPORATIONInventors: Zsolt Mathe, Charles Claudius Marais
-
Publication number: 20120134575Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device and a model of a user in the depth image may be generated. The background of a received depth image may be removed to isolate a human target in the received depth image. A model may then be adjusted to fit with in the isolated human target in the received depth image. To adjust the model, a joint or a bone may be magnetized to the closest pixel of the isolated human target. The joint or the bone may then be refined such that the joint or the bone may be further adjusted to a pixels equidistant between two edges the body part of the isolated human target where the joint or bone may have been magnetized.Type: ApplicationFiled: February 2, 2012Publication date: May 31, 2012Applicant: MICROSOFT CORPORATIONInventor: Zsolt Mathe
-
Publication number: 20120105585Abstract: A system and method are disclosed for calibrating a depth camera in a natural user interface. The system in general obtains an objective measurement of true distance between a capture device and one or more objects in a scene. The system then compares the true depth measurement to the depth measurement provided by the depth camera at one or more points and determines an error function describing an error in the depth camera measurement. The depth camera may then be recalibrated to correct for the error. The objective measurement of distance to one or more objects in a scene may be accomplished by a variety of systems and methods.Type: ApplicationFiled: November 3, 2010Publication date: May 3, 2012Applicant: MICROSOFT CORPORATIONInventors: Prafulla J. Masalkar, Szymon P. Stachniak, Tommer Leyvand, Zhengyou Zhang, Leonardo Del Castillo, Zsolt Mathe
-
Patent number: 8013862Abstract: Techniques for pre-processing image blocks containing texture are disclosed herein which reduce memory requirements without degradation of quality. This is accomplished by determining the level of texture in each pixel block of the image and then performing a compression algorithm on such pixel block. Various methods are available to determine the texture level, including identifying the luminescence variation or difference within the pixel block. Depending on the amount of texture level contained within each pixel block, pre-processing may involve assigning the pixel block a single color or replacing the pixel block with an interpolated pixel block. Pre-processing on the pixel block may not be performed when the texture level therein is determined to be at a predetermined amount or level. Additional techniques are also disclosed herein which involve full processing of an image block.Type: GrantFiled: November 16, 2007Date of Patent: September 6, 2011Assignee: Microsoft CorporationInventor: Zsolt Mathe
-
Patent number: 8009867Abstract: A depth image of a scene may be received, observed, or captured by a device. The depth image may then be analyzed to determine whether the depth image includes a human target. For example, the depth image may include one or more targets including a human target and non-human targets. Each of the targets may be flood filled and compared to a pattern to determine whether the target may be a human target. If one or more of the targets in the depth image includes a human target, the human target may be scanned. A skeletal model of the human target may then be generated based on the scan.Type: GrantFiled: January 28, 2011Date of Patent: August 30, 2011Assignee: Microsoft CorporationInventors: Zsolt Mathe, Charles Claudius Marais, Ryan Michael Geiss