Patents by Inventor Boris Aleksandrovich Babenko
Boris Aleksandrovich Babenko 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: 10607362Abstract: Disclosed is a method and system for processing images from an aerial imaging device. The method includes receiving a first image of a geographical area having a first resolution. The method transmits the first image to a machine learning model to identify an area of interest containing an object of interest. The method receives a second image of the geographical area having a second resolution higher than the first resolution. The method transmits the second image to the machine learning model to determine a likelihood that the area of interest contains the object of interest. The method trains the machine learning model to filter out features corresponding to the area of interest in images having the first resolution if the likelihood is below a threshold. The method transmits a visual representation of the object of interest to a user device if the likelihood exceeds the threshold.Type: GrantFiled: February 15, 2019Date of Patent: March 31, 2020Assignee: ORBITAL INSIGHT, INC.Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Daniel Michael Sammons, Jasper Lin, Jason D. Lohn
-
Publication number: 20190220696Abstract: A method comprises accessing a plurality of images of a substantially same geographical area, each image of the plurality of images captured at a separate time from each other using a separate imaging sensor, each imaging sensor capturing information corresponding to a different spectral band. The method further comprises identifying, for the images, a set of blobs, each blob comprising a plurality of adjacent pixels, wherein each image of the plurality of images includes a blob of the set of blobs, and wherein each blob in the set of blobs has a location in each image that differs from a location of other blobs in the set of blobs. The method further comprises generating a score indicating a likelihood that the set of blobs correspond to a moving object, storing an indication that the set of blobs correspond to the moving object responsive to the generated score exceeding a threshold.Type: ApplicationFiled: March 22, 2019Publication date: July 18, 2019Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Michael Alan Baxter, Steven Jeffrey Bickerton
-
Publication number: 20190180464Abstract: Disclosed is a method and system for processing images from an aerial imaging device. The method includes receiving a first image of a geographical area having a first resolution. The method transmits the first image to a machine learning model to identify an area of interest containing an object of interest. The method receives a second image of the geographical area having a second resolution higher than the first resolution. The method transmits the second image to the machine learning model to determine a likelihood that the area of interest contains the object of interest. The method trains the machine learning model to filter out features corresponding to the area of interest in images having the first resolution if the likelihood is below a threshold. The method transmits a visual representation of the object of interest to a user device if the likelihood exceeds the threshold.Type: ApplicationFiled: February 15, 2019Publication date: June 13, 2019Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Daniel Michael Sammons, Jasper Lin, Jason D. Lohn
-
Patent number: 10319107Abstract: Disclosed is a method and system for processing images from an aerial imaging device. An image of an object of interest is received from the aerial imaging device. A parameter vector is extracted from the image. Image analysis is performed on the image to determine a height and a width of the object of interest. Idealized images of the object of interest are generated using the extracted parameter vector, the determined height, and the determined width of the object of interest. Each idealized image corresponds to a distinct filled volume of the object of interest. The received image of the object of interest is matched to each idealized image to determine a filled volume of the object of interest. Information corresponding to the determined filled volume of the object of interest is transmitted to a user device.Type: GrantFiled: January 26, 2018Date of Patent: June 11, 2019Assignee: Orbital Insight, Inc.Inventors: Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Jason D. Lohn
-
Patent number: 10255523Abstract: Disclosed is a method and system for processing images from an aerial imaging device. A moving vehicle analysis system receives images from an aerial imaging device. The system may perform edge analysis in the images to identify a pairs of edges corresponding to a road. The system may identify pixel blobs in the images including adjacent pixels matching each other based on a pixel attribute. The system uses a machine learning model for generating an output identifying moving vehicles in the images. The system determines a count of the moving vehicles captured by the images, where each moving vehicle is associated with corresponding pixel blobs.Type: GrantFiled: November 14, 2016Date of Patent: April 9, 2019Assignee: ORBITAL INSIGHT, INC.Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Michael Alan Baxter, Steven Jeffrey Bickerton
-
Patent number: 10217236Abstract: Disclosed is a method and system for processing images from an aerial imaging device. The method includes receiving a first image of a geographical area having a first resolution. The method transmits the first image to a machine learning model to identify an area of interest containing an object of interest. The method receives a second image of the geographical area having a second resolution higher than the first resolution. The method transmits the second image to the machine learning model to determine a likelihood that the area of interest contains the object of interest. The method trains the machine learning model to filter out features corresponding to the area of interest in images having the first resolution if the likelihood is below a threshold. The method transmits a visual representation of the object of interest to a user device if the likelihood exceeds the threshold.Type: GrantFiled: April 12, 2018Date of Patent: February 26, 2019Assignee: ORBITAL INSIGHT, INC.Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Daniel Michael Sammons, Jasper Lin, Jason D. Lohn
-
Patent number: 10192323Abstract: Disclosed is a method and system for processing images from an aerial imaging device. The method includes receiving a first image of a geographical area having a first resolution. The method transmits the first image to a machine learning model to identify an area of interest containing an object of interest. The method receives a second image of the geographical area having a second resolution higher than the first resolution. The method transmits the second image to the machine learning model to determine a likelihood that the area of interest contains the object of interest. The method trains the machine learning model to filter out features corresponding to the area of interest in images having the first resolution if the likelihood is below a threshold. The method transmits a visual representation of the object of interest to a user device if the likelihood exceeds the threshold.Type: GrantFiled: March 27, 2017Date of Patent: January 29, 2019Assignee: ORBITAL INSIGHT, INC.Inventors: Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Jason D. Lohn
-
Publication number: 20180232900Abstract: Disclosed is a method and system for processing images from an aerial imaging device. The method includes receiving a first image of a geographical area having a first resolution. The method transmits the first image to a machine learning model to identify an area of interest containing an object of interest. The method receives a second image of the geographical area having a second resolution higher than the first resolution. The method transmits the second image to the machine learning model to determine a likelihood that the area of interest contains the object of interest. The method trains the machine learning model to filter out features corresponding to the area of interest in images having the first resolution if the likelihood is below a threshold. The method transmits a visual representation of the object of interest to a user device if the likelihood exceeds the threshold.Type: ApplicationFiled: April 12, 2018Publication date: August 16, 2018Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Daniel Michael Sammons, Jasper Lin, Jason D. Lohn
-
Publication number: 20180182122Abstract: Disclosed is a method and system for processing images from an aerial imaging device. An image of an object of interest is received from the aerial imaging device. A parameter vector is extracted from the image. Image analysis is performed on the image to determine a height and a width of the object of interest. Idealized images of the object of interest are generated using the extracted parameter vector, the determined height, and the determined width of the object of interest. Each idealized image corresponds to a distinct filled volume of the object of interest. The received image of the object of interest is matched to each idealized image to determine a filled volume of the object of interest. Information corresponding to the determined filled volume of the object of interest is transmitted to a user device.Type: ApplicationFiled: January 26, 2018Publication date: June 28, 2018Inventors: Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Jason D. Lohn
-
Patent number: 9934591Abstract: Disclosed is a method and system for processing images from an aerial imaging device. An image of an object of interest is received from the aerial imaging device. A parameter vector is extracted from the image. Image analysis is performed on the image to determine a height and a width of the object of interest. Idealized images of the object of interest are generated using the extracted parameter vector, the determined height, and the determined width of the object of interest. Each idealized image corresponds to a distinct filled volume of the object of interest. The received image of the object of interest is matched to each idealized image to determine a filled volume of the object of interest. Information corresponding to the determined filled volume of the object of interest is transmitted to a user device.Type: GrantFiled: March 27, 2017Date of Patent: April 3, 2018Assignee: Orbital Insight, Inc.Inventors: Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Jason D. Lohn
-
Publication number: 20170294027Abstract: Disclosed is a method and system for processing images from an aerial imaging device. An image of an object of interest is received from the aerial imaging device. A parameter vector is extracted from the image. Image analysis is performed on the image to determine a height and a width of the object of interest. Idealized images of the object of interest are generated using the extracted parameter vector, the determined height, and the determined width of the object of interest. Each idealized image corresponds to a distinct filled volume of the object of interest. The received image of the object of interest is matched to each idealized image to determine a filled volume of the object of interest. Information corresponding to the determined filled volume of the object of interest is transmitted to a user device.Type: ApplicationFiled: March 27, 2017Publication date: October 12, 2017Inventors: Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Jason D. Lohn
-
Publication number: 20170293800Abstract: Disclosed is a method and system for processing images from an aerial imaging device. The method includes receiving a first image of a geographical area having a first resolution. The method transmits the first image to a machine learning model to identify an area of interest containing an object of interest. The method receives a second image of the geographical area having a second resolution higher than the first resolution. The method transmits the second image to the machine learning model to determine a likelihood that the area of interest contains the object of interest. The method trains the machine learning model to filter out features corresponding to the area of interest in images having the first resolution if the likelihood is below a threshold. The method transmits a visual representation of the object of interest to a user device if the likelihood exceeds the threshold.Type: ApplicationFiled: March 27, 2017Publication date: October 12, 2017Inventors: Boris Aleksandrovich Babenko, Alexander Bogdanov Avtanski, Jason D. Lohn
-
Publication number: 20170140245Abstract: Disclosed is a method and system for processing images from an aerial imaging device. A moving vehicle analysis system receives images from an aerial imaging device. The system may perform edge analysis in the images to identify a pairs of edges corresponding to a road. The system may identify pixel blobs in the images including adjacent pixels matching each other based on a pixel attribute. The system uses a machine learning model for generating an output identifying moving vehicles in the images. The system determines a count of the moving vehicles captured by the images, where each moving vehicle is associated with corresponding pixel blobs.Type: ApplicationFiled: November 14, 2016Publication date: May 18, 2017Inventors: Adam Wiggen Kraft, Boris Aleksandrovich Babenko, Michael Alan Baxter, Steven Jeffrey Bickerton