Patents by Inventor Philip L. Davidson
Philip L. Davidson 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: 11037026Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.Type: GrantFiled: January 22, 2020Date of Patent: June 15, 2021Assignee: Google LLCInventors: Sean Ryan Fanello, Julien Pascal Christophe Valentin, Adarsh Prakash Murthy Kowdle, Christoph Rhemann, Vladimir Tankovich, Philip L. Davidson, Shahram Izadi
-
Patent number: 11030773Abstract: An electronic device estimates a pose of a hand by volumetrically deforming a signed distance field using a skinned tetrahedral mesh to locate a local minimum of an energy function, wherein the local minimum corresponds to the hand pose. The electronic device identifies a pose of the hand by fitting an implicit surface model of a hand to the pixels of a depth image that correspond to the hand. The electronic device uses a skinned tetrahedral mesh to warp space from a base pose to a deformed pose to define an articulated signed distance field from which the hand tracking module derives candidate poses of the hand. The electronic device then minimizes an energy function based on the distance of each corresponding pixel to identify the candidate pose that most closely approximates the pose of the hand.Type: GrantFiled: February 24, 2020Date of Patent: June 8, 2021Assignee: Google LLCInventors: Jonathan James Taylor, Vladimir Tankovich, Danhang Tang, Cem Keskin, Adarsh Prakash Murthy Kowdle, Philip L. Davidson, Shahram Izadi, David Kim
-
Patent number: 10937182Abstract: An electronic device estimates a pose of one or more subjects in an environment based on estimating a correspondence between a data volume containing a data mesh based on a current frame captured by a depth camera and a reference volume containing a plurality of fused prior data frames based on spectral embedding and performing bidirectional non-rigid matching between the reference volume and the current data frame to refine the correspondence so as to support location-based functionality. The electronic device predicts correspondences between the data volume and the reference volume based on spectral embedding. The correspondences provide constraints that accelerate the convergence between the data volume and the reference volume. By tracking changes between the current data mesh frame and the reference volume, the electronic device avoids tracking failures that can occur when relying solely on a previous data mesh frame.Type: GrantFiled: May 31, 2018Date of Patent: March 2, 2021Assignee: GOOGLE LLCInventors: Mingsong Dou, Sean Ryan Fanello, Adarsh Prakash Murthy Kowdle, Christoph Rhemann, Sameh Khamis, Philip L. Davidson, Shahram Izadi, Vladimir Tankovich
-
Patent number: 10839539Abstract: An electronic device estimates a depth map of an environment based on stereo depth images captured by depth cameras having exposure times that are offset from each other in conjunction with illuminators pulsing illumination patterns into the environment. A processor of the electronic device matches small sections of the depth images from the cameras to each other and to corresponding patches of immediately preceding depth images (e.g., a spatio-temporal image patch “cube”). The processor computes a matching cost for each spatio-temporal image patch cube by converting each spatio-temporal image patch into binary codes and defining a cost function between two stereo image patches as the difference between the binary codes. The processor minimizes the matching cost to generate a disparity map, and optimizes the disparity map by rejecting outliers using a decision tree with learned pixel offsets and refining subpixels to generate a depth map of the environment.Type: GrantFiled: May 31, 2018Date of Patent: November 17, 2020Assignee: GOOGLE LLCInventors: Adarsh Prakash Murthy Kowdle, Vladimir Tankovich, Danhang Tang, Cem Keskin, Jonathan James Taylor, Philip L. Davidson, Shahram Izadi, Sean Ryan Fanello, Julien Pascal Christophe Valentin, Christoph Rhemann, Mingsong Dou, Sameh Khamis, David Kim
-
Publication number: 20200193638Abstract: An electronic device estimates a pose of a hand by volumetrically deforming a signed distance field using a skinned tetrahedral mesh to locate a local minimum of an energy function, wherein the local minimum corresponds to the hand pose. The electronic device identifies a pose of the hand by fitting an implicit surface model of a hand to the pixels of a depth image that correspond to the hand. The electronic device uses a skinned tetrahedral mesh to warp space from a base pose to a deformed pose to define an articulated signed distance field from which the hand tracking module derives candidate poses of the hand. The electronic device then minimizes an energy function based on the distance of each corresponding pixel to identify the candidate pose that most closely approximates the pose of the hand.Type: ApplicationFiled: February 24, 2020Publication date: June 18, 2020Inventors: Jonathan James TAYLOR, Vladimir TANKOVICH, Danhang TANG, Cem KESKIN, Adarsh Prakash Murthy KOWDLE, Philip L. DAVIDSON, Shahram IZADI, David KIM
-
Publication number: 20200160109Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.Type: ApplicationFiled: January 22, 2020Publication date: May 21, 2020Inventors: Sean Ryan FANELLO, Julien Pascal Christophe VALENTIN, Adarsh Prakash Murthy KOWDLE, Christoph RHEMANN, Vladimir TANKOVICH, Philip L. DAVIDSON, Shahram IZADI
-
Patent number: 10614591Abstract: An electronic device estimates a pose of a hand by volumetrically deforming a signed distance field using a skinned tetrahedral mesh to locate a local minimum of an energy function, wherein the local minimum corresponds to the hand pose. The electronic device identifies a pose of the hand by fitting an implicit surface model of a hand to the pixels of a depth image that correspond to the hand. The electronic device uses a skinned tetrahedral mesh to warp space from a base pose to a deformed pose to define an articulated signed distance field from which the hand tracking module derives candidate poses of the hand. The electronic device then minimizes an energy function based on the distance of each corresponding pixel to identify the candidate pose that most closely approximates the pose of the hand.Type: GrantFiled: May 31, 2018Date of Patent: April 7, 2020Assignee: GOOGLE LLCInventors: Jonathan James Taylor, Vladimir Tankovich, Danhang Tang, Cem Keskin, Adarsh Prakash Murthy Kowdle, Philip L. Davidson, Shahram Izadi, David Kim
-
Patent number: 10579905Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.Type: GrantFiled: March 19, 2018Date of Patent: March 3, 2020Assignee: GOOGLE LLCInventors: Sean Ryan Fanello, Julien Pascal Christophe Valentin, Adarsh Prakash Murthy Kowdle, Christoph Rhemann, Vladimir Tankovich, Philip L. Davidson, Shahram Izadi
-
Patent number: 10554957Abstract: A first and second image of a scene are captured. Each of a plurality of pixels in the first image is associated with a disparity value. An image patch associated with each of the plurality of pixels of the first image and the second image is mapped into a binary vector. Thus, values of pixels in an image are mapped to a binary space using a function that preserves characteristics of values of the pixels. The difference between the binary vector associated with each of the plurality of pixels of the first image and its corresponding binary vector in the second image designated by the disparity value associated with each of the plurality of pixels of the first image is determined. Based on the determined difference between binary vectors, correspondence between the plurality of pixels of the first image and the second image is established.Type: GrantFiled: June 4, 2018Date of Patent: February 4, 2020Assignee: GOOGLE LLCInventors: Julien Pascal Christophe Valentin, Sean Ryan Fanello, Adarsh Prakash Murthy Kowdle, Christoph Rhemann, Vladimir Tankovich, Philip L. Davidson, Shahram Izadi
-
Publication number: 20180350105Abstract: An electronic device estimates a pose of a hand by volumetrically deforming a signed distance field using a skinned tetrahedral mesh to locate a local minimum of an energy function, wherein the local minimum corresponds to the hand pose. The electronic device identifies a pose of the hand by fitting an implicit surface model of a hand to the pixels of a depth image that correspond to the hand. The electronic device uses a skinned tetrahedral mesh to warp space from a base pose to a deformed pose to define an articulated signed distance field from which the hand tracking module derives candidate poses of the hand. The electronic device then minimizes an energy function based on the distance of each corresponding pixel to identify the candidate pose that most closely approximates the pose of the hand.Type: ApplicationFiled: May 31, 2018Publication date: December 6, 2018Inventors: Jonathan James TAYLOR, Vladimir TANKOVICH, Danhang TANG, Cem KESKIN, Adarsh Prakash Murthy KOWDLE, Philip L. DAVIDSON, Shahram IZADI, David KIM
-
Publication number: 20180352213Abstract: A first and second image of a scene are captured. Each of a plurality of pixels in the first image is associated with a disparity value. An image patch associated with each of the plurality of pixels of the first image and the second image is mapped into a binary vector. Thus, values of pixels in an image are mapped to a binary space using a function that preserves characteristics of values of the pixels. The difference between the binary vector associated with each of the plurality of pixels of the first image and its corresponding binary vector in the second image designated by the disparity value associated with each of the plurality of pixels of the first image is determined. Based on the determined difference between binary vectors, correspondence between the plurality of pixels of the first image and the second image is established.Type: ApplicationFiled: June 4, 2018Publication date: December 6, 2018Inventors: Julien Pascal Christophe Valentin, Sean Ryan Fanello, Adarsh Prakash Murthy Kowdle, Christoph Rhemann, Vladimir Tankovich, Philip L. Davidson, Shahram Izadi
-
Publication number: 20180350088Abstract: An electronic device estimates a pose of one or more subjects in an environment based on estimating a correspondence between a data volume containing a data mesh based on a current frame captured by a depth camera and a reference volume containing a plurality of fused prior data frames based on spectral embedding and performing bidirectional non-rigid matching between the reference volume and the current data frame to refine the correspondence so as to support location-based functionality. The electronic device predicts correspondences between the data volume and the reference volume based on spectral embedding. The correspondences provide constraints that accelerate the convergence between the data volume and the reference volume. By tracking changes between the current data mesh frame and the reference volume, the electronic device avoids tracking failures that can occur when relying solely on a previous data mesh frame.Type: ApplicationFiled: May 31, 2018Publication date: December 6, 2018Inventors: Mingsong DOU, Sean Ryan FANELLO, Adarsh Prakash Murthy KOWDLE, Christoph RHEMANN, Sameh KHAMIS, Philip L. DAVIDSON, Shahram IZADI, Vladimir Tankovich
-
Publication number: 20180350087Abstract: An electronic device estimates a depth map of an environment based on stereo depth images captured by depth cameras having exposure times that are offset from each other in conjunction with illuminators pulsing illumination patterns into the environment. A processor of the electronic device matches small sections of the depth images from the cameras to each other and to corresponding patches of immediately preceding depth images (e.g., a spatio-temporal image patch “cube”). The processor computes a matching cost for each spatio-temporal image patch cube by converting each spatio-temporal image patch into binary codes and defining a cost function between two stereo image patches as the difference between the binary codes. The processor minimizes the matching cost to generate a disparity map, and optimizes the disparity map by rejecting outliers using a decision tree with learned pixel offsets and refining subpixels to generate a depth map of the environment.Type: ApplicationFiled: May 31, 2018Publication date: December 6, 2018Inventors: Adarsh Prakash Murthy KOWDLE, Vladimir TANKOVICH, Danhang TANG, Cem KESKIN, Jonathan James Taylor, Philip L. DAVIDSON, Shahram IZADI, Sean Ryan FANELLO, Julien Pascal Christophe VALENTIN, Christoph RHEMANN, Mingsong DOU, Sameh KHAMIS, David KIM
-
Publication number: 20180300588Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.Type: ApplicationFiled: March 19, 2018Publication date: October 18, 2018Inventors: Sean Ryan FANELLO, Julien Pascal Christophe VALENTIN, Adarsh Prakash Murthy KOWDLE, Christoph RHEMANN, Vladimir TANKOVICH, Philip L. DAVIDSON, Shahram IZADI
-
Patent number: 10031608Abstract: A process for enabling objects displayed on a multi-input display device to be grouped together is disclosed that includes defining a target element that enables objects displayed on a multi-input display device to be grouped together through interaction with the target element. Operations are invoked that establish a relationship between a particular displayed object and a position on the target element and that causes transformations applied to the target element also to be applied to the particular displayed object while maintaining the relationship between the particular displayed object and the position on the target element.Type: GrantFiled: February 24, 2012Date of Patent: July 24, 2018Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventor: Philip L. Davidson
-
Publication number: 20170235478Abstract: Dynamic registration of event handlers in a computer application or operating system recognizes multiple synchronous input streams by identifying each new stroke in a frame representing a single moment in time and mapping in a registration process each identified new stroke to a listening process that is associated with the user interface element to which the new input stream is to he applied. In the same frame, released strokes are unmapped and then each active listening process is called to carry out a respective control operation. When called, the strokes have the correct data for the given frame. The process is repeated for subsequent frames. By carrying out various processes in a sequence of frames, the concept of concurrency is preserved, which is particularly beneficial to multi-touch and multi-user systems.Type: ApplicationFiled: March 2, 2017Publication date: August 17, 2017Applicant: Perceptive Pixel Inc.Inventor: Philip L. Davidson
-
Patent number: 9671890Abstract: A process for enabling objects displayed on a multi-input display device to be grouped together is disclosed that includes defining a target element that enables objects displayed on a multi-input display device to be grouped together through interaction with the target element. Operations are invoked that establish a relationship between a particular displayed object and a position on the target element and that causes transformations applied to the target element also to be applied to the particular displayed object while maintaining the relationship between the particular displayed object and the position on the target element.Type: GrantFiled: February 24, 2012Date of Patent: June 6, 2017Assignee: PERCEPTIVE PIXEL, INC.Inventor: Philip L. Davidson
-
Publication number: 20170115872Abstract: Dynamic registration of event handlers in a computer application or operating system recognizes multiple synchronous input streams by identifying each new stroke in a frame representing a single moment in time and mapping in a registration process each identified new stroke to a listening process that is associated with the user interface element to which the new input stream is to be applied. In the same frame, released strokes are unmapped and then each active listening process is called to carry out a respective control operation. When called, the strokes have the correct data for the given frame. The process is repeated for subsequent frames. By carrying out various processes in a sequence of frames, the concept of concurrency is preserved, which is particularly beneficial to multi-touch and multi-user systems.Type: ApplicationFiled: January 4, 2017Publication date: April 27, 2017Applicant: Perceptive Pixel Inc.Inventor: Philip L. Davidson
-
Patent number: 9632605Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for input classification for multi-touch systems. In one aspect, a method includes maintaining a history of prior state information related to a touch sensitive display. The method further includes detecting that a previous contact with the touch sensitive display was incorrectly classified. The method further includes updating a classification of the previous contact based on the detection that the previous contact was incorrectly classified. The method further includes rewinding a state of the touch sensitive display to reflect a state that would have resulted had the previous contact been correctly classified based on the history of prior state information and the updated classification of the previous contact.Type: GrantFiled: October 17, 2012Date of Patent: April 25, 2017Assignee: PERCEPTIVE PIXEL, INC.Inventors: Philip L. Davidson, Jefferson Y. Han
-
Patent number: 9626034Abstract: A process for enabling objects displayed on a multi-input display device to be grouped together is disclosed that includes defining a target element that enables objects displayed on a multi-input display device to be grouped together through interaction with the target element. Operations are invoked that establish a relationship between a particular displayed object and a position on the target element and that causes transformations applied to the target element also to be applied to the particular displayed object while maintaining the relationship between the particular displayed object and the position on the target element.Type: GrantFiled: July 29, 2013Date of Patent: April 18, 2017Assignee: PERCEPTIVE PIXEL, INC.Inventor: Philip L. Davidson