Video encoding apparatus and video encoding system

1. A video encoding apparatus, comprising:

a memory configured to store interest region information for each of a plurality of scenarios; and a processor configured to, encode a current frame of an input video received from the memory to generate compressed data by,

recognizing a scenario in the input video from among a plurality of scenarios, the scenario including a region of interest (ROI) and a non-region of interest (non-ROI) set based on the interest region information,

in response to the scenario in the input video being recognized, extracting the interest region information corresponding to the scenario recognized in the input video from among the plurality of scenarios,

in response to the scenario in the input video not being recognized, setting a block among a plurality of blocks included in the current frame having a texture value less than a set value as a first block corresponding to the ROI, and setting a block excluding the first block among the plurality of blocks as a second block corresponding to the non-ROI, and

encoding the current frame based on the ROI and the non-ROI set for the scenario to generate the compressed data; and

updating the interest region information stored in the memory based on a user input by,

displaying the input video based on a first one of the interest region information for the scenario,

receiving the user input selecting a second one of the interest region information for the scenario,

mapping the second one of the interest region information for the scenario to the input video based on the user input, and storing the second one of the interest region information in the memory.

2. The video encoding apparatus of claim 1 , wherein the processor is further configured to,

divide the current frame included in the input video into the plurality of blocks,

divide the plurality of blocks into the first block corresponding to the ROI and the second block corresponding to the non-ROI based on the interest region information,

determine a first quantization parameter value for the first block and a second quantization parameter value for the second block; and

encode the current frame based on the first quantization parameter value and the second quantization parameter value to generate the compressed data.

3. The video encoding apparatus of claim 1 , wherein the processor is configured to extract the interest region information by,

extracting the second one of the interest region information mapped for scenario, if the input video corresponds to the scenario.

4. The video encoding apparatus of claim 1 , wherein the processor is configured to,

receive the user input selecting the second one of the interest region information for the scenario based on at least one of user gaze information and user input information.

5. A video encoding apparatus, comprising:

a memory configured to store interest region information for each of a plurality of scenarios; and

a processor configured to,

recognize a scenario in the input video from among of the plurality of scenarios, the scenario including a region of interest (ROI) and a non-region of interest (non-ROI) set based on the interest region information,

in response to the scenario in the input video being recognized, extract, from the memory, the interest region information corresponding to the scenario recognized in the input video from among the plurality of scenarios, divide a current frame included in the input video into a plurality of blocks, and divide the plurality of blocks into a first dock corresponding to the ROI and a second block corresponding to the non-ROI based on the interest region information,

in response to the scenario in the input video not being recognized, set a block among the plurality of blocks included in the current frame having a texture value less than a set value as the first block corresponding to the ROI, and set a block excluding the first block among the plurality of blocks as the second block corresponding to the non-ROI,

determine a first quantization parameter value for the first block and a second quantization parameter value for the second block,

encode the current frame based on the first quantization parameter value and the second quantization parameter value to generate compressed data, and

update the interest region information stored in the memory based on a user input by, displaying the input video based on a first one of the interest region information for the scenario,

receiving the user input selecting a second one of the interest region information for the scenario,

mapping the second one of the interest region information for the scenario to the input video based on the user input, and storing the second one of the interest region information in the memory.

6. The video encoding apparatus of claim 5 , wherein the processor is configured to,

extract the second one of the interest region information mapped in the scenario, if the input video corresponds to the scenario, and

determine the first block and the second block based on the second one of the interest region information.

7. A video encoding system, comprising: a video source configured to transmit an input video; a video encoding apparatus including, a first memory configured to store interest region information for each of a plurality of scenarios, and a processor configured to,

recognize a scenario in the input video from among the plurality of scenarios, the scenario including a region of interest (ROI) and a non-region of interest (non-ROI) set based on the interest region information,

in response to the scenario in the input video being recognized, extract, from the first memory, the interest region information corresponding to the scenario recognized in the input video from among the plurality of scenarios, divide a current frame included in the input video into a plurality of blocks, and divide the plurality of blocks into a first block corresponding to the ROI and a second block corresponding to the non-ROI based on the interest region information,

in response to the scenario in the input video not being recognized, set a block among the plurality of blocks included in the current frame having a texture value less than a set value as the first block corresponding to the ROI, and set a block excluding the first block among the plurality of blocks as the second block corresponding to the non-ROI,

determine a first quantization parameter value for the first block and a second quantization parameter value for the second block,

encode the current frame based on the first quantization parameter value and the second quantization parameter value to generate compressed data, and

update the interest region information stored in the memory based on a user input by,

displaying the input video based on a first one of the interest region information for the scenario,

receiving the user input selecting a second one of the interest region information for the scenario,

mapping the second one of the interest region information for the scenario to the input video based on the user input, and

storing the second one of the interest region information in the memory and

a second memory configured to store a bit stream, the bit stream being entropy-encoded based on the compressed data.

8. The video encoding system of claim 7 , wherein the second memory is configured to,

store a first video having the first one of the interest region information associated with the scenario, and

store a second video having the second one of the interest region information associated with the scenario.

9. The video encoding system of claim 8 , further comprising:

a display device configured to display the first video and the second video stored in the second memory according to a pre-test command.

10. The video encoding system of claim 9 , wherein the processor is configured to,

extract the second one of the interest region information mapped in the scenario, if the input video corresponds to the scenario, and

determine the first block and the second block based on the second one of the interest region information.

11. The video encoding system of claim 7 , wherein

the first memory is configured to store the first one of the interest region information and the second one of the interest region information,

the second memory is configured to store a first video having the first one of the interest region information associated with the scenario, and a second video having the second one of the interest region information associated with the scenario, and

the processor is configured to select the second interest region information based on at least one of user gaze information for the second video and user input information for the second video when displaying the second video.