Patents by Inventor Lars P. Dyrud
Lars P. Dyrud 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: 11734560Abstract: Methods and systems for automatic estimation of object characteristics from a digital image are disclosed, including a method comprising sub-dividing into two or more segments a digital image comprising pixels and depicting an object of interest, wherein each segment comprises two or more pixels; assessing content depicted in one or more of the segments for a predetermined object characteristic using machine learning techniques comprising General Image Classification of the one or more segments using a convolutional neural network, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined object characteristic; and determining a level of confidence of one or more of the segments having the one or more predetermined object characteristic based on the General Image Classification assessment.Type: GrantFiled: March 5, 2021Date of Patent: August 22, 2023Assignee: OmniEarth, Inc.Inventors: Shadrian Strong, David Murr, Lars P. Dyrud
-
Patent number: 11145008Abstract: A device includes an image data receiving component, a vegetation index generation component, a crop data receiving component, a masking component and a multivariate regression component. The image data receiving component receives image data of a geographic region. The vegetation index generation component generates an array of vegetation indices based on the received image data, and includes a plurality of vegetation index generating components, each operable to generate a respective individual vegetation index based on the received image data. The crop data receiving component receives crop data associated with the geographic region. The masking component generates a masked vegetation index based on the array of vegetation indices and the received crop data. The multivariate regression component generates a crop parameter based on the masked vegetation index.Type: GrantFiled: June 12, 2020Date of Patent: October 12, 2021Assignee: OmniEarth, Inc.Inventors: David Murr, Shadrian Strong, Kristin Lavigne, Lars P Dyrud, Jonathan T Fentzke
-
Publication number: 20210264217Abstract: Methods and systems for automatic estimation of object characteristics from a digital image are disclosed, including a method comprising sub-dividing into two or more segments a digital image comprising pixels and depicting an object of interest, wherein each segment comprises two or more pixels; assessing content depicted in one or more of the segments for a predetermined object characteristic using machine learning techniques comprising General Image Classification of the one or more segments using a convolutional neural network, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined object characteristic; and determining a level of confidence of one or more of the segments having the one or more predetermined object characteristic based on the General Image Classification assessment.Type: ApplicationFiled: March 5, 2021Publication date: August 26, 2021Inventors: Shadrian Strong, David Murr, Lars P. Dyrud
-
Patent number: 10943149Abstract: Methods and systems for automatic estimation of object characteristics from a digital image are disclosed, including a method comprising sub-dividing into two or more segments a digital image comprising pixels and depicting an object of interest, wherein each segment comprises two or more pixels; assessing content depicted in one or more of the segments for a predetermined object characteristic using machine learning techniques comprising General Image Classification of the one or more segments using a convolutional neural network, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined object characteristic; and determining a level of confidence of one or more of the segments having the one or more predetermined object characteristic based on the General Image Classification assessment.Type: GrantFiled: August 30, 2018Date of Patent: March 9, 2021Assignee: OMNIEARTH, INC.Inventors: Shadrian Strong, David Murr, Lars P. Dyrud
-
Publication number: 20200380617Abstract: A device includes an image data receiving component, a vegetation index generation component, a crop data receiving component, a masking component and a multivariate regression component. The image data receiving component receives image data of a geographic region. The vegetation index generation component generates an array of vegetation indices based on the received image data, and includes a plurality of vegetation index generating components, each operable to generate a respective individual vegetation index based on the received image data. The crop data receiving component receives crop data associated with the geographic region. The masking component generates a masked vegetation index based on the array of vegetation indices and the received crop data. The multivariate regression component generates a crop parameter based on the masked vegetation index.Type: ApplicationFiled: June 12, 2020Publication date: December 3, 2020Inventors: David Murr, Shadrian Strong, Kristin Lavigne, Lars P. Dyrud, Jonathan T. Fentzke
-
Patent number: 10685408Abstract: A device includes an image data receiving component, a vegetation index generation component, a crop data receiving component, a masking component and a multivariate regression component. The image data receiving component receives image data of a geographic region. The vegetation index generation component generates an array of vegetation indices based on the received image data, and includes a plurality of vegetation index generating components, each operable to generate a respective individual vegetation index based on the received image data. The crop data receiving component receives crop data associated with the geographic region. The masking component generates a masked vegetation index based on the array of vegetation indices and the received crop data. The multivariate regression component generates a crop parameter based on the masked vegetation index.Type: GrantFiled: September 5, 2015Date of Patent: June 16, 2020Assignee: OmniEarth, Inc.Inventors: David Murr, Shadrian Strong, Kristin Lavigne, Lars P Dyrud, Jonathan T Fentzke
-
Publication number: 20190065907Abstract: Methods and systems for automatic estimation of object characteristics from a digital image are disclosed, including a method comprising sub-dividing into two or more segments a digital image comprising pixels and depicting an object of interest, wherein each segment comprises two or more pixels; assessing content depicted in one or more of the segments for a predetermined object characteristic using machine learning techniques comprising General Image Classification of the one or more segments using a convolutional neural network, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined object characteristic; and determining a level of confidence of one or more of the segments having the one or more predetermined object characteristic based on the General Image Classification assessment.Type: ApplicationFiled: August 30, 2018Publication date: February 28, 2019Inventors: Shadrian Strong, David Murr, Lars P. Dyrud
-
Publication number: 20180293671Abstract: A device includes an image data receiving component, a vegetation index generation component, a crop data receiving component, a masking component and a multivariate regression component. The image data receiving component receives image data of a geographic region. The vegetation index generation component generates an array of vegetation indices based on the received image data, and includes a plurality of vegetation index generating components, each operable to generate a respective individual vegetation index based on the received image data. The crop data receiving component receives crop data associated with the geographic region. The masking component generates a masked vegetation index based on the array of vegetation indices and the received crop data. The multivariate regression component generates a crop parameter based on the masked vegetation index.Type: ApplicationFiled: September 5, 2015Publication date: October 11, 2018Inventors: David Murr, Shadrian Strong, Kristin Lavigne, Lars P. Dyrud, Jonathan T. Fentzke
-
Patent number: 9552638Abstract: A device includes an image data receiving component, a vegetation index generation component, a spatial structure variance generation component, a classification component and a water budget component. The image data receiving component receives multiband image data of a geographic region. The vegetation index generation component generates a vegetation index based on the received multiband image data. The spatial structure variance generation component generates a spatial structure variance image band based on the received multiband image data. The classification component generates a land cover classification based on the received multiband image data, the vegetation index and the spatial structure variance image band. The water budget component generates a water budget of a portion of the geographic region based on the land cover classification.Type: GrantFiled: June 2, 2016Date of Patent: January 24, 2017Assignee: OMNIEARTH, INC.Inventors: Kristin Lavigne, Shadrian Strong, David Murr, Lars P. Dyrud, Jonathan T. Fentzke, Indra Epple
-
Publication number: 20160314586Abstract: A device includes an image data receiving component, a vegetation index generation component, a spatial structure variance generation component, a classification component and a water budget component. The image data receiving component receives multiband image data of a geographic region. The vegetation index generation component generates a vegetation index based on the received multiband image data. The spatial structure variance generation component generates a spatial structure variance image band based on the received multiband image data. The classification component generates a land cover classification based on the received multiband image data, the vegetation index and the spatial structure variance image band. The water budget component generates a water budget of a portion of the geographic region based on the land cover classification.Type: ApplicationFiled: June 2, 2016Publication date: October 27, 2016Inventors: Kristin Lavigne, Shadrian Strong, David Murr, Lars P. Dyrud, Jonathan T. Fentzke, Indra Epple
-
Patent number: 9418290Abstract: A device includes an image data receiving component, a vegetation index generation component, a GLC matrix component, a plurality of classifying components and a voting component. The image data receiving component receives multiband image data of a geographic region. The vegetation index generation component generates a normalized difference vegetation index based on the received multiband image data. The GLC matrix component generates a grey level co-occurrence matrix image band based on the received multiband image data. The classifying components generate land cover classifications based on the received multiband image data, the normalized difference vegetation index and the grey level co-occurrence matrix image band. The voting component generates a final land cover classification based a majority vote of the land cover classifications.Type: GrantFiled: April 27, 2015Date of Patent: August 16, 2016Assignee: OmniEarth, Inc.Inventors: Kristin Lavigne, David Murr, Lars P. Dyrud, Jonathan T. Fentzke, Indra Epple, Shadrian Strong
-
Publication number: 20160171302Abstract: A device includes an image data receiving component, a vegetation index generation component, a GLC matrix component, a plurality of classifying components and a voting component. The image data receiving component receives multiband image data of a geographic region. The vegetation index generation component generates a normalized difference vegetation index based on the received multiband image data. The GLC matrix component generates a grey level co-occurrence matrix image band based on the received multiband image data. The classifying components generate land cover classifications based on the received multiband image data, the normalized difference vegetation index and the grey level co-occurrence matrix image band. The voting component generates a final land cover classification based a majority vote of the land cover classifications.Type: ApplicationFiled: April 27, 2015Publication date: June 16, 2016Inventors: Kristin Lavigne, David Murr, Lars P. Dyrud, Jonathan T. Fentzke, Indra Epple, Shadrian Strong
-
Patent number: 8686721Abstract: A system, method and computer-readable medium for mapping magnetic activity for a current linking a planet's space environment to an ionosphere of the planet are disclosed. Magnetic field measurements of the current are obtained from a plurality of satellites orbiting the planet. A residual magnetic field is determined from the obtained magnetic field measurements. The determined residual magnetic field is arranged to create a time series for a selected location of a planet-centered coordinate system. The magnetic activity is mapped using the created time series for the selected location.Type: GrantFiled: April 19, 2012Date of Patent: April 1, 2014Assignee: The Johns Hopkins UniversityInventors: Brian J. Anderson, Lars P. Dyrud, Jonathan T. Fentzke, Robin J. Barnes
-
Publication number: 20130221951Abstract: A system, method and computer-readable medium for mapping magnetic activity for a current linking a planet's space environment to an ionosphere of the planet are disclosed. Magnetic field measurements of the current are obtained from a plurality of satellites orbiting the planet. A residual magnetic field is determined from the obtained magnetic field measurements. The determined residual magnetic field is arranged to create a time series for a selected location of a planet-centered coordinate system. The magnetic activity is mapped using the created time series for the selected location.Type: ApplicationFiled: April 19, 2012Publication date: August 29, 2013Applicant: THE JOHNS HOPKINS UNIVERSITYInventors: Brian J. Anderson, Lars P. Dyrud, Jonathan T. Fentzke, Robin J. Barnes