Patents by Inventor Carlo Dal Mutto

Carlo Dal Mutto 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: 11379688
    Abstract: A keypoint detection system includes: a camera system including at least one camera; and a processor and memory, the processor and memory being configured to: receive an image captured by the camera system; compute a plurality of keypoints in the image using a convolutional neural network including: a first layer implementing a first convolutional kernel; a second layer implementing a second convolutional kernel; an output layer; and a plurality of connections between the first layer and the second layer and between the second layer and the output layer, each of the connections having a corresponding weight stored in the memory; and output the plurality of keypoints of the image computed by the convolutional neural network.
    Type: Grant
    Filed: March 16, 2018
    Date of Patent: July 5, 2022
    Assignee: PACKSIZE LLC
    Inventors: Paolo Di Febbo, Carlo Dal Mutto, Kinh Tieu
  • Publication number: 20210243369
    Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.
    Type: Application
    Filed: September 11, 2020
    Publication date: August 5, 2021
    Inventors: Carlo Dal Mutto, Giulio Marin
  • Publication number: 20200380229
    Abstract: A method for automatically recognizing content of labels on objects includes: capturing visual information of an object using a scanning system including one or more cameras, the object having one or more labels on one or more exterior surfaces; detecting, by a computing system, one or more surfaces of the object having labels; rectifying, by the computing system, the visual information of the one or more surfaces of the object to compute one or more rectified images; and decoding, by the computing system, content of a label depicted in at least one of the one or more rectified images.
    Type: Application
    Filed: December 30, 2019
    Publication date: December 3, 2020
    Inventors: Francesco Peruch, Carlo Dal Mutto, Jason Trachewsky
  • Publication number: 20200372625
    Abstract: A method for performing automatic visual inspection includes: capturing visual information of an object using a scanning system including a plurality of cameras; extracting, by a computing system including a processor and memory, one or more feature maps from the visual information using one or more feature extractors; classifying, by the computing system, the object by supplying the one or more feature maps to a complex classifier to compute a classification of the object, the complex classifier including: a plurality of simple classifiers, each simple classifier of the plurality of simple classifiers being configured to compute outputs representing a characteristic of the object; and one or more logical operators configured to combine the outputs of the simple classifiers to compute the classification of the object; and outputting, by the computing system, the classification of the object as a result of the automatic visual inspection.
    Type: Application
    Filed: December 19, 2019
    Publication date: November 26, 2020
    Inventors: Carlo Dal Mutto, Francesco Peruch, Alexander Ou, Robert Hayes
  • Publication number: 20200372626
    Abstract: A method for estimating tightly enclosing bounding boxes by a computing system includes: controlling a scanning system including one or more depth cameras to capture visual information of the scene including one or more objects; detecting the one or more objects of the scene based on the visual information; singulating each the one or more objects from the frame of the scene to generate one or more 3D models corresponding to the one or more objects, the one or more 3D models including a partial 3D model of a corresponding one of the one or more objects; extrapolating a more complete 3D model of the corresponding one of the one or more objects based on the partial 3D model; and estimating a tightly enclosing bounding box of the corresponding one of the one or more objects based on the more complete 3D model.
    Type: Application
    Filed: December 20, 2019
    Publication date: November 26, 2020
    Inventors: Carlo Dal Mutto, Kinh Tieu, Francesco Peruch, Jason Trachewsky, Tony Zuccarino, Chase Garber
  • Patent number: 10805535
    Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.
    Type: Grant
    Filed: May 24, 2019
    Date of Patent: October 13, 2020
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Giulio Marin
  • Patent number: 10691979
    Abstract: A method for classifying physical objects includes: controlling, by a processor, one or more depth cameras to capture depth images of a query object; controlling, by the processor, one or more color cameras to capture a color images of the query object; computing, by the processor, a three-dimensional (3D) model of the query object using the depth images; combining, by the processor, the color images with the 3D model; computing, by the processor, a descriptor from the 3D model and the color images, the descriptor including: a multi-dimensional shape descriptor space representation of a 3D shape of the query object; a multi-dimensional color descriptor space representation of a texture of the query object; and a one-dimensional size descriptor space representation of a size of query object; supplying, by the processor, the descriptor to a classifier to compute a classification of the query object; and outputting the classification of the query object.
    Type: Grant
    Filed: January 4, 2018
    Date of Patent: June 23, 2020
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Alvise Memo
  • Patent number: 10650588
    Abstract: A method for generating a three-dimensional model of an object, by a scanning system including a client-side device including: an acquisition system configured to capture images; and an interaction system including a display device and a network interface includes: capturing a plurality of images of the object by the acquisition system, the images being captured from a plurality of different poses of the acquisition system; computing depth maps from the images of the objects, each of the depth maps corresponding to one of the poses of the acquisition system; combining the depth maps to generate a combined point cloud; and displaying, on the display device, the combined point cloud or a 3D mesh model generated from the combined point cloud.
    Type: Grant
    Filed: December 7, 2018
    Date of Patent: May 12, 2020
    Assignee: Aquifi, Inc.
    Inventors: Aryan Hazeghi, Giuliano Pasqualotto, Keith Blackstone, Carlo Dal Mutto, Abbas Rafii, Jason Trachewsky, Jackson Masters
  • Publication number: 20200098122
    Abstract: A system for acquiring three-dimensional (3-D) models of objects includes a first camera group including: a first plurality of depth cameras having overlapping fields of view; a first processor; and a first memory storing instructions that, when executed by the first processor, cause the first processor to: control the first depth cameras to simultaneously capture a first group of images of a first portion of a first object; compute a partial 3-D model representing the first portion of the first object; and detect defects in the first object based on the partial 3-D model representing the first portion of the first object.
    Type: Application
    Filed: May 6, 2019
    Publication date: March 26, 2020
    Inventors: Carlo Dal Mutto, Francesco Peruch
  • Patent number: 10579875
    Abstract: A method for identifying and tracking objects includes: capturing one or more 3-D models of one or more objects in a scene using a three-dimensional (3-D) scanning system, the one or more 3-D models including color and geometry information of the one or more objects; and computing, by an analysis agent, one or more descriptors of the one or more 3-D models, each descriptor corresponding to a fixed-length feature vector; and retrieving metadata identifying the one or more objects based on the one or more descriptors.
    Type: Grant
    Filed: October 11, 2018
    Date of Patent: March 3, 2020
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Kinh Tieu, Tony Zuccarino, Jason Trachewsky, Abbas Rafii
  • Patent number: 10528616
    Abstract: According to one embodiment of the present invention, a method for automatically generating metadata for a media document includes: computing a feature vector of the media document using a convolutional neural network; searching a collection of media documents for one or more matching media documents having corresponding feature vectors similar to the feature vector of the media document, each media document of the collection of media documents being associated with metadata; generating metadata for the media document based on the metadata associated with the one or more matching media documents; and displaying the media document in association with the generated metadata.
    Type: Grant
    Filed: April 4, 2019
    Date of Patent: January 7, 2020
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Alvise Memo, Duc Nguyen, Abbas Rafii, Jason Trachewsky
  • Publication number: 20190364206
    Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.
    Type: Application
    Filed: May 24, 2019
    Publication date: November 28, 2019
    Inventors: Carlo Dal Mutto, Giulio Marin
  • Patent number: 10453185
    Abstract: A method for capturing a depth map includes: controlling a plurality of cameras to capture, concurrently, a plurality of first images during a first exposure interval, each of the cameras concurrently capturing a corresponding one of the first images, the cameras having overlapping fields of view; controlling a projection source to emit light at a first illumination level during the first exposure interval; controlling the cameras to capture, concurrently, a plurality of second images during a second exposure interval, each of the cameras concurrently capturing a corresponding one of the second images; controlling the projection source to emit light at a second illumination level during the second exposure interval, the second illumination level being different from the first illumination level; combining the first images with the second images to generate a depth map; and outputting the depth map.
    Type: Grant
    Filed: November 2, 2016
    Date of Patent: October 22, 2019
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Abbas Rafii, Pietro Salvagnini, Aryan Hazeghi, Michele Stoppa, Francesco Peruch, Giulio Marin
  • Publication number: 20190236096
    Abstract: According to one embodiment of the present invention, a method for automatically generating metadata for a media document includes: computing a feature vector of the media document using a convolutional neural network; searching a collection of media documents for one or more matching media documents having corresponding feature vectors similar to the feature vector of the media document, each media document of the collection of media documents being associated with metadata; generating metadata for the media document based on the metadata associated with the one or more matching media documents; and displaying the media document in association with the generated metadata.
    Type: Application
    Filed: April 4, 2019
    Publication date: August 1, 2019
    Inventors: Carlo Dal Mutto, Alvise Memo, Duc Nguyen, Abbas Rafii, Jason Trachewsky
  • Patent number: 10311648
    Abstract: A method for computing a three-dimensional (3D) model of an object includes: receiving, by a processor, a first chunk including a 3D model of a first portion of the object, the first chunk being generated from a plurality of depth images of the first portion of the object; receiving, by the processor, a second chunk including a 3D model of a second portion the object, the second chunk being generated from a plurality of depth images of the second portion of the object; computing, by the processor, a registration of the first chunk with the second chunk, the registration corresponding to a transformation aligning corresponding portions of the first and second chunks; aligning, by the processor, the first chunk with the second chunk in accordance with the registration; and outputting, by the processor, a 3D model corresponding to the first chunk merged with the second chunk.
    Type: Grant
    Filed: June 22, 2017
    Date of Patent: June 4, 2019
    Assignee: AQUIFI, INC.
    Inventors: Giridhar Murali, Keith Blackstone, Francesco Peruch, Carlo Dal Mutto
  • Patent number: 10296603
    Abstract: According to one embodiment of the present invention, a method for automatically generating metadata for a media document includes: computing a feature vector of the media document using a convolutional neural network; searching a collection of media documents for one or more matching media documents having corresponding feature vectors similar to the feature vector of the media document, each media document of the collection of media documents being associated with metadata; generating metadata for the media document based on the metadata associated with the one or more matching media documents; and displaying the media document in association with the generated metadata.
    Type: Grant
    Filed: August 11, 2017
    Date of Patent: May 21, 2019
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Alvise Memo, Duc Nguyen, Abbas Rafii, Jason Trachewsky
  • Publication number: 20190108678
    Abstract: A method for generating a three-dimensional model of an object, by a scanning system including a client-side device including: an acquisition system configured to capture images; and an interaction system including a display device and a network interface includes: capturing a plurality of images of the object by the acquisition system, the images being captured from a plurality of different poses of the acquisition system; computing depth maps from the images of the objects, each of the depth maps corresponding to one of the poses of the acquisition system; combining the depth maps to generate a combined point cloud; and displaying, on the display device, the combined point cloud or a 3D mesh model generated from the combined point cloud.
    Type: Application
    Filed: December 7, 2018
    Publication date: April 11, 2019
    Inventors: Aryan Hazeghi, Giuliano Pasqualotto, Keith Blackstone, Carlo Dal Mutto, Abbas Rafii, Jason Trachewsky, Jackson Masters
  • Publication number: 20190108396
    Abstract: A method for identifying and tracking objects includes: capturing one or more 3-D models of one or more objects in a scene using a three-dimensional (3-D) scanning system, the one or more 3-D models including color and geometry information of the one or more objects; and computing, by an analysis agent, one or more descriptors of the one or more 3-D models, each descriptor corresponding to a fixed-length feature vector; and retrieving metadata identifying the one or more objects based on the one or more descriptors.
    Type: Application
    Filed: October 11, 2018
    Publication date: April 11, 2019
    Inventors: Carlo Dal Mutto, Kinh Tieu, Tony Zuccarino, Jason Trachewsky, Abbas Rafii
  • Publication number: 20190096135
    Abstract: A system for visual inspection includes: a scanning system configured to capture images of an object and to compute a three-dimensional (3-D) model of the object based on the captured images; an inspection system configured to: compute a descriptor of the object based on the 3-D model of the object; retrieve metadata corresponding to the object based on the descriptor; and compute a plurality of inspection results based on the retrieved metadata and the 3-D model of the object; and a display device system including: a display; a processor; and a memory storing instructions that, when executed by the processor, cause the processor to: generate overlay data from the inspection results; and show the overlay data on the display, the overlay data being aligned with a view of the object through the display.
    Type: Application
    Filed: September 26, 2018
    Publication date: March 28, 2019
    Inventors: Carlo Dal Mutto, Jason Trachewsky, Tony Zuccarino
  • Patent number: 10204448
    Abstract: A method for generating a three-dimensional model of an object, by a scanning system including a client-side device including: an acquisition system configured to capture images; and an interaction system including a display device and a network interface includes: capturing a plurality of images of the object by the acquisition system, the images being captured from a plurality of different poses of the acquisition system; computing depth maps from the images of the objects, each of the depth maps corresponding to one of the poses of the acquisition system; combining the depth maps to generate a combined point cloud; and displaying, on the display device, the combined point cloud or a 3D mesh model generated from the combined point cloud.
    Type: Grant
    Filed: November 6, 2017
    Date of Patent: February 12, 2019
    Assignee: AQUIFI, INC.
    Inventors: Aryan Hazeghi, Giuliano Pasqualotto, Keith Blackstone, Carlo Dal Mutto, Abbas Rafii, Jason Trachewsky, Jackson Masters