US 11,836,930 B2
Slip-to-slip connection time on oil rigs with computer vision
Adriano De Araújo Abreu Mourão, Belo Horizonte (BR); Hugo Zanini Gomes, Belo Horizonte (BR); Rogerio Cosendey Labanca, Belo Horizonte (BR); Rafael Soares Mendonça, São Paulo (BR); Paulo Henrique Barchi, Limeira (BR); and Renato Mintz, Belo Horizonte (BR)
Assigned to Accenture Global Solutions Limited, Dublin (IE)
Filed by Accenture Global Solutions Limited, Dublin (IE)
Filed on Nov. 22, 2021, as Appl. No. 17/532,516.
Claims priority of provisional application 63/119,588, filed on Nov. 30, 2020.
Prior Publication US 2022/0172373 A1, Jun. 2, 2022
Int. Cl. G06T 7/20 (2017.01); G06T 7/00 (2017.01); G06N 20/00 (2019.01); G06V 10/22 (2022.01); G06V 20/40 (2022.01); G06F 18/214 (2023.01); G06T 5/20 (2006.01); G08B 21/18 (2006.01)
CPC G06T 7/20 (2013.01) [G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 5/20 (2013.01); G06T 7/0004 (2013.01); G06V 10/22 (2022.01); G06V 20/40 (2022.01); G08B 21/18 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30164 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for detecting motion of a pipe of an oil rig based on video analysis and machine learning, the method comprising:
obtaining, by one or more processors, video data associated with a pipe on an oil rig;
detecting, by the one or more processors, motion in one or more regions within one or more frames of the video data;
providing, by the one or more processors, the one or more frames to one or more machine learning (ML) models to determine whether the pipe is moving during a time period associated with the one or more frames,
wherein the one or more ML models comprise a convolutional neural network (CNN) comprising three convolutional layers, three spatial dropout layers, and three fully connected layers,
wherein the one or more ML models are configured to determine whether the pipe is moving based on input video data; and
generating, by the one or more processors, an output indicating whether the pipe is moving during the time period.