Patents by Inventor Andrei Vakunov
Andrei Vakunov 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).
-
Publication number: 20230410329Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.Type: ApplicationFiled: September 1, 2023Publication date: December 21, 2023Inventors: Valentin Bazarevsky, Fan Zhang, Andrei Tkachenka, Andrei Vakunov, Matthias Grundmann
-
Patent number: 11783496Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.Type: GrantFiled: November 16, 2021Date of Patent: October 10, 2023Assignee: GOOGLE LLCInventors: Valentin Bazarevsky, Fan Zhang, Andrei Vakunov, Andrei Tkachenka, Matthias Grundmann
-
Patent number: 11694087Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.Type: GrantFiled: September 19, 2022Date of Patent: July 4, 2023Assignee: GOOGLE LLCInventors: Valentin Bazarevsky, Yury Kartynnik, Andrei Vakunov, Karthik Raveendran, Matthias Grundmann
-
Publication number: 20230017459Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.Type: ApplicationFiled: September 19, 2022Publication date: January 19, 2023Inventors: Valentin Bazarevsky, Yury Kartynnik, Andrei Vakunov, Karthik Raveendran, Matthias Grundmann
-
Patent number: 11449714Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.Type: GrantFiled: October 30, 2019Date of Patent: September 20, 2022Assignee: GOOGLE LLCInventors: Valentin Bazarevsky, Yury Kartynnik, Andrei Vakunov, Karthik Raveendran, Matthias Grundmann
-
Publication number: 20220076433Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.Type: ApplicationFiled: November 16, 2021Publication date: March 10, 2022Inventors: Valentin Bazarevsky, Fan Zhang, Andrei Vakunov, Andrei Tkachenka, Matthias Grundmann
-
Patent number: 11182909Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.Type: GrantFiled: December 10, 2019Date of Patent: November 23, 2021Assignee: Google LLCInventors: Valentin Bazarevsky, Fan Zhang, Andrei Vakunov, Andrei Tkachenka, Matthias Grundmann
-
Publication number: 20210174519Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.Type: ApplicationFiled: December 10, 2019Publication date: June 10, 2021Inventors: Valentin Bazarevsky, Fan Zhang, Andrei Vakunov, Andrei Tkachenka, Matthias Grundmann
-
Publication number: 20210133508Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.Type: ApplicationFiled: October 30, 2019Publication date: May 6, 2021Inventors: Valentin Bazarevsky, Yury Kartynnik, Andrei Vakunov, Karthik Raveendran, Matthias Grundmann