Patents by Inventor Manuel Alberto Parente Da Silva

Manuel Alberto Parente Da Silva 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: 12012189
    Abstract: The present invention provides systems and methods for leveraging synthetic data to train machine learning models. A synthetic training engine may be used to train machine learning models. The synthetic training engine can automatically annotate real images for valuable tasks, such as object segmentation, depth map estimation, and classifying whether a structure is in an image. The synthetic training engine can also train the machine learning model with synthetic images in such a way that the machine learning model will work on real images. The output of the machine learning model may perform valuable tasks, such as the detection of integrity threats in underwater structures.
    Type: Grant
    Filed: August 8, 2018
    Date of Patent: June 18, 2024
    Assignee: Ocean Infinity (Portugal), S.A.
    Inventors: Manuel Alberto Parente Da Silva, Pedro Miguel Vendas Da Costa
  • Patent number: 11475551
    Abstract: The present invention provides a system and method of automatic detection of structure integrity threats. A threat detection engine detects integrity threats in structures, such as underwater structures, and segments the structures in an image using convolutional neural networks (“CNN”). The threat detection engine may include a dataset module, a CNN training module, a segmentation map module, a semi-supervision module, and an efficiency module. The threat detection engine may train a deep learning model to detect anomalies in videos. To do so, a dataset module with videos may be used where the dataset module includes annotations detailing at what timestamps one or more anomalies are visible.
    Type: Grant
    Filed: August 8, 2018
    Date of Patent: October 18, 2022
    Assignee: ABYSSAL S.A.
    Inventors: Pedro Miguel Vendas Da Costa, Manuel Alberto Parente Da Silva
  • Patent number: 11455740
    Abstract: The present invention provides systems and methods for simultaneous localization and mapping from video with adversarial shape prior learning in real-time. For example, an unsupervised direct and dense SLAM may learn a geometry prior from data. Given a video sequence, a depth map of a target frame, as well as the target frame and the camera motions between the target frame and all the remaining frames may be output. Further, by fusing a camera motion estimate with a positional sensor's output, positional drift and the need for loop closure can be avoided.
    Type: Grant
    Filed: August 8, 2018
    Date of Patent: September 27, 2022
    Assignee: ABYSSAL S.A.
    Inventors: Pedro Miguel Vendas Da Costa, Manuel Alberto Parente Da Silva
  • Patent number: 11436807
    Abstract: The present invention provides a system and method of position estimation for remotely operated vehicles, even in noisy environments. In some embodiments, a position estimation engine includes a 2D projection module, a registration module, a position estimation module, and an efficiency module. The improved position estimation starts with a real frame from a video and a virtual image that is the projection of the 3D elements given the ROV's noisy position. The position estimate begins by projecting each of the visible structures individually and then registers them with the real image. Then the 2D transformation resulting from the registration process is used to estimate the 3D ROV's position. Then, the ROV's position estimates are robustly combined. Because this position estimation needs to run in real-time or near real-time, an efficiency module improves the efficiency of the position estimation.
    Type: Grant
    Filed: August 8, 2018
    Date of Patent: September 6, 2022
    Assignee: ABYSSAL S.A.
    Inventors: Pedro Miguel Vendas Da Costa, Manuel Alberto Parente Da Silva
  • Publication number: 20210366097
    Abstract: The present invention provides a system and method of automatic detection of structure integrity threats. A threat detection engine detects integrity threats in structures, such as underwater structures, and segments the structures in an image using convolutional neural networks (“CNN”). The threat detection engine may include a dataset module, a CNN training module, a segmentation map module, a semi-supervision module, and an efficiency module. The threat detection engine may train a deep learning model to detect anomalies in videos. To do so, a dataset module with videos may be used where the dataset module includes annotations detailing at what timestamps one or more anomalies are visible.
    Type: Application
    Filed: August 8, 2018
    Publication date: November 25, 2021
    Inventors: Pedro Miguel VENDAS DA COSTA, Manuel Alberto PARENTE DA SILVA
  • Publication number: 20210309331
    Abstract: The present invention provides systems and methods for leveraging synthetic data to train machine learning models. A synthetic training engine may be used to train machine learning models. The synthetic training engine can automatically annotate real images for valuable tasks, such as object segmentation, depth map estimation, and classifying whether a structure is in an image. The synthetic training engine can also train the machine learning model with synthetic images in such a way that the machine learning model will work on real images. The output of the machine learning model may perform valuable tasks, such as the detection of integrity threats in underwater structures.
    Type: Application
    Filed: August 8, 2018
    Publication date: October 7, 2021
    Inventors: Manuel Alberto PARENTE DA SILVA, Pedro Miguel VENDAS DA COSTA
  • Publication number: 20210304430
    Abstract: The present invention provides systems and methods for simultaneous localization and mapping from video with adversarial shape prior learning in real-time. For example, an unsupervised direct and dense SLAM may learn a geometry prior from data. Given a video sequence, a depth map of a target frame, as well as the target frame and the camera motions between the target frame and all the remaining frames may be output. Further, by fusing a camera motion estimate with a positional sensor's output, positional drift and the need for loop closure can be avoided.
    Type: Application
    Filed: August 8, 2018
    Publication date: September 30, 2021
    Inventors: Pedro Miguel VENDAS DA COSTA, Manuel Alberto PARENTE DA SILVA
  • Publication number: 20210295605
    Abstract: The present invention provides a system and method of position estimation for remotely operated vehicles, even in noisy environments. In some embodiments, a position estimation engine includes a 2D projection module, a registration module, a position estimation module, and an efficiency module. The improved position estimation starts with a real frame from a video and a virtual image that is the projection of the 3D elements given the ROV's noisy position. The position estimate begins by projecting each of the visible structures individually and then registers them with the real image. Then the 2D transformation resulting from the registration process is used to estimate the 3D ROV's position. Then, the ROV's position estimates are robustly combined. Because this position estimation needs to run in real-time or near real-time, an efficiency module improves the efficiency of the position estimation.
    Type: Application
    Filed: August 8, 2018
    Publication date: September 23, 2021
    Inventors: Pedro Miguel VENDAS DA COSTA, Manuel Alberto PARENTE DA SILVA
  • Patent number: 10424119
    Abstract: The present invention provides a system and method of utilizing superimposed 3D imagery for remotely operated vehicles, namely 3D, reconstructed images of the environment of the ROV. In another aspect, it includes generating a virtual video of 3D elements in the operation environment, synchronizing the angle and position of the camera of a virtual video with the angle and position of a real camera, superimposing the virtual video and the real video from the real camera; superimposing these video feeds such that one is manipulated to show transparencies in areas of less interest, in order to show through the other video. It furthermore may include superimposing information, whether graphic, textual or both on to the hybrid virtual-real 3D imagery. The subject invention is also networked, such that the immersive visual interface described above is accessible to a plurality of users operating from a plurality of locations.
    Type: Grant
    Filed: July 20, 2017
    Date of Patent: September 24, 2019
    Assignee: ABYSSAL S.A.
    Inventor: Manuel Alberto Parente Da Silva
  • Publication number: 20170323487
    Abstract: The present invention provides a system and method of utilizing superimposed 3D imagery for remotely operated vehicles, namely 3D, reconstructed images of the environment of the ROV. In another aspect, it includes generating a virtual video of 3D elements in the operation environment, synchronizing the angle and position of the camera of a virtual video with the angle and position of a real camera, superimposing the virtual video and the real video from the real camera; superimposing these video feeds such that one is manipulated to show transparencies in areas of less interest, in order to show through the other video. It furthermore may include superimposing information, whether graphic, textual or both on to the hybrid virtual-real 3D imagery. The subject invention is also networked, such that the immersive visual interface described above is accessible to a plurality of users operating from a plurality of locations.
    Type: Application
    Filed: July 20, 2017
    Publication date: November 9, 2017
    Inventor: Manuel Alberto Parente Da Silva
  • Patent number: 9741173
    Abstract: The present invention provides a system and method of utilizing superimposed 3D imagery for remotely operated vehicles, namely 3D, reconstructed images of the environment of the ROV. In another aspect, it includes generating a virtual video of 3D elements in the operation environment, synchronizing the angle and position of the camera of a virtual video with the angle and position of a real camera, superimposing the virtual video and the real video from the real camera; superimposing these video feeds such that one is manipulated to show transparencies in areas of less interest, in order to show through the other video. It furthermore may include superimposing information, whether graphic, textual or both on to the hybrid virtual-real 3D imagery. The subject invention is also networked, such that the immersive visual interface described above accessible to a plurality of users operating from to plurality of locations.
    Type: Grant
    Filed: November 9, 2015
    Date of Patent: August 22, 2017
    Assignee: Abyssal S.A.
    Inventor: Manuel Alberto Parente Da Silva
  • Publication number: 20160063768
    Abstract: The present invention provides a system and method of utilizing superimposed 3D imagery for remotely operated vehicles, namely 3D, reconstructed images of the environment of the ROV. In another aspect, it includes generating a virtual video of 3D elements in the operation environment, synchronizing the angle and position of the camera of a virtual video with the angle and position of a real camera, superimposing the virtual video and the real video from the real camera; superimposing these video feeds such that one is manipulated to show transparencies in areas of less interest, in order to show through the other video. It furthermore may include superimposing information, whether graphic, textual or both on to the hybrid virtual-real 3D imagery. The subject invention is also networked, such that the immersive visual interface described above accessible to a plurality of users operating from to plurality of locations.
    Type: Application
    Filed: November 9, 2015
    Publication date: March 3, 2016
    Inventor: Manuel Alberto Parente Da Silva
  • Patent number: 9195231
    Abstract: The present invention provides a system and method of utilizing superimposed 3D imagery for remotely operated vehicles, namely 3D, reconstructed images of the environment of the ROV. In another aspect, it includes generating a virtual video of 3D elements in the operation environment, synchronizing the angle and position of the camera of a virtual video with the angle and position of a real camera, superimposing the virtual video and the real video from the real camera; superimposing these video feeds such that one is manipulated to show transparencies in areas of less interest, in order to show through the other video. It furthermore may include superimposing information, whether graphic, textual or both on to the hybrid virtual-real 3D imagery. The subject invention is also networked, such that the immersive visual interface described above is accessible to a plurality of users operating from a plurality of locations.
    Type: Grant
    Filed: November 8, 2012
    Date of Patent: November 24, 2015
    Assignee: Abyssal S.A.
    Inventor: Manuel Alberto Parente Da Silva
  • Publication number: 20140316611
    Abstract: The present invention provides a system and method of utilizing superimposed 3D imagery for remotely operated vehicles, namely 3D, reconstructed images of the environment of the ROV. In another aspect, it includes generating a virtual video of 3D elements in the operation environment, synchronizing the angle and position of the camera of a virtual video with the angle and position of a real camera, superimposing the virtual video and the real video from the real camera; superimposing these video feeds such that one is manipulated to show transparencies in areas of less interest, in order to show through the other video. It furthermore may include superimposing information, whether graphic, textual or both on to the hybrid virtual-real 3D imagery. The subject invention is also networked, such that the immersive visual interface described above is accessible to a plurality of users operating from a plurality of locations.
    Type: Application
    Filed: November 8, 2012
    Publication date: October 23, 2014
    Inventor: Manuel Alberto Parente Da Silva