Patents by Inventor Alexander Schwing
Alexander Schwing 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: 11699239Abstract: An image processing method includes defining relations between entities of a target of which a motion is to be predicted from an image of a first time point based on a feature vector of the entities, estimating a dynamic interaction between the entities at the first time point based on the defined relations between the entities, predicting a motion of the entities changing at a second time point based on the estimated dynamic interaction, and outputting a result to which the motion predicted at the second time point is applied.Type: GrantFiled: April 13, 2021Date of Patent: July 11, 2023Assignees: The Board of Trustees of the University of Illinois (Urbana, IL), Samsung Electronics Co., Ltd.Inventors: Alexander Schwing, Colin Graber, Raymond Yeh, Jihye Kim, Jaejoon Han
-
Publication number: 20220319016Abstract: Panoptic segmentation forecasting predicts future positions of foreground objects and background objects separately. An egomotion model may be implemented to estimate egomotion of the camera. Pixels in frames of captured video are classified between foreground and background. The foreground pixels are grouped into foreground objects. A foreground motion model forecasts motion of the foreground objects to a future timestamp. A background motion model backprojects the background pixels into point clouds in a three-dimensional space. The background motion model predicts future positions of the point clouds based on egomotion. The background motion model may further generate novel point clouds to fill in occluded space. With the predicted future positions, the foreground objects and the background pixels are combined into a single panoptic segmentation forecast.Type: ApplicationFiled: April 6, 2022Publication date: October 6, 2022Inventors: Colin Graber, Grace Shin-Yee Tsai, Michael David Firman, Gabriel J. Brostow, Alexander Schwing
-
Publication number: 20210327074Abstract: An image processing method includes defining relations between entities of a target of which a motion is to be predicted from an image of a first time point based on a feature vector of the entities, estimating a dynamic interaction between the entities at the first time point based on the defined relations between the entities, predicting a motion of the entities changing at a second time point based on the estimated dynamic interaction, and outputting a result to which the motion predicted at the second time point is applied.Type: ApplicationFiled: April 13, 2021Publication date: October 21, 2021Applicants: The Board of Trustees of the University of Illinois (Urbana, IL), SAMSUNG ELECTRONICS CO., LTD.Inventors: Alexander Schwing, Colin Graber, Raymond Yeh, Jihye KIM, Jaejoon HAN
-
Patent number: 8744172Abstract: A method of performing image retrieval includes training a random forest RF classifier based on low-level features of training images and a high-level feature, using similarity values generated by the RF classifier to determine a subset of the training images that are most similar to one another, and classifying input images for the high-level feature using the RF classifier and the determined subset of images.Type: GrantFiled: June 15, 2011Date of Patent: June 3, 2014Assignee: Siemens AktiengesellschaftInventors: Alexey Tsymbal, Michael Kelm, Maria Jimena Costa, Shaohua Kevin Zhou, Dorin Comaniciu, Yefeng Zheng, Alexander Schwing
-
Patent number: 8363918Abstract: A method and apparatus for detecting multiple anatomical landmarks in a 3D volume. A first anatomical landmark is detected in a 3D volume using marginal space learning (MSL). Locations of remaining anatomical landmarks are estimated in the 3D volume based on the detected first anatomical landmark using a learned geometric model relating the anatomical landmarks. Each of the remaining anatomical landmarks is then detected using MSL in a portion of the 3D volume constrained based on the estimated location of each remaining landmark. This method can be used to detect the anatomical landmarks of the crista galli (CG), tip of the occipital bone (OB), anterior of the corpus callosum (ACC), and posterior of the corpus callosum (PCC) in a brain magnetic resonance imaging (MRI) volume.Type: GrantFiled: October 23, 2009Date of Patent: January 29, 2013Assignee: Siemens AktiengesellschaftInventors: Alexander Schwing, Yefeng Zheng, Martin Harder, Dorin Comaniciu
-
Publication number: 20120321174Abstract: A method of performing image retrieval includes training a random forest RF classifier based on low-level features of training images and a high-level feature, using similarity values generated by the RF classifier to determine a subset of the training images that are most similar to one another, and classifying input images for the high-level feature using the RF classifier and the determined subset of images.Type: ApplicationFiled: June 15, 2011Publication date: December 20, 2012Applicants: Siemens Aktiengesellschaft, Siemens CorporationInventors: Alexey Tsymbal, Michael Kelm, Maria Jimena Costa, Shaohua Kevin Zhou, Dorin Comaniciu, Yefeng Zheng, Alexander Schwing
-
Publication number: 20100119137Abstract: A method and apparatus for detecting multiple anatomical landmarks in a 3D volume. A first anatomical landmark is detected in a 3D volume using marginal space learning (MSL). Locations of remaining anatomical landmarks are estimated in the 3D volume based on the detected first anatomical landmark using a learned geometric model relating the anatomical landmarks. Each of the remaining anatomical landmarks is then detected using MSL in a portion of the 3D volume constrained based on the estimated location of each remaining landmark. This method can be used to detect the anatomical landmarks of the crista galli (CG), tip of the occipital bone (OB), anterior of the corpus callosum (ACC), and posterior of the corpus callosum (PCC) in a brain magnetic resonance imaging (MRI) volume.Type: ApplicationFiled: October 23, 2009Publication date: May 13, 2010Applicants: Siemens Corporation, Siemens AktiengesellschaftInventors: Alexander Schwing, Yefeng Zheng, Martin Harder, Dorin Comaniciu
-
Patent number: 6802375Abstract: A method for carrying out well construction, repair and abandonment operations, the method involves introducing a resin into a well and curing the same to form a seal, plug or connection, wherein the cured resin is expanded to at least the volume occupied by the resin prior to curing (compensating shrinkage), by cooling the well and curing the resin at a reduced temperature and subsequently allowing the well to reach its static bottom hole temperature. A method is also disclosed for analyzing the setting time, elastic properties, shrinkage/expansion, compressibility or coefficient of thermal expansion of thermosetting resins or oil well cements under simulated reservoir pressure and temperature conditions, which involves introducing a sample of a thermosetting resin or oil well cement into a pressure vessel that is equipped to provide the pressure and register the volume change to the analyzer used by this method.Type: GrantFiled: November 21, 2002Date of Patent: October 12, 2004Assignee: Shell Oil CompanyInventors: Martin Gerard Rene Bosma, Erik Kerst Cornelissen, Alexander Schwing
-
Publication number: 20030121662Abstract: This invention relates to a method for carrying out well construction, repair and abandonment operations, which method involves introducing a resin into a well and curing the same to form a seal, plug or connection, wherein the cured resin is expanded to at least the volume occupied by the resin prior to curing (compensating shrinkage), by cooling the well and curing the resin at a reduced temperature and subsequently allowing the well to reach its static bottom hole temperature. This invention also relates to a method for analyzing the setting time, elastic properties, shrinkage/expansion, compressibility or coefficient of thermal expansion of thermosetting resins or oil well cements under simulated reservoir pressure and temperature conditions, which comprises a introducing a sample (7) of a thermosetting resin or oil well cement into a pressure vessel (3) that is equipped with a means(9) to provide the pressure and register the volume change; and to the analyzer used by this method.Type: ApplicationFiled: November 21, 2002Publication date: July 3, 2003Inventors: Martin Gerard Rene Bosma, Erik Kerst Conelissen, Alexander Schwing