Dynamic frame padding in a video hardware engine

Abstract

A video hardware engine which support dynamic frame padding is disclosed. The video hardware engine includes an external memory. The external memory stores a reference frame. The reference frame includes a plurality of reference pixels. A motion estimation (ME) engine receives a current LCU (largest coding unit), and defines a search area around the current LCU for motion estimation. The ME engine receives a set of reference pixels corresponding to the current LCU. The set of reference pixels of the plurality of reference pixels are received from the external memory. The ME engine pads a set of duplicate pixels along an edge of the reference frame when a part area of the search area is outside the reference frame.

What is claimed is: 
     
         1 . A device comprising:
 a motion estimation unit configured to:
 receive a current coding unit; 
 define a search area around the current coding unit; 
 receive a reference frame; 
 define a boundary beyond an edge of the reference frame; 
 pad a portion of the search area between the boundary and the edge; and 
 output motion information; and 
   a motion compensation unit configured to:
 receive the output motion information; and 
 generate a predicted coding unit based on the output motion information. 
   
     
     
         2 . The device of  claim 1 , wherein:
 the reference frame is stored in an external memory.   
     
     
         3 . The device of  claim 1 , wherein:
 the reference frame includes a set of reference pixels associated with the current coding unit.   
     
     
         4 . The device of  claim 3 , wherein:
 the portion of the search area padded by the motion estimation unit includes a set of duplicate pixels of the set of reference pixels.   
     
     
         5 . The device of  claim 1 , wherein:
 the motion compensation unit receives the current coding unit from the motion estimation unit.   
     
     
         6 . The device of  claim 1 , wherein:
 the output motion information includes the current coding unit; and   the motion compensation unit is configured to:
 receive the current coding unit; 
 determine a motion vector based on the current coding unit; 
 determine a motion reference coding unit based on the motion vector, wherein the motion referenced coding unit includes a second boundary; and 
 in response to the second boundary being beyond the reference frame, pad an area between the second boundary and the reference frame. 
   
     
     
         7 . The device of  claim 6 , wherein:
 the motion compensation unit is configured to receive a set of reference pixels associated with the motion reference coding unit.   
     
     
         8 . The device of  claim 7 , wherein:
 the motion compensation unit configures a video direct memory access engine for access to the set of reference pixels associated with the motion reference coding unit.   
     
     
         9 . The device of  claim 1 , wherein:
 the current coding unit is a center of the search area around the current coding unit.   
     
     
         10 . The device of  claim 1 , wherein:
 the search area includes a top horizontal edge, a bottom horizontal edge, a right vertical edge, and a left vertical edge.   
     
     
         11 . A method comprising:
 receiving, by a motion estimation unit, a current coding unit;   defining, by the motion estimation unit, a search area around the current coding unit;   receiving, by the motion estimation unit, a reference frame;   defining, by the motion estimation unit, a boundary beyond an edge of the reference frame;   padding, by the motion estimation unit, a portion of the search area between the boundary and the edge;   outputting, by the motion estimation unit, motion information;   receiving, by a motion compensation unit, the output motion information; and   generating, by the motion compensation unit, a predicted coding unit based on the output motion information.   
     
     
         12 . The method of  claim 11 , wherein:
 the reference frame is stored in an external memory.   
     
     
         13 . The method of  claim 11 , wherein:
 the reference frame includes a set of reference pixels associated with the current coding unit.   
     
     
         14 . The method of  claim 13 , wherein:
 the portion of the search area padded by the motion estimation unit includes a set of duplicate pixels of the set of reference pixels.   
     
     
         15 . The method of  claim 11 , further comprising:
 receiving, by the motion compensation unit, the current coding unit from the motion estimation unit.   
     
     
         16 . The method of  claim 11 , further comprising:
 receiving, by the motion compensation unit, the current coding unit, wherein the output motion information includes the current coding unit;   determining, by the motion compensation unit, a motion vector based on the current coding unit;   determining, by the motion compensation unit, a motion reference coding unit based on the motion vector, wherein the motion referenced coding unit includes a second boundary; and   in response to the second boundary being beyond the reference frame, padding, by the motion compensation unit, an area between the second boundary and the reference frame.   
     
     
         17 . The method of  claim 16 , further comprising:
 receiving, by the motion compensation unit, a set of reference pixels associated with the motion reference coding unit.   
     
     
         18 . The method of  claim 17 , further comprising:
 configuring, by the motion compensation unit, a video direct memory access engine for access to the set of reference pixels associated with the motion reference coding unit.   
     
     
         19 . The method of  claim 11 , wherein:
 the current coding unit is a center of the search area around the current coding unit.   
     
     
         20 . The method of  claim 11 , wherein:
 the search area includes a top horizontal edge, a bottom horizontal edge, a right vertical edge, and a left vertical edge.