Method and apparatus for visual background subtraction with one or more preprocessing modules

Abstract

Methods and apparatus are provided for visual background subtraction using one or more preprocessing modules. One or more effects are detected in a received image signal and one or more blocks are selectively enabled to preprocess the image signal to compensate for the detected one or more effects. Visual analysis is then performed on the preprocessed signal using background subtraction. A spatially-variant temporal smoothing of the image signal is also disclosed. The spatially-variant temporal smoothing can be achieved by the mixing of a new intensity value with a previous intensity time-average as determined by a weighting matrix. The mixing can be influenced by a dynamic bias term that is a real-time estimate of a variance at the pixel, such as a degree of change, and the weighting can be determined by a relative stability of an observed value compared to a stability of the time-average.

1 . A method for processing an image signal, comprising: 
 receiving an image signal that has been corrupted by one or more effects;    detecting said one or more effects in said received image signal;    selectively enabling one or more blocks to preprocess said image signal to compensate for said detected one or more effects; and    performing visual analysis on said preprocessed signal using background subtraction.    
   
   
       2 . The method of  claim 1 , wherein said visual analysis identifies one or more objects in said preprocessed image signal.  
   
   
       3 . The method of  claim 1 , wherein said one or more blocks performs a jitter correction on said image signal.  
   
   
       4 . The method of  claim 1 , wherein said one or more blocks performs a color correction on said image signal.  
   
   
       5 . The method of  claim 1 , wherein said one or more blocks performs a contrast enhancement on said image signal.  
   
   
       6 . The method of  claim 1 , wherein said one or more blocks performs a cable-induced visual artifact reduction on said image signal.  
   
   
       7 . The method of  claim 1 , wherein said one or more blocks performs a spatially-variant temporal smoothing on said image signal.  
   
   
       8 . The method of  claim 1 , wherein said one or more blocks performs a lens geometry normalization on said image signal.  
   
   
       9 . A system for processing an image signal, comprising: 
 a memory; and    at least one processor, coupled to the memory, operative to:    receive an image signal that has been corrupted by one or more effects;    detect said one or more effects in said received image signal;    selectively enable one or more blocks to preprocess said image signal to compensate for said detected one or more effects; and    perform visual analysis on said preprocessed signal using background subtraction.    
   
   
       10 . The system of  claim 9 , wherein said visual analysis identifies one or more objects in said preprocessed image signal.  
   
   
       11 . The system of  claim 9 , wherein said one or more blocks performs a jitter correction on said image signal.  
   
   
       12 . The system of  claim 9 , wherein said one or more blocks performs a color correction on said image signal.  
   
   
       13 . The system of  claim 9 , wherein said one or more blocks performs a contrast enhancement on said image signal.  
   
   
       14 . The system of  claim 9 , wherein said one or more blocks performs a cable-induced visual artifact reduction on said image signal.  
   
   
       15 . The system of  claim 9 , wherein said one or more blocks performs a spatially-variant temporal smoothing on said image signal.  
   
   
       16 . The system of  claim 9 , wherein said one or more blocks performs a lens geometry normalization on said image signal.  
   
   
       17 . An article of manufacture for processing an image signal, comprising a machine readable medium containing one or more programs which when executed implement the steps of: 
 receiving an image signal that has been corrupted by one or more effects;    detecting said one or more effects in said received image signal;    selectively enabling one or more blocks to preprocess said image signal to compensate for said detected one or more effects; and    performing visual analysis on said preprocessed signal using background subtraction.    
   
   
       18 . The article of manufacture of  claim 17 , wherein said one or more blocks performs one or more of a jitter correction on said image signal, a color correction on said image signal, a contrast enhancement on said image signal, a cable-induced visual artifact reduction on said image signal, a spatially-variant temporal smoothing on said image signal, or a lens geometry normalization on said image signal.  
   
   
       19 . A method for processing an image signal, comprising: 
 receiving an image signal that has been corrupted by one or more effects;    selectively enabling one or more blocks to preprocess said image signal to compensate for said one or more effects;    performing spatially-variant temporal smoothing to further preprocess said image signal; and    presenting said preprocessed image signal for visual analysis.    
   
   
       20 . The method of  claim 19 , wherein said visual analysis identifies one or more objects in said preprocessed image signal.  
   
   
       21 . The method of  claim 19 , wherein said visual analysis uses background subtraction.  
   
   
       22 . The method of  claim 19 , wherein said visual analysis is performed by a human watching a video screen.  
   
   
       23 . The method of  claim 19 , wherein said spatially-variant temporal smoothing is achieved by the mixing of a new intensity value with a previous intensity time-average as determined by a weighting matrix.  
   
   
       24 . The method of  claim 23 , wherein said mixing is influenced by a dynamic bias term that is a real-time estimate of a variance at said pixel.  
   
   
       25 . The method of  claim 23 , wherein said weighting is determined by a relative stability of an observed value compared to a stability of the time-average.  
   
   
       26 . The method of  claim 23 , wherein an amount of said mixing is based on a degree of change observed at said pixel.  
   
   
       27 . The method of  claim 23 , wherein an amount of said mixing is reduced as a degree of motion at said pixel increases.  
   
   
       28 . The method of  claim 19 , wherein said spatially-variant temporal smoothing is achieved by associating one or more independent Kalman filters with each pixel position.