Patents by Inventor Nikhil Gagvani
Nikhil Gagvani 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).
-
Publication number: 20220312021Abstract: A method and apparatus for encoding surveillance video where one or more regions of interest are identified and the encoding parameter values associated with those regions are specified in accordance with intermediate outputs of a video analytics process. Such an analytics-modulated video compression approach allows the coding process to adapt dynamically based on the content of the surveillance images. In this manner, the fidelity of the region of interest is increased relative to that of a background region such that the coding efficiency is improved, including instances when no target objects appear in the scene. Better compression results can be achieved by assigning different coding priority levels to different types of detected objects.Type: ApplicationFiled: November 5, 2021Publication date: September 29, 2022Applicant: CheckVideo LLCInventors: Lai-Tee Cheok, Nikhil Gagvani
-
Patent number: 11172209Abstract: A method and apparatus for encoding surveillance video where one or more regions of interest are identified and the encoding parameter values associated with those regions are specified in accordance with intermediate outputs of a video analytics process. Such an analytics-modulated video compression approach allows the coding process to adapt dynamically based on the content of the surveillance images. In this manner, the fidelity of the region of interest is increased relative to that of a background region such that the coding efficiency is improved, including instances when no target objects appear in the scene. Better compression results can be achieved by assigning different coding priority levels to different types of detected objects.Type: GrantFiled: December 15, 2017Date of Patent: November 9, 2021Assignee: CheckVideo LLCInventors: Lai-Tee Cheok, Nikhil Gagvani
-
Publication number: 20190066472Abstract: A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.Type: ApplicationFiled: March 16, 2018Publication date: February 28, 2019Applicant: CheckVideo LLCInventors: Nikhil GAGVANI, Philip Allen ROBERTSON
-
Publication number: 20180139456Abstract: A method and apparatus for encoding surveillance video where one or more regions of interest are identified and the encoding parameter values associated with those regions are specified in accordance with intermediate outputs of a video analytics process. Such an analytics-modulated video compression approach allows the coding process to adapt dynamically based on the content of the surveillance images. In this manner, the fidelity of the region of interest is increased relative to that of a background region such that the coding efficiency is improved, including instances when no target objects appear in the scene. Better compression results can be achieved by assigning different coding priority levels to different types of detected objects.Type: ApplicationFiled: December 15, 2017Publication date: May 17, 2018Applicant: CheckVideo LLCInventors: Lai-Tee CHEOK, Nikhil GAGVANI
-
Patent number: 9922514Abstract: A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.Type: GrantFiled: December 4, 2015Date of Patent: March 20, 2018Assignee: CheckVideo LLPInventors: Nikhil Gagvani, Philip Allen Robertson
-
Publication number: 20160337647Abstract: A method and apparatus for encoding surveillance video where one or more regions of interest are identified and the encoding parameter values associated with those regions are specified in accordance with intermediate outputs of a video analytics process. Such an analytics-modulated video compression approach allows the coding process to adapt dynamically based on the content of the surveillance images. In this manner, the fidelity of the region of interest is increased relative to that of a background region such that the coding efficiency is improved, including instances when no target objects appear in the scene. Better compression results can be achieved by assigning different coding priority levels to different types of detected objects.Type: ApplicationFiled: December 11, 2015Publication date: November 17, 2016Applicant: CheckVideo LLCInventors: Lai-Tee CHEOK, Nikhil GAGVANI
-
Publication number: 20160321889Abstract: A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.Type: ApplicationFiled: December 4, 2015Publication date: November 3, 2016Applicant: CheckVideo LLCInventors: Nikhil GAGVANI, Philip Allen ROBERTSON
-
Patent number: 9230175Abstract: In some embodiments, a non-transitory processor-readable medium stores code representing instructions to cause a processor to smooth a current image of a scene to produce a smoothed image and subtract pixel values of a background image of the scene from corresponding pixel values of the smoothed image to produce an altitude difference image. Pixel values of the altitude difference image are weighted to produce a weighted difference image. The weighted difference image is convolved to produce a convoluted difference image. A threshold is applied to each pixel of the convoluted difference image to produce a thresholded difference image. Pixels having a value less than the threshold are removed from the thresholded difference image and classified as background pixels. Foreground pixels are determined based on the thresholded difference image.Type: GrantFiled: October 28, 2013Date of Patent: January 5, 2016Assignee: CheckVideo LLCInventors: Nikhil Gagvani, Alexei Gritai
-
Patent number: 9215467Abstract: A method and apparatus for encoding surveillance video where one or more regions of interest are identified and the encoding parameter values associated with those regions are specified in accordance with intermediate outputs of a video analytics process. Such an analytics-modulated video compression approach allows the coding process to adapt dynamically based on the content of the surveillance images. In this manner, the fidelity of the region of interest is increased relative to that of a background region such that the coding efficiency is improved, including instances when no target objects appear in the scene. Better compression results can be achieved by assigning different coding priority levels to different types of detected objects.Type: GrantFiled: November 17, 2009Date of Patent: December 15, 2015Assignee: CheckVideo LLCInventors: Lai-Tee Cheok, Nikhil Gagvani
-
Patent number: 9208667Abstract: A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.Type: GrantFiled: August 6, 2014Date of Patent: December 8, 2015Assignee: CheckVideo LLCInventors: Nikhil Gagvani, Philip Allen Robertson
-
Publication number: 20150098613Abstract: A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.Type: ApplicationFiled: August 6, 2014Publication date: April 9, 2015Applicant: CHECKVIDEO LLCInventors: Nikhil GAGVANI, Philip Allen ROBERTSON
-
Patent number: 8804997Abstract: A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.Type: GrantFiled: July 16, 2008Date of Patent: August 12, 2014Assignee: CheckVideo LLCInventors: Nikhil Gagvani, Philip Allen Robertson
-
Publication number: 20140198257Abstract: In some embodiments, a non-transitory processor-readable medium stores code representing instructions to cause a processor to smooth a current image of a scene to produce a smoothed image and subtract pixel values of a background image of the scene from corresponding pixel values of the smoothed image to produce an altitude difference image. Pixel values of the altitude difference image are weighted to produce a weighted difference image. The weighted difference image is convolved to produce a convoluted difference image. A threshold is applied to each pixel of the convoluted difference image to produce a thresholded difference image. Pixels having a value less than the threshold are removed from the thresholded difference image and classified as background pixels. Foreground pixels are determined based on the thresholded difference image.Type: ApplicationFiled: October 28, 2013Publication date: July 17, 2014Applicant: CheckVideo LLCInventors: Nikhil Gagvani, Alexei Gritai
-
Patent number: 8692885Abstract: A system and method for preparing for distribution to, distributing to and/or use by one or more devices broadband data associated with intelligence information garnered from an aerial vehicle (“AV”): The method may include obtaining from sensors coupled to the AV video depicting an area of surveillance, obtaining metadata associated with the video, aligning, temporally, the video and metadata, using reference information to align, spatially, the video and metadata, forming for distribution to the at least one device enhanced metadata as a function of the video, metadata and reference information, wherein the enhanced metadata is operable to enable displaying at the devices at least a portion of the video, whereby after receiving a distribution of the enhanced metadata, the devices are operable to display such portion of the video.Type: GrantFiled: February 21, 2006Date of Patent: April 8, 2014Assignee: SRI InternationalInventors: Mark Alan Sartor, Philip Wayne Miller, Arthur Robert Pope, Peter L. Demers, Nikhil Gagvani, Vincent Paragano, Daniel Clement Williams
-
Patent number: 8571261Abstract: In some embodiments, a non-transitory processor-readable medium stores code representing instructions to cause a processor to smooth a current image of a scene to produce a smoothed image and subtract pixel values of a background image of the scene from corresponding pixel values of the smoothed image to produce an altitude difference image. Pixel values of the altitude difference image are weighted to produce a weighted difference image. The weighted difference image is convolved to produce a convoluted difference image. A threshold is applied to each pixel of the convoluted difference image to produce a thresholded difference image. Pixels having a value less than the threshold are removed from the thresholded difference image and classified as background pixels. Foreground pixels are determined based on the thresholded difference image.Type: GrantFiled: April 22, 2010Date of Patent: October 29, 2013Assignee: CheckVideo LLCInventors: Nikhil Gagvani, Alexei Gritai
-
Publication number: 20130121527Abstract: A method for remote event notification over a data network is disclosed. The method includes receiving video data from any source, analyzing the video data with reference to a profile to select a segment of interest associated with an event of significance, encoding the segment of interest, and sending to a user a representation of the segment of interest for display at a user display device. A further method for sharing video data based on content according to a user-defined profile over a data network is disclosed. The method includes receiving the video data, analyzing the video data for relevant content according to the profile, consulting a profile to determine a treatment of the relevant content, and sending data representative of the relevant content according to the treatment.Type: ApplicationFiled: June 15, 2012Publication date: May 16, 2013Applicant: Cernium CorporationInventors: Craig A. Chambers, Nikhil Gagvani, Philip Robertson, Helen E. Shepro
-
Patent number: 8204273Abstract: A method for remote event notification over a data network is disclosed. The method includes receiving video data from any source, analyzing the video data with reference to a profile to select a segment of interest associated with an event of significance, encoding the segment of interest, and sending to a user a representation of the segment of interest for display at a user display device. A further method for sharing video data based on content according to a user-defined profile over a data network is disclosed. The method includes receiving the video data, analyzing the video data for relevant content according to the profile, consulting a profile to determine a treatment of the relevant content, and sending data representative of the relevant content according to the treatment.Type: GrantFiled: November 25, 2008Date of Patent: June 19, 2012Assignee: Cernium CorporationInventors: Craig A. Chambers, Nikhil Gagvani, Philip Robertson, Helen E. Shepro
-
Publication number: 20110234829Abstract: In some embodiments, a non-transitory processor-readable medium stores code representing instructions to cause a processor to receive a first image of a visual pattern from a sensor. The visual pattern encodes at least one compression parameter, at least one capture parameter or at least one video analytic parameter to be applied to the sensor. The code represents instructions to cause the processor to apply the at least one compression parameter, the at least one capture parameter or the at least one video analytic parameter to the sensor. The code further represents instructions to cause the processor to receive a second image from the sensor. The sensor captures or analyzes the second image according to the at least one compression parameter, the at least one capture parameter or the at least one video analytic parameter.Type: ApplicationFiled: October 6, 2010Publication date: September 29, 2011Inventors: Nikhil Gagvani, Steven Bryant
-
Publication number: 20100290710Abstract: In some embodiments, a non-transitory processor-readable medium stores code representing instructions to cause a processor to smooth a current image of a scene to produce a smoothed image and subtract pixel values of a background image of the scene from corresponding pixel values of the smoothed image to produce an altitude difference image. Pixel values of the altitude difference image are weighted to produce a weighted difference image. The weighted difference image is convolved to produce a convoluted difference image. A threshold is applied to each pixel of the convoluted difference image to produce a thresholded difference image. Pixels having a value less than the threshold are removed from the thresholded difference image and classified as background pixels. Foreground pixels are determined based on the thresholded difference image.Type: ApplicationFiled: April 22, 2010Publication date: November 18, 2010Inventors: Nikhil Gagvani, Alexei Gritai
-
Publication number: 20100124274Abstract: A method and apparatus for encoding surveillance video where one or more regions of interest are identified and the encoding parameter values associated with those regions are specified in accordance with intermediate outputs of a video analytics process. Such an analytics-modulated video compression approach allows the coding process to adapt dynamically based on the content of the surveillance images. In this manner, the fidelity of the region of interest is increased relative to that of a background region such that the coding efficiency is improved, including instances when no target objects appear in the scene. Better compression results can be achieved by assigning different coding priority levels to different types of detected objects.Type: ApplicationFiled: November 17, 2009Publication date: May 20, 2010Inventors: Lai-Tee Cheok, Nikhil Gagvani