Video surveillance system employing video primitives

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 system can undertake a response, such as an alarm, based on extracted event occurrences.

1 . A computer-readable medium comprising software for a video surveillance system, comprising code segments for operating the video surveillance system based on video primitives.  
   
   
       2 . A computer-readable medium as in  claim 1 , wherein the code segments for operating the video surveillance system comprise: 
 code segments for extracting video primitives; and    code segments for extracting event occurrences from the video primitives.    
   
   
       3 . A computer-readable medium as in  claim 2 , wherein the event occurrences are extracted using event discriminators.  
   
   
       4 . A computer-readable medium as in  claim 2 , further comprising code segments for archiving the extracted video primitives.  
   
   
       5 . A computer-readable medium as in  claim 2 , further comprising code segments for undertaking a response based on extracted event occurrences.  
   
   
       6 . A computer-readable medium as in  claim 5 , wherein the response comprises initiating another sensor system.  
   
   
       7 . A computer-readable medium as in  claim 1 , further comprising code segments for calibrating the video surveillance system.  
   
   
       8 . A computer-readable medium as in  claim 7 , wherein the code segments for calibrating comprise code segments for self-calibrating the video surveillance system.  
   
   
       9 . A computer-readable medium as in  claim 8 , wherein the code segments for self-calibrating comprise: 
 code segments for detecting as least one object in a source video; and    code segments for tracking the object.    
   
   
       10 . A computer-readable medium as in  claim 9 , wherein the code segments for detecting at least one object comprise: 
 code segments for detecting at least one object via motion of the object; and    code segments for detecting at least one object via change in a background model.    
   
   
       11 . A computer-readable medium as in  claim 7 , wherein the code segments for self-calibrating comprise: 
 code segments for identifying trackable areas; and    code segments for identifying typical sizes of typical objects.    
   
   
       12 . A computer-readable medium as in  claim 7 , wherein the code segments for calibrating comprise: 
 code segments for manual calibration;    code segments for semi-automatic calibration; and    code segments for automatic calibration.    
   
   
       13 . A computer-readable medium as in  claim 1 , further comprising code segments for tasking the video surveillance system with event discriminators.  
   
   
       14 . A computer-readable medium as in  claim 13 , wherein the code segments for tasking comprise code segments for identifying at least one object.  
   
   
       15 . A computer-readable medium as in  claim 13 , wherein the code segments for tasking comprise code segments for identifying at least one spatial area.  
   
   
       16 . A computer-readable medium as in  claim 13 , wherein the code segments for tasking comprise code segments for identifying at least one temporal attribute.  
   
   
       17 . A computer-readable medium as in  claim 13 , wherein the code segments for tasking identify at least one interaction.  
   
   
       18 . A computer-readable medium as in  claim 13 , wherein the code segments for tasking identify at least one alarm.  
   
   
       19 . A computer-readable medium as in  claim 1 , wherein the video primitives are from at least one of a video sensor and another sensor.  
   
   
       20 . A computer-readable medium as in  claim 1 , wherein the video primitives are retrieved from an archive of video primitives.  
   
   
       21 . A computer system comprising the computer-readable medium of  claim 1 .  
   
   
       22 . A computer-readable medium comprising software for a video surveillance system, comprising: 
 code segments for accessing archived video primitives; and    code segments for extracting event occurrences from accessed archived video primitives.    
   
   
       23 . A computer-readable medium as in  claim 22 , wherein the event occurrences are extracted using event discriminators.  
   
   
       24 . A computer-readable medium as in  claim 22 , further comprising code segments for undertaking a response based on extracted event occurrences.  
   
   
       25 . A method comprising the step of operating a video surveillance system based on video primitives.  
   
   
       26 . A method comprising the steps of: 
 accessing archived video primitives; and    extracting event occurrences from accessed video primitives.    
   
   
       27 . An apparatus for video surveillance, wherein the apparatus is adapted to perform video surveillance based on video primitives.  
   
   
       28 . The apparatus of  claim 27 , wherein the apparatus comprises application-specific hardware to emulate a computer and/or software.