AUTOMATIC EXTRACTION OF SECONDARY VIDEO STREAMS

• US 20170132471A1
• Filed: 11/22/2016
• Published: 05/11/2017
• Est. Priority Date: 03/28/2006
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Fortress Corporation
• Inventors: Scanlon, W. Andrew, Chosak, Andrew J., Cutting, Robert A., Lipton, Alan J., Myers, Gary W., Clark, John I.W.
• Granted Patent: US 10,614,311 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04N 19/167 Position within a video image, e.g. region of interest [ROI]
• CPC Class Codes: H04N 19/17 the unit being an image region, e.g. an object
• CPC Class Codes: H04N 19/20 using video object coding
• CPC Class Codes: H04N 5/262 Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

The automatic generation of one or more secondary video streams based on an input primary video stream may use analytics performed on the video to provide information on targets, events, and/or areas of interest to permit the one or more secondary video streams to concentrate on one or more targets, events and/or areas of interest.

Claims

1-67. -67. (canceled)

68. A computer-implemented method of automatically generating a secondary video stream based on an incoming primary video stream, comprising:

performing video analytics on a target in the primary video stream to generate an analysis result by a hardware processor, the analysis result including information relating to a classification of the target;

automatically extracting the secondary video stream, the secondary video stream including the target;

based on the classification of the target, determining a best-shot of the target; and

bounding the secondary video stream based on the best-shot of the target.

69. The method of claim 68, further comprising performing video analytics by down-sampling a higher resolution primary video stream to obtain a lower resolution primary video stream, and performing video analytics on the lower resolution primary video stream.

70. The method of claim 69, wherein the secondary video stream is extracted from the higher resolution primary video stream.

71. The method of claim 68, wherein the classification of the target is a human.

72. The method of claim 71, wherein the best-shot is a face of the human.

73. The method of claim 68, wherein the classification of the target is a vehicle.

74. The method of claim 73, wherein the best-shot is a license plate of the vehicle.

75. The method of claim 68, wherein a field of view of the first secondary stream is smaller than a field of view of the primary video stream.

76. The method of claim 68, wherein determination of the best-shot is further based on an orientation of the target.

77. The method of claim 68, wherein determination of the best shot is further based on a velocity vector of the target.

78. A system to automatically generate a secondary video stream based on an incoming primary video stream, comprising:

a computer configured to;

perform video analytics on a target in the primary video stream to generate an analysis result by a hardware processor, the analysis result including information relating to a classification of the target;

automatically extract the secondary video stream, the secondary video stream including the target; and

based on the classification of the target, determine a best-shot of the target, and bound the secondary video stream on a user interface based on the best-shot of the target.

79. The system of claim 78, wherein the computer is further configured to perform video analytics by down-sampling a higher resolution primary video stream to obtain a lower resolution primary video stream, and the computer is further configured to perform video analytics on the lower resolution primary video stream.

80. The system of claim 78, wherein the classification of the target is a human.

81. The system of claim 80, wherein the best-shot is a face of the human.

82. The system of claim 78, wherein the classification of the target is a vehicle.

83. The system of claim 82, wherein the best-shot is a license plate of the vehicle.

84. The system of claim 78, wherein a field of view of the first secondary stream is smaller than a field of view of the primary video stream.

85. The system of claim 78, wherein the computer is further configured to determine the best-shot based on the orientation of the target.

86. The system of claim 78, wherein the computer is further configured to determine the best shot based on a velocity vector of the target.

87. A computer-implemented method of automatically generating a secondary video stream and a tertiary video stream based on an incoming primary video stream, comprising:

performing video analytics on a target in the primary video stream to generate an analysis result by a hardware processor, the analysis result including information relating to a classification of the target;

automatically extracting the secondary video stream, the secondary video stream including the target;

based on the classification of the target, determining a best-shot of the target; and

automatically extracting the tertiary video stream from the secondary video stream, the tertiary video stream including the best-shot of the target.