Method and system for characteristic-based video processing
AssigneeAlibaba Group Holding Limited
InventorsShaolin Xie, Minghai Qin, Yen-kuang Chen, Tae Meon Bae, Qinggang Zhou
Life of this patent
Estimating the term…
Abstract
A method and apparatus for characteristic-based video processing include: in response to receiving a region of a picture of a video sequence, determining a characteristic in the region, the region being independent of other regions of the picture for video coding; determining a class associated with the region based on the characteristic, the class being selected from a plurality of classes; and encoding the region using a parameter set associated with the class, the parameter set being selected from a plurality of parameter sets for video coding at different quality levels.
Claims20
A non-transitory computer-readable storage medium storing a set of instructions that are executable by one or more processors of a device to cause the device to perform a method comprising:
- in response to receiving a region of a picture of a video sequence, determining a characteristic in the region, the region being independent of other regions of the picture for video coding;
- determining a class associated with the region based on the characteristic, the class being selected from a plurality of classes;
- encoding the region using a parameter set associated with the class, the parameter set being selected from a plurality of parameter sets for video coding at different quality levels;
- generating a coded video stream comprising the parameter set and the region encoded;
- and
- storing the coded video stream and classes associated with at least one picture of the video sequence in a database, wherein the classes are searchable, and a portion of the coded video stream corresponding to any class is locatable by a class.
An apparatus, comprising:
- a memory configured to store instructions;
- and
- at least one processor configured to execute the instructions to cause the apparatus to:
- in response to receiving a region of a picture of a video sequence, determine a characteristic in the region, the region being independent of other regions of the picture for video coding;
- determine a class associated with the region based on the characteristic, the class being selected from a plurality of classes;
- encode the region using a parameter set associated with the class, the parameter set being selected from a plurality of parameter sets for video coding at different quality levels;
- generate a coded video stream comprising the parameter set and the region encoded;
- and
- store the coded video stream and classes associated with at least one picture of the video sequence in a database, wherein the classes are searchable, and a portion of the coded video stream corresponding to any class is locatable by a class.
A computer-implemented method, comprising:
- in response to receiving a region of a picture of a video sequence, determining a characteristic in the region, the region being independent of other regions of the picture for video coding;
- determining a class associated with the region based on the characteristic, the class being selected from a plurality of classes;
- encoding the region using a parameter set associated with the class, the parameter set being selected from a plurality of parameter sets for video coding at different quality levels;
- generating a coded video stream comprising the parameter set and the region encoded;
- and
- storing the coded video stream and classes associated with at least one picture of the video sequence in a database, wherein the classes are searchable, and a portion of the coded video stream corresponding to any class is locatable by a class.
Dependencies are inferred from the claim text.