-
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.
-
-
-
-