- 专利标题: PIPE FEATURE IDENTIFICATION USING PIPE INSPECTION DATA ANALYSIS
-
申请号: US16184073申请日: 2018-11-08
-
公开(公告)号: US20190139215A1公开(公告)日: 2019-05-09
- 发明人: Justin Starr , Galin Konakchiev , Foster J Salotti , Mark Jordan , Nate Alford , Thorin Tobiassen , Todd Kueny , Jason Mizgorski
- 申请人: RedZone Robotics, Inc.
- 申请人地址: US PA Pittsburgh
- 专利权人: RedZone Robotics, Inc.
- 当前专利权人: RedZone Robotics, Inc.
- 当前专利权人地址: US PA Pittsburgh
- 主分类号: G06T7/00
- IPC分类号: G06T7/00 ; G01M3/00 ; G01M3/38 ; G06T7/73 ; G06K9/62
摘要:
One aspect provides a method, including: operating a mobile pipe inspection platform to obtain sensor data for the interior of a pipe; analyzing, using a processor, the sensor data using a trained model, where the trained model is trained using a dataset including sensor data of pipe interiors and one or more of: metadata identifying pipe feature locations contained within the sensor data of the dataset and metadata classifying pipe features contained within the sensor data of the dataset; performing one or more of: identifying, using a processor, a pipe feature location within the sensor data; and classifying, using a processor, a pipe feature of the sensor data; and thereafter producing, using a processor, an output including one or more of an indication of the identifying and an indication of the classifying. Other aspects are described and claimed.