Peter L. Venetianer - McLean VA Mark C. Allmen - Morrison CO Paul C. Brewer - Arlington VA Andrew J. Chosak - McLean VA John I. W. Clark - Leesburg VA Matthew F. Frazier - Arlington VA Niels Haering - Arlington VA Tasuki Hirata - Silver Spring MD Caspar Horne - Herndon VA Alan J. Lipton - Falls Church VA William E. Severson - Littleton CO James S. Sfekas - Arlington VA Thomas E. Slowe - Middleburg VA Thomas M. Strat - Oakton VA John F. Tilki - Reston VA Zhong Zhang - Herndon VA
Assignee:
DiamondBack Vision, Inc. - Reston VA
International Classification:
G08B 1300
US Classification:
340541, 348152, 702 85
Abstract:
A method for implementing a video tripwire includes steps of calibrating a sensing device to determine sensing device parameters for use by the system; initializing the system, including entering at least one virtual tripwire; obtaining data from the sensing device; analyzing the data obtained from the sensing device to determine if the at least one virtual tripwire has been crossed; and triggering a response to a virtual tripwire crossing.
Scene Model Generation From Video For Use In Video Processing
Mark Allmen - Morrison CO Chris Debrunner - Conifer CO William Severson - Littleton CO Thomas M. Strat - Oakton VA
Assignee:
ObjectVideo, Inc. - Reston VA
International Classification:
H04N 712
US Classification:
37524008, 382154
Abstract:
A method of generating and utilizing a scene model from a sequence of video frames produces a three-dimensional scene model, useful for video processing. The method separates foreground and background data. It uses an estimate of relative motion of an observer to project each frame onto a coordinate system of the three-dimensional scene model. It then merges the background data of a given frame into the scene model.
Thomas E. Slowe - Middlleburg VA, US Paul C. Brewer - Arlington VA, US Robert J. Douglass - Oak Hill VA, US Thomas M. Strat - McLean VA, US Thomas J. Burns - McLean VA, US Andrew J. Chosak - McLean VA, US
Assignee:
ObjectVideo, Inc. - Reston VA
International Classification:
H04N 7/18
US Classification:
37524016, 347154, 347155, 37524017, 37524026
Abstract:
A decomposed original video sequence includes one or more original camera-motion layers and zero or more original fixed-frame layers decomposed from an original video sequence. The decomposed original video sequence is edited by editing at least one of the original camera-motion layers to obtain modified camera-motion layers such that each frame of a composite modified video sequence composed from the modified camera-motion layers and the original fixed-frame layers is obtained without editing each frame of said original video sequence. The editing comprises performing an edge operation to one of said original camera-motion layers.
Video Segmentation Using Statistical Pixel Modeling
Alan J. Lipton - Herndon VA, US Mark C. Allmen - Morrison CO, US Niels Haering - Reston VA, US William E. Severson - Littleton CO, US Thomas M. Strat - Oakton VA, US
Assignee:
ObjectVideo, Inc. - Reston VA
International Classification:
G06K 9/32 H04N 7/18 G06K 9/00
US Classification:
382294
Abstract:
A method for segmenting video data into foreground and background portions utilizes statistical modeling of the pixels. A statistical model of the background is built for each pixel, and each pixel in an incoming video frame is compared with the background statistical model for that pixel. Pixels are determined to be foreground or background based on the comparisons. The method for segmenting video data may be further incorporated into a method for implementing an intelligent video surveillance system.
Bit-Rate Allocation System For Object-Based Video Encoding
Mark Allmen - Morrison CO, US Zhong Zhang - Herndon VA, US Thomas M. Strat - Oakton VA, US
Assignee:
Objectvideo, Inc. - Reston VA
International Classification:
H04N 7/18
US Classification:
37524008, 382251
Abstract:
A video sequence is encoded, where the video sequence includes a background composite and foreground regions. The video sequence is encoded based on balancing bits per pixel for the background composite with bits per pixel for the foreground regions.
Alan J. Lipton - Austin TX, US John I. W. Clark - Flamborough, CA Zhong Zhang - Great Falls VA, US Peter L. Venetianer - McLean VA, US Thomas Strat - Oakton VA, US Mark Allmen - Morrison CO, US William Severson - Centennial CO, US Niels Haering - Reston VA, US Andrew Chosak - Arlington VA, US Matthew Frazier - New York NY, US James Sfekas - Seattle WA, US Tasuki Hirata - Cambridge MA, US
Assignee:
ObjectVideo, Inc. - Reston VA
International Classification:
H04N 9/47
US Classification:
348143, 382103, 382115
Abstract:
A video surveillance system is set up, calibrated, tasked, and operated. The system extracts video primitives and extracts event occurrences from the video primitives using event discriminators. The extracted video primitives and event occurrences may be used to create and define additional video analytic rules. The system can undertake a response, such as an alarm, based on extracted event occurrences.
Video Segmentation Using Statistical Pixel Modeling
Alan Lipton - Falls Church VA, US Mark Allmen - Morrison CO, US Niels Haering - Arlington VA, US William Severson - Littleton CO, US Thomas Strat - Oakton VA, US
International Classification:
G06K009/00
US Classification:
382/173000
Abstract:
A method for segmenting video data into foreground and background portions utilizes statistical modeling of the pixels. A statistical model of the background is built for each pixel, and each pixel in an incoming video frame is compared with the background statistical model for that pixel. Pixels are determined to be foreground or background based on the comparisons.
Extraction Of Textual And Graphic Overlays From Video
Huiping Li - Silver Spring MD, US Thomas Strat - Oakton VA, US
International Classification:
G09G005/00
US Classification:
345/636000
Abstract:
A method for extracting textual and graphical overlays from video sequences involves steps of detecting a potential overlay in a video sequence and then verifying that the potential overlay is an actual overlay. Detection of textual overlays involves wavelet decomposition and neural network processing, while detection of graphical overlays involves template matching. Verification of textual and graphical overlays involves spatial and/or temporal verification.