公开(公告)号：US20220309687A1

公开(公告)日：2022-09-29

申请号：US17712613

申请日：2022-04-04

Applicant: Skydio, Inc.

Inventor： Saumitro Dasgupta ,  Hayk Martirosyan ,  Hema Koppula ,  Alex Kendall ,  Austin Stone ,  Matthew Donahoe ,  Abraham Galton Bachrach ,  Adam Parker Bry

IPC: G06T7/292 ,  B64C39/02 ,  G06T7/73 ,  G06K9/62 ,  G06T7/10 ,  G06T3/60 ,  G05D1/00 ,  H04N13/243 ,  H04N13/239 ,  G06T7/579 ,  H04N13/282 ,  G06T7/11 ,  G06T7/20 ,  G06V20/13 ,  G06V30/194 ,  G06V30/262

Abstract: Systems and methods are disclosed for tracking objects in a physical environment using visual sensors onboard an autonomous unmanned aerial vehicle (UAV). In certain embodiments, images of the physical environment captured by the onboard visual sensors are processed to extract semantic information about detected objects. Processing of the captured images may involve applying machine learning techniques such as a deep convolutional neural network to extract semantic cues regarding objects detected in the images. The object tracking can be utilized, for example, to facilitate autonomous navigation by the UAV or to generate and display augmentative information regarding tracked objects to users.

公开(公告)号：US11861892B2

公开(公告)日：2024-01-02

申请号：US17712613

申请日：2022-04-04

Applicant: Skydio, Inc.

Inventor： Saumitro Dasgupta ,  Hayk Martirosyan ,  Hema Koppula ,  Alex Kendall ,  Austin Stone ,  Matthew Donahoe ,  Abraham Galton Bachrach ,  Adam Parker Bry

IPC: G06V20/13 ,  G06T7/292 ,  B64C39/02 ,  G06T7/73 ,  G06T7/10 ,  G06T3/60 ,  G05D1/00 ,  H04N13/243 ,  H04N13/239 ,  G06T7/579 ,  H04N13/282 ,  G06T7/11 ,  G06T7/20 ,  G06V30/262 ,  G06F18/2431 ,  G06V10/82 ,  G06V20/17 ,  H04N13/00 ,  G06N3/045 ,  B64U101/00 ,  B64U101/30

CPC classification number: G06V20/13 ,  B64C39/024 ,  G05D1/0011 ,  G05D1/0094 ,  G06F18/2431 ,  G06T3/60 ,  G06T7/10 ,  G06T7/11 ,  G06T7/20 ,  G06T7/292 ,  G06T7/579 ,  G06T7/75 ,  G06V10/82 ,  G06V20/17 ,  G06V30/274 ,  H04N13/239 ,  H04N13/243 ,  H04N13/282 ,  B64U2101/00 ,  B64U2101/30 ,  B64U2201/10 ,  G06N3/045 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/20084 ,  G06T2207/20088 ,  G06T2207/30196 ,  G06T2207/30241 ,  H04N2013/0081 ,  H04N2013/0085 ,  H04N2013/0092

Abstract: Systems and methods are disclosed for tracking objects in a physical environment using visual sensors onboard an autonomous unmanned aerial vehicle (UAV). In certain embodiments, images of the physical environment captured by the onboard visual sensors are processed to extract semantic information about detected objects. Processing of the captured images may involve applying machine learning techniques such as a deep convolutional neural network to extract semantic cues regarding objects detected in the images. The object tracking can be utilized, for example, to facilitate autonomous navigation by the UAV or to generate and display augmentative information regarding tracked objects to users.

公开(公告)号：US11295458B2

公开(公告)日：2022-04-05

申请号：US15827945

申请日：2017-11-30

Applicant: Skydio, Inc.

Inventor： Saumitro Dasgupta ,  Hayk Martirosyan ,  Hema Koppula ,  Alex Kendall ,  Austin Stone ,  Matthew Donahoe ,  Abraham Galton Bachrach ,  Adam Parker Bry

IPC: G06T7/292 ,  B64C39/02 ,  G06T7/73 ,  G06K9/62 ,  G06K9/72 ,  G06K9/00 ,  G06K9/66 ,  G06T7/10 ,  G06T3/60 ,  G05D1/00 ,  H04N13/243 ,  H04N13/239 ,  G06T7/579 ,  H04N13/282 ,  G06T7/11 ,  G06T7/20 ,  H04N13/00 ,  G06N3/04

Abstract: Systems and methods are disclosed for tracking objects in a physical environment using visual sensors onboard an autonomous unmanned aerial vehicle (UAV). In certain embodiments, images of the physical environment captured by the onboard visual sensors are processed to extract semantic information about detected objects. Processing of the captured images may involve applying machine learning techniques such as a deep convolutional neural network to extract semantic cues regarding objects detected in the images. The object tracking can be utilized, for example, to facilitate autonomous navigation by the UAV or to generate and display augmentative information regarding tracked objects to users.

公开(公告)号：US20240273894A1

公开(公告)日：2024-08-15

申请号：US18400113

申请日：2023-12-29

Applicant: Skydio, Inc.

Inventor： Saumitro Dasgupta ,  Hayk Martirosyan ,  Hema Koppula ,  Alex Kendall ,  Austin Stone ,  Matthew Donahoe ,  Abraham Galton Bachrach ,  Adam Parker Bry

IPC: G06V20/13 ,  B64C39/02 ,  B64U101/00 ,  B64U101/30 ,  G06F18/2431 ,  G06N3/045 ,  G06T3/60 ,  G06T7/10 ,  G06T7/11 ,  G06T7/20 ,  G06T7/292 ,  G06T7/579 ,  G06T7/73 ,  G06V10/82 ,  G06V20/17 ,  G06V30/262 ,  H04N13/00 ,  H04N13/239 ,  H04N13/243 ,  H04N13/282

CPC classification number: G06V20/13 ,  B64C39/024 ,  G06F18/2431 ,  G06T3/60 ,  G06T7/10 ,  G06T7/11 ,  G06T7/20 ,  G06T7/292 ,  G06T7/579 ,  G06T7/75 ,  G06V10/82 ,  G06V20/17 ,  G06V30/274 ,  H04N13/239 ,  H04N13/243 ,  H04N13/282 ,  B64U2101/00 ,  B64U2101/30 ,  B64U2201/10 ,  G06N3/045 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/20084 ,  G06T2207/20088 ,  G06T2207/30196 ,  G06T2207/30241 ,  H04N2013/0081 ,  H04N2013/0085 ,  H04N2013/0092

Abstract: Systems and methods are disclosed for tracking objects in a physical environment using visual sensors onboard an autonomous unmanned aerial vehicle (UAV). In certain embodiments, images of the physical environment captured by the onboard visual sensors are processed to extract semantic information about detected objects. Processing of the captured images may involve applying machine learning techniques such as a deep convolutional neural network to extract semantic cues regarding objects detected in the images. The object tracking can be utilized, for example, to facilitate autonomous navigation by the UAV or to generate and display augmentative information regarding tracked objects to users.

公开(公告)号：US20180158197A1

公开(公告)日：2018-06-07

申请号：US15827945

申请日：2017-11-30

Applicant: Skydio, Inc.

Inventor： Saumitro Dasgupta ,  Hayk Martirosyan ,  Hema Koppula ,  Alex Kendall ,  Austin Stone ,  Matthew Donahoe ,  Abraham Bachrach ,  Adam Bry

IPC: G06T7/292 ,  G05D1/00 ,  G05D1/10 ,  B64C39/02 ,  G06T7/73 ,  G06K9/62 ,  G06K9/72 ,  G06K9/00 ,  G06K9/66 ,  G06T7/10 ,  G06T3/60 ,  H04N13/02

CPC classification number: G06T7/292 ,  B64C39/024 ,  B64C2201/123 ,  B64C2201/126 ,  B64C2201/127 ,  B64C2201/141 ,  G05D1/0011 ,  G05D1/0094 ,  G05D1/101 ,  G06K9/0063 ,  G06K9/628 ,  G06K9/66 ,  G06K9/726 ,  G06N3/0454 ,  G06T3/60 ,  G06T7/10 ,  G06T7/11 ,  G06T7/20 ,  G06T7/579 ,  G06T7/75 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/20084 ,  G06T2207/20088 ,  G06T2207/30196 ,  G06T2207/30241 ,  H04N13/239 ,  H04N13/243 ,  H04N13/282 ,  H04N2013/0081 ,  H04N2013/0085 ,  H04N2013/0092

Abstract: Systems and methods are disclosed for tracking objects in a physical environment using visual sensors onboard an autonomous unmanned aerial vehicle (UAV). In certain embodiments, images of the physical environment captured by the onboard visual sensors are processed to extract semantic information about detected objects. Processing of the captured images may involve applying machine learning techniques such as a deep convolutional neural network to extract semantic cues regarding objects detected in the images. The object tracking can be utilized, for example, to facilitate autonomous navigation by the UAV or to generate and display augmentative information regarding tracked objects to users.