×

Methods and apparatus for filtering video packets for large-scale video stream monitoring

  • US 7,545,978 B2
  • Filed: 07/01/2005
  • Issued: 06/09/2009
  • Est. Priority Date: 07/01/2005
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method of filtering video packets for video stream monitoring, comprising executing the following steps using a computer system:

  • receiving a video packet of a video stream;

    extracting one or more features from a specified frame of the video packet via one or more histograms and frequency domain coefficients of the specified frame, wherein the one or more features comprise compressed-domain slice features, further wherein the step of extracting one or more features further comprises the steps of parsing the video packet to attain a specified frame, calculating a histogram for each of one or more slices of the specified frame using frequency domain coefficients of the specified frame, and creating a feature vector of the specified frame based on the one or more calculated histograms, wherein the step of calculating a histogram further comprises the steps of determining frequency domain coefficients of the specified frame, partitioning the specified frame into one or more slices, and calculating a histogram of the frequency domain coefficients for each of the one or more slices of the specified frame, and truncating selected frequency domain coefficients in each of the one or more slices of the specified frame, the step of calculating a histogram of the frequency domain coefficients further comprising the step of using a DC coefficient and one or more AC coefficients of discrete cosine transformation coefficients on one or more color planes, the one or more AC coefficients comprising two lowest frequency AC coefficients, further wherein the step of determining frequency domain coefficients comprises the step of mapping a data compression coding scheme to frequency domain coefficients of the specified frame, the data compression coding scheme comprising variable length codes;

    implementing a plurality of concept detectors on the one or more features creating one or more confidence values by multicasting each of the one or more features to the plurality of concept detectors, wherein the step of implementing the plurality of concept detectors further comprises the step of matching user interests with a confidence output of semantic model vectors; and

    transmitting the one or more confidence values to a display module for filtering of video packets, wherein the step of transmitting the one or more confidence values further comprises storing the one or more confidence values as metadata, and transmitting the metadata to the display module for filtering of video packets.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×