Patents by Inventor John G. Apostolopoulos

John G. Apostolopoulos 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: 10354660
    Abstract: An endpoint device receives a sequence of audio frames. The endpoint device determines for each audio frame a respective importance level among possible importance levels ranging from a low importance level to a high importance level based on content in the audio frame indicative of the respective importance level. The endpoint device associates each audio frame with the respective importance level, to produce different subsets of audio frames associated with respective ones of different importance levels. The endpoint device, for each subset of audio frames, applies forward error correction to a fraction of audio frames in the subset of audio frames, wherein the fraction increases as the importance level of the audio frames in the subset increases, and does not apply forward error correction to remaining audio frames in the subset.
    Type: Grant
    Filed: April 28, 2017
    Date of Patent: July 16, 2019
    Assignee: Cisco Technology, Inc.
    Inventors: Ahmed Badr, Ashish J. Khisti, Wai-tian Tan, Michael A. Ramalho, John G. Apostolopoulos
  • Publication number: 20190156487
    Abstract: Presented herein are techniques for automatically generating object segmentation training data. In particular, a segmentation data generation system is configured to obtain training images derived from a scene captured by one or more image capture devices. Each training image is a still image that includes a foreground object and a background. The segmentation data generation system automatically generates a mask of the training image to delineate the object from the background and, based on the mask automatically generates a masked image. The masked image includes only the object present in the training image. The segmentation data generation system composites the masked image with an image of an environmental scene to generate a composite image that includes the masked image and the environmental scene.
    Type: Application
    Filed: January 25, 2019
    Publication date: May 23, 2019
    Inventors: Rob Liston, John G. Apostolopoulos
  • Patent number: 10275683
    Abstract: Presented herein are techniques for assignment of an identity to a group of captured images. A plurality of captured images that each include an image of at least one person are obtained. For each of the plurality of captured images, relational metrics indicating a relationship between the image of the person in a respective captured image and the images of the persons in each of the remaining plurality of captured images is calculated. Based on the relational metrics, a clustering process is performed to generate one or more clusters from the plurality of captured images. Each of the one or more clusters are associated with an identity of an identity database. The one or more clusters may each be associated with an existing identity of the identity database or an additional identity that is not yet present in the identity database.
    Type: Grant
    Filed: January 19, 2017
    Date of Patent: April 30, 2019
    Assignee: Cisco Technology, Inc.
    Inventors: Xiaoqing Zhu, Rob Liston, John G. Apostolopoulos, Wai-tian Tan
  • Patent number: 10242449
    Abstract: Presented herein are techniques for automatically generating object segmentation training data. In particular, a segmentation data generation system is configured to obtain training images derived from a scene captured by one or more image capture devices. Each training image is a still image that includes a foreground object and a background. The segmentation data generation system automatically generates a mask of the training image to delineate the object from the background and, based on the mask automatically generates a masked image. The masked image includes only the object present in the training image. The segmentation data generation system composites the masked image with an image of an environmental scene to generate a composite image that includes the masked image and the environmental scene.
    Type: Grant
    Filed: January 4, 2017
    Date of Patent: March 26, 2019
    Assignee: Cisco Technology, Inc.
    Inventors: Rob Liston, John G. Apostolopoulos
  • Publication number: 20180315431
    Abstract: An endpoint device receives a sequence of audio frames. The endpoint device determines for each audio frame a respective importance level among possible importance levels ranging from a low importance level to a high importance level based on content in the audio frame indicative of the respective importance level. The endpoint device associates each audio frame with the respective importance level, to produce different subsets of audio frames associated with respective ones of different importance levels. The endpoint device, for each subset of audio frames, applies forward error correction to a fraction of audio frames in the subset of audio frames, wherein the fraction increases as the importance level of the audio frames in the subset increases, and does not apply forward error correction to remaining audio frames in the subset.
    Type: Application
    Filed: April 28, 2017
    Publication date: November 1, 2018
    Inventors: Ahmed Badr, Ashish J. Khisti, Wai-tian Tan, Michael A. Ramalho, John G. Apostolopoulos
  • Publication number: 20180299274
    Abstract: Presented herein are techniques for updating detailed maps used to navigate an autonomous vehicle. The techniques include determining that a vehicle has come within a predetermined range of a road side unit, establishing a communication link with the vehicle, receiving, from the vehicle, data sufficient to identify a vehicle type of the vehicle, based on the vehicle type, selecting a map, stored by the road side unit, for the vehicle, sending a query to a neighbor road side unit seeking data to augment the map, in response to the query, receiving the data to augment the map from the neighbor road side unit, updating the map based on the data to augment the map to obtain an updated map, and sending at least a aspects of the updated map to the vehicle.
    Type: Application
    Filed: April 17, 2017
    Publication date: October 18, 2018
    Inventors: Ashok K. Moghe, John G. Apostolopoulos, Avraham A. Poupko
  • Publication number: 20180240011
    Abstract: Presented herein are techniques for training a central/global machine learning model in a distributed machine learning system. In the data sampling techniques, a subset of the data obtained at the local sites is intelligently selected for transfer to the central site for use in training the central machine learning model. In the model merging techniques, distributed local training occurs in each local site and copies of the local machine learning models are sent to the central site for aggregation of learning by merging of the models. As a result, in accordance with the examples presented herein, a central machine learning model can be trained based on various representations/transformations of data seen at the local machine learning models, including sampled selections of data-label pairs, intermediate representation of training errors, or synthetic data-label pairs generated by models trained at various local sites.
    Type: Application
    Filed: February 22, 2017
    Publication date: August 23, 2018
    Inventors: Wai-tian Tan, Rob Liston, John G. Apostolopoulos, Xiaoqing Zhu
  • Publication number: 20180204093
    Abstract: Presented herein are techniques for assignment of an identity to a group of captured images. A plurality of captured images that each include an image of at least one person are obtained. For each of the plurality of captured images, relational metrics indicating a relationship between the image of the person in a respective captured image and the images of the persons in each of the remaining plurality of captured images is calculated. Based on the relational metrics, a clustering process is performed to generate one or more clusters from the plurality of captured images. Each of the one or more clusters are associated with an identity of an identity database. The one or more clusters may each be associated with an existing identity of the identity database or an additional identity that is not yet present in the identity database.
    Type: Application
    Filed: January 19, 2017
    Publication date: July 19, 2018
    Inventors: Xiaoqing Zhu, Rob Liston, John G. Apostolopoulos, Wai-tian Tan
  • Publication number: 20180189951
    Abstract: Presented herein are techniques for automatically generating object segmentation training data. In particular, a segmentation data generation system is configured to obtain training images derived from a scene captured by one or more image capture devices. Each training image is a still image that includes a foreground object and a background. The segmentation data generation system automatically generates a mask of the training image to delineate the object from the background and, based on the mask automatically generates a masked image. The masked image includes only the object present in the training image. The segmentation data generation system composites the masked image with an image of an environmental scene to generate a composite image that includes the masked image and the environmental scene.
    Type: Application
    Filed: January 4, 2017
    Publication date: July 5, 2018
    Inventors: Rob Liston, John G. Apostolopoulos
  • Patent number: 9432620
    Abstract: An example partially transmissive display is provided to output data to a user. The partially transmissive display can include a capture device to receive captured data transmitted through the partially transmissive display, and data generated on and/or reflected from the partially transmissive display. A cross-talk reduction component may be included to receive the captured data and a remote signal comprising displayed content on the partially transmissive display. The cross-talk component may utilize the remote signal and the captured data to reduce cross-talk and output a corrected signal to one or more remote participants.
    Type: Grant
    Filed: February 6, 2015
    Date of Patent: August 30, 2016
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: John G. Apostolopoulos, Ramin Samadani, Mitchell Trott
  • Publication number: 20150156453
    Abstract: An example partially transmissive display is provided to output data to a user. The partially transmissive display can include a capture device to receive captured data transmitted through the partially transmissive display, and data generated on and/or reflected from the partially transmissive display. A cross-talk reduction component may be included to receive the captured data and a remote signal comprising displayed content on the partially transmissive display. The cross-talk component may utilize the remote signal and the captured data to reduce cross-talk and output a corrected signal to one or more remote participants.
    Type: Application
    Filed: February 6, 2015
    Publication date: June 4, 2015
    Inventors: John G. Apostolopoulos, Ramin Samadani, Mitchell Trott
  • Patent number: 8988489
    Abstract: A synchronization relationship determiner comprising an input visual information signal receiver configured to receive an input visual information signal, and a capture signal receiver configured to receive a capture signal generated by a capture device. The synchronization relationship determiner is configured to determine a synchronization relationship between the input visual information signal and the capture signal. The synchronization relationship determination is signal based.
    Type: Grant
    Filed: September 15, 2010
    Date of Patent: March 24, 2015
    Assignee: Hewlett-Packard Development Company, L. P.
    Inventors: John G. Apostolopoulos, Ramin Samadani, Mitchell Trott
  • Patent number: 8878894
    Abstract: A video cross-talk estimator comprising a visual input signal receiver configured to receive a visual input signal, a capture signal receiver configured to receive a capture signal, and a signal based video-cross talk determiner configured to estimate video cross-talk based on at least two frames of the visual input signal. The estimation of the video cross-talk is signal based.
    Type: Grant
    Filed: September 15, 2010
    Date of Patent: November 4, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: John G. Apostolopoulos, Ramin Samadani, Mitchell Trott
  • Patent number: 8832434
    Abstract: Methods for generating data for describing scalable media are disclosed. Data is associated with the scalable media that identifies portions of the scalable media to combine in order to produce media that is scaled to possess a desired scalable attribute without decoding. Portions of the scalable media are encrypted. Data is associated with the portions of the scalable media that identifies protection attributes of the encryption scheme used to encrypt the portions of the scalable media.
    Type: Grant
    Filed: February 13, 2004
    Date of Patent: September 9, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: John G. Apostolopoulos, Susie J. Wee
  • Patent number: 8737219
    Abstract: Methods and systems thereof for streaming media data are described. Media data comprising a plurality of data packets is accessed. Information that quantifies a characteristic of each data packet in the plurality of data packets is also accessed. That information is used to determine an order for sending the data packets over a network.
    Type: Grant
    Filed: January 30, 2004
    Date of Patent: May 27, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: John G. Apostolopoulos, Jakov Cakareski, Susie J. Wee, Wai-tian Tan
  • Patent number: 8692865
    Abstract: A visual-collaborative system including a display screen configured to display images and a camera configured to capture images. The system also includes a video cross-talk reducer configured to estimate video cross-talk that is to be displayed on the display screen and captured by the camera, and reducing the estimated video cross-talk from captured images by the camera. The estimation of the video cross-talk and reduction of the video cross-talk is signal based.
    Type: Grant
    Filed: September 15, 2010
    Date of Patent: April 8, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: John G. Apostolopoulos, Ramin Samadani
  • Patent number: 8693326
    Abstract: Utilizing multiple distortion measures. A first distortion measure for at least one packet is received. A second distortion measure for the at least one packet is received, wherein the second distortion measure is different than the first distortion measure. A processing operation is performed based at least in part on the first distortion measure and the second distortion measure.
    Type: Grant
    Filed: May 3, 2011
    Date of Patent: April 8, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Susie J. Wee, Carri Chan, John G. Apostolopoulos
  • Patent number: 8400490
    Abstract: At least one camera lens captures a field of view comprising at least one object of interest, wherein the at least one camera lens is configured for extending the field of view in at least one direction. The at least one object of interest that is within said field of view is detected. Then, an image of a detected at least one object of interest is warped to fit within the field of view. A plurality of pixels surrounding the image of the detected at least one object of interest within the field of view is cropped such that, based on the warping and the cropping, the detected at least one object appears as centered within the field of view.
    Type: Grant
    Filed: October 30, 2010
    Date of Patent: March 19, 2013
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: John G. Apostolopoulos, Ramin Samadani
  • Patent number: 8391482
    Abstract: A computer readable medium having a data packet stored therein for causing a functional change in the operation of a device is disclosed. In one embodiment, the data packet is comprised of a scalably encoded data portion. In the present embodiment, the data packet further includes a header data portion corresponding to the scalably encoded data portion. The header data portion includes information adapted to be used by a transcoder to transcode the scalably encoded data portion.
    Type: Grant
    Filed: September 16, 2002
    Date of Patent: March 5, 2013
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Susie J. Wee, John G. Apostolopoulos
  • Patent number: 8307024
    Abstract: Assisted peer-to-peer media streaming. A first connection to at least one peer of a peer-to-peer network is initiated for receiving media content from the peer-to-peer network. Responsive to a disruption of delivery of the media content over the first connection from the peer, the media content is received over a second connection with a data source, wherein the data source comprises the media content.
    Type: Grant
    Filed: July 20, 2007
    Date of Patent: November 6, 2012
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Eric E. Setton, John G. Apostolopoulos