Patents by Inventor Dennis J. Yelton
Dennis J. Yelton 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: 11536843Abstract: Jitter is removed from point cloud data of a target by fitting the data to 3-D models of possible targets. The point cloud data is de-jittered as a group by shifting the point cloud data in its coordinate system until a minimum fit error is observed between the shifted data and a 3-D model under analysis. Different 3-D models may be evaluated in succession until a 3-D model is identified that has the least fit error. The 3-D model with the least fit error most likely represents the identity of the target.Type: GrantFiled: February 8, 2020Date of Patent: December 27, 2022Assignee: The Boeing CompanyInventor: Dennis J. Yelton
-
Patent number: 11236990Abstract: Jitter is removed from point cloud data by processing different groups of data points in the point cloud data in succession to minimize the entropy of the point cloud data. Each group in the point cloud data is generated at either different points in time or from detecting different pulses of reflected laser light from a target. The data points in a selected group are repetitively shifted en masse in the coordinate system of the point cloud data and the entropy of the point cloud data is re-calculated until subsequent shifts of the data points in the selected group does not further reduce the entropy. The remaining groups are subsequently processed in a similar fashion until the entropy of the point cloud data reaches a minimum.Type: GrantFiled: February 8, 2020Date of Patent: February 1, 2022Assignee: The Boeing CompanyInventor: Dennis J. Yelton
-
Publication number: 20210247517Abstract: Jitter is removed from point cloud data of a target by fitting the data to 3-D models of possible targets. The point cloud data is de-jittered as a group by shifting the point cloud data in its coordinate system until a minimum fit error is observed between the shifted data and a 3-D model under analysis. Different 3-D models may be evaluated in succession until a 3-D model is identified that has the least fit error. The 3-D model with the least fit error most likely represents the identity of the target.Type: ApplicationFiled: February 8, 2020Publication date: August 12, 2021Inventor: Dennis J. Yelton
-
Publication number: 20210247179Abstract: Jitter is removed from point cloud data by processing different groups of data points in the point cloud data in succession to minimize the entropy of the point cloud data. Each group in the point cloud data is generated at either different points in time or from detecting different pulses of reflected laser light from a target. The data points in a selected group are repetitively shifted en masse in the coordinate system of the point cloud data and the entropy of the point cloud data is re-calculated until subsequent shifts of the data points in the selected group does not further reduce the entropy. The remaining groups are subsequently processed in a similar fashion until the entropy of the point cloud data reaches a minimum.Type: ApplicationFiled: February 8, 2020Publication date: August 12, 2021Inventor: Dennis J. Yelton
-
Patent number: 10453187Abstract: A method of suppressing background clutter in video imagery of a scene including a foreground target and background clutter includes applying successive images of the video imagery to a clutter suppression process, thereby producing video imagery of a derived scene in which the background clutter is suppressed. This process includes processing the current image to remove a fixed pattern noise associated with the camera, and spatially re-registering the current image to a fixed geolocation or known clutter pattern of the scene in a reference image of the successive images. The process also includes subjecting independent copies of the current image to two infinite impulse response filters having different time constants to produce filtered, time-delayed images, and differencing the filtered images to reduce the background clutter, thereby producing a clutter-suppressed version of the current image in which the background clutter is suppressed with respect to the foreground target.Type: GrantFiled: July 21, 2017Date of Patent: October 22, 2019Assignee: THE BOEING COMPANYInventors: Scott M. Peterson, Dennis J. Yelton
-
Patent number: 10438326Abstract: A method of suppressing clutter in video imagery includes receiving video imagery from a focal plane array, and decomposing the video imagery into independently-moving coordinate transformations corresponding to clutter patterns that are subimages of the video imagery. The method also includes removing the subimages from an image of the video imagery to produce a clutter-suppressed version of the image, and rendering the clutter-suppressed version of the image. Removing the subimages from the image includes generating respective zeroth-order corrections for the subimages, and subtracting the respective zeroth-order corrections from the image. And removing the subimages includes recursively generating respective first-order corrections for the subimages from the respective zeroth-order corrections, and subtracting the respective first-order corrections from the image.Type: GrantFiled: July 21, 2017Date of Patent: October 8, 2019Assignee: THE BOEING COMPANYInventor: Dennis J. Yelton
-
Publication number: 20190026868Abstract: A method of suppressing clutter in video imagery includes receiving video imagery from a focal plane array, and decomposing the video imagery into independently-moving coordinate transformations corresponding to clutter patterns that are subimages of the video imagery. The method also includes removing the subimages from an image of the video imagery to produce a clutter-suppressed version of the image, and rendering the clutter-suppressed version of the image. Removing the subimages from the image includes generating respective zeroth-order corrections for the subimages, and subtracting the respective zeroth-order corrections from the image. And removing the subimages includes recursively generating respective first-order corrections for the subimages from the respective zeroth-order corrections, and subtracting the respective first-order corrections from the image.Type: ApplicationFiled: July 21, 2017Publication date: January 24, 2019Inventor: Dennis J. Yelton
-
Publication number: 20190026867Abstract: A method of suppressing background clutter in video imagery of a scene including a foreground target and background clutter includes applying successive images of the video imagery to a clutter suppression process, thereby producing video imagery of a derived scene in which the background clutter is suppressed. This process includes processing the current image to remove a fixed pattern noise associated with the camera, and spatially re-registering the current image to a fixed geolocation or known clutter pattern of the scene in a reference image of the successive images. The process also includes subjecting independent copies of the current image to two infinite impulse response filters having different time constants to produce filtered, time-delayed images, and differencing the filtered images to reduce the background clutter, thereby producing a clutter-suppressed version of the current image in which the background clutter is suppressed with respect to the foreground target.Type: ApplicationFiled: July 21, 2017Publication date: January 24, 2019Inventors: Scott M. Peterson, Dennis J. Yelton
-
Patent number: 7876258Abstract: A collision sense and avoidance system and method and an aircraft, such as an Unmanned Air Vehicle (UAV) and/or Remotely Piloted Vehicle (RPV), including the collision sense and avoidance system. The collision sense and avoidance system includes an image interrogator identifies potential collision threats to the aircraft and provides maneuvers to avoid any identified threat. Motion sensors (e.g., imaging and/or infrared sensors) provide image frames of the surroundings to a clutter suppression and target detection unit that detects local targets moving in the frames. A Line Of Sight (LOS), multi-target tracking unit, tracks detected local targets and maintains a track history in LOS coordinates for each detected local target. A threat assessment unit determines whether any tracked local target poses a collision threat. An avoidance maneuver unit provides flight control and guidance with a maneuver to avoid any identified said collision threat.Type: GrantFiled: March 13, 2006Date of Patent: January 25, 2011Assignee: The Boeing CompanyInventors: Michael R. Abraham, Christian C. Witt, Dennis J. Yelton, John N. Sanders-Reed, Christopher J. Musial
-
Patent number: 7512258Abstract: Method and system for passively detecting wires from a mobile transport system is provided. The method includes, pre-processing a digital image taken from a digital camera of the transport system, wherein the pre-processing is performed by a pre-processing module to reduce non-wire like clutter from the digital image; identifying pixels that can be classified as wire like by using a segment finder module on the digital image that has been pre-processed by the pre-processing module; and linking the identified pixels to determine if a wire like structure is present, wherein a linker module links the pixels that can be classified as wire like, to generate a wire overlay.Type: GrantFiled: July 19, 2005Date of Patent: March 31, 2009Assignee: The Boeing CompanyInventors: Dennis J. Yelton, Robert L. Wright
-
Patent number: 7466243Abstract: A hardware system for passively detecting wires from a mobile transportation system is provided. The hardware system includes a main processor in the hardware system that uses plural commands to manage a preprocessor module and a linker module, wherein the pre-processing module pre-processes a digital image taken from a digital camera of the transport system and reduces non-wire like clutter from the digital image and identifies pixels that can be classified as wire like; and the linker module links the identified pixels to determine if a wire like structure is present and a binary output from the linker module is sent to an output select module that allows a user to select a video output.Type: GrantFiled: October 13, 2005Date of Patent: December 16, 2008Assignee: The Boeing CompanyInventors: Christian C. Witt, Dennis J. Yelton, James C. Hansen, Christopher J. Musial
-
Patent number: 7148861Abstract: The systems and methods of the present invention provide an image processor that displays enhanced vision images based on a plurality images sources. The image processor comprises both serial and parallel processors. The serial processor performs low data volume calculations needed by the parallel processor for image display. The serial processor precalculates transformations needed to convert source data from each source to a primary coordinate system. The parallel processor uses these transforms and correlates source data with the display on a pixel by pixel basis as each frame from the sources is received to thereby provide display data with decreased latency. The image processor reduces parallax effect and is capable of: 1) stitching images of different fields of view to provide a mosaic image; 2) fusing images taken of the same field of view by different types of sources into a fused image; and 3) correcting anomalies in the displayed image.Type: GrantFiled: March 1, 2003Date of Patent: December 12, 2006Assignee: The Boeing CompanyInventors: Dennis J. Yelton, Kenneth L. Bernier
-
Publication number: 20040169617Abstract: The systems and methods of the present invention provide an image processor that displays enhanced vision images based on a plurality images sources. The image processor comprises both serial and parallel processors. The serial processor performs low data volume calculations needed by the parallel processor for image display. The serial processor precalculates transformations needed to convert source data from each source to a primary coordinate system. The parallel processor uses these transforms and correlates source data with the display on a pixel by pixel basis as each frame from the sources is received to thereby provide display data with decreased latency. The image processor reduces parallax effect and is capable of: 1) stitching images of different fields of view to provide a mosaic image; 2) fusing images taken of the same field of view by different types of sources into a fused image; and 3) correcting anomalies in the displayed image.Type: ApplicationFiled: March 1, 2003Publication date: September 2, 2004Applicant: The Boeing CompanyInventors: Dennis J. Yelton, Kenneth L. Bernier