Patents by Inventor Amit Kumar KC
Amit Kumar KC 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: 11972607Abstract: In one implementation, a method of generating a plane hypothesis is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method includes obtaining a plurality of points of a point cloud based on the image of the scene. The method includes obtaining an object classification set based on the image of the scene. Each element of the object classification set includes a plurality of pixels respectively associated with a corresponding object in the scene. The method includes detecting a plane within the scene by identifying a subset of the plurality of points of the point cloud that correspond to a particular element of the object classification set.Type: GrantFiled: February 18, 2023Date of Patent: April 30, 2024Assignee: APPLE INC.Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar Kc
-
Publication number: 20230206623Abstract: In one implementation, a method of generating a plane hypothesis is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method includes obtaining a plurality of points of a point cloud based on the image of the scene. The method includes obtaining an object classification set based on the image of the scene. Each element of the object classification set includes a plurality of pixels respectively associated with a corresponding object in the scene. The method includes detecting a plane within the scene by identifying a subset of the plurality of points of the point cloud that correspond to a particular element of the object classification set.Type: ApplicationFiled: February 18, 2023Publication date: June 29, 2023Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC
-
Patent number: 11610397Abstract: In one implementation, a method of generating a plane hypothesis is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method includes obtaining a plurality of points of a point cloud based on the image of the scene. The method includes obtaining an object classification set based on the image of the scene. Each element of the object classification set includes a plurality of pixels respectively associated with a corresponding object in the scene. The method includes detecting a plane within the scene by identifying a subset of the plurality of points of the point cloud that correspond to a particular element of the object classification set.Type: GrantFiled: September 13, 2021Date of Patent: March 21, 2023Assignee: APPLE INC.Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC
-
Publication number: 20210406541Abstract: In one implementation, a method of generating a plane hypothesis is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method includes obtaining a plurality of points of a point cloud based on the image of the scene. The method includes obtaining an object classification set based on the image of the scene. Each element of the object classification set includes a plurality of pixels respectively associated with a corresponding object in the scene. The method includes detecting a plane within the scene by identifying a subset of the plurality of points of the point cloud that correspond to a particular element of the object classification set.Type: ApplicationFiled: September 13, 2021Publication date: December 30, 2021Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC
-
Patent number: 11132546Abstract: In one implementation, a method of generating a plane hypothesis is performed by a head-mounted device (HMD) including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method include obtaining a point cloud based on the image of the scene and generating an object classification set based on the image of the scene, each element of the object classification set including a respective plurality of pixels classified as a respective object in the scene. The method includes generating a plane hypothesis based on the point cloud and the object classification set.Type: GrantFiled: September 25, 2020Date of Patent: September 28, 2021Assignee: APPLE INC.Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC
-
Patent number: 10977798Abstract: In some implementations a neural network is trained to perform to directly predict thin boundaries of objects in images based on image characteristics. A neural network can be trained to predict thin boundaries of objects without requiring subsequent computations to reduce the thickness of the boundary prediction. Instead, the network is trained to make the predicted boundaries thin by effectively suppressing non-maximum values in normal directions along what might otherwise be a thick predicted boundary. To do so, the neural network can be trained to determine normal directions and suppress non-maximum values based on those determined normal directions.Type: GrantFiled: August 20, 2019Date of Patent: April 13, 2021Assignee: Apple Inc.Inventors: Amit Kumar Kc, Daniel Ulbricht
-
Publication number: 20210012112Abstract: In one implementation, a method of generating a plane hypothesis is performed by a head-mounted device (HMD) including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method include obtaining a point cloud based on the image of the scene and generating an object classification set based on the image of the scene, each element of the object classification set including a respective plurality of pixels classified as a respective object in the scene. The method includes generating a plane hypothesis based on the point cloud and the object classification set.Type: ApplicationFiled: September 25, 2020Publication date: January 14, 2021Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC
-
Patent number: 10824864Abstract: In one implementation, a method of generating a plane hypothesis is performed by a head-mounted device (HMD) including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method include obtaining a point cloud based on the image of the scene and generating an object classification set based on the image of the scene, each element of the object classification set including a respective plurality of pixels classified as a respective object in the scene. The method includes generating a plane hypothesis based on the point cloud and the object classification set.Type: GrantFiled: March 21, 2019Date of Patent: November 3, 2020Assignee: APPLE INC.Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC
-
Publication number: 20200065973Abstract: In some implementations a neural network is trained to perform to directly predict thin boundaries of objects in images based on image characteristics. A neural network can be trained to predict thin boundaries of objects without requiring subsequent computations to reduce the thickness of the boundary prediction. Instead, the network is trained to make the predicted boundaries thin by effectively suppressing non-maximum values in normal directions along what might otherwise be a thick predicted boundary. To do so, the neural network can be trained to determine normal directions and suppress non-maximum values based on those determined normal directions.Type: ApplicationFiled: August 20, 2019Publication date: February 27, 2020Inventors: Amit Kumar KC, Daniel Ulbricht
-
Publication number: 20190392213Abstract: In one implementation, a method of generating a plane hypothesis is performed by a head-mounted device (HMD) including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method include obtaining a point cloud based on the image of the scene and generating an object classification set based on the image of the scene, each element of the object classification set including a respective plurality of pixels classified as a respective object in the scene. The method includes generating a plane hypothesis based on the point cloud and the object classification set.Type: ApplicationFiled: March 21, 2019Publication date: December 26, 2019Inventors: Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Tanmay Batra, Eshan Verma, Amit Kumar KC