Video player, video playback method, and program
A video player includes a processor; and a memory that includes instructions, which when executed, cause the processor to execute the following steps: predicting a future throughput by using a past throughput value; configuring a search space for identifying a quality adaptation schedule; extracting a plurality of paths in the search space; estimating, based on the future throughput, a quality of experience value for each path of the extracted plurality of paths; identifying a path corresponding to a highest quality of experience value from among the estimated quality of experience values, as the quality adaptation schedule; determining, based on the quality adaptation schedule, a quality value of a chunk to be requested for the future unit time interval subsequent to the current unit time interval; requesting the chunk with the determined quality value; and receiving the chunk with the determined quality value.
1 . A video player comprising:
a transmitter;
a receiver,
a processor; and
a memory that includes instructions, which when executed, cause the processor to execute the following steps:
predicting a future throughput for a future first time interval by using a past throughput value, the future first time interval including m future unit time intervals;
configuring a search space for identifying a quality adaptation schedule, the search space being defined by k quality values, and a second time interval including a current unit time interval, the m future unit time intervals, and n past unit time intervals;
extracting a plurality of paths in the search space, each path of the plurality of paths being obtained by selecting one quality level from the k quality levels for each unit time interval included in the second time interval;
estimating, based on the future throughput, a quality of experience value for each path of the extracted plurality of paths;
identifying a path corresponding to a highest quality of experience value from among the estimated quality of experience values, as the quality adaptation schedule;
determining, based on the quality adaptation schedule, a quality value of a chunk to be requested for the future unit time interval subsequent to the current unit time interval;
requesting the chunk with the determined quality value through the transmitter; and
receiving the chunk with the determined quality value through the receiver.
2 . The video player according to claim 1 , wherein the extracting extracts (2×A+1) m paths in the m future unit time intervals by allowing, as a difference between quality levels in two adjacent unit time intervals, only the difference that is less than or equal to A levels.
3 . The video player according to claim 1 , wherein the predicting the future throughput uses a throughput measured in the n past unit time intervals to predict the throughput for the m future unit time intervals.
4 . The video player according to claim 1 , wherein the predicting the future throughput uses a throughput of another video that is previously watched or a preset low throughput.
5 . The video player according to claim 1 , wherein the estimating the quality of experience value uses a predetermined quality of experience model to evaluate the quality of experience value.
6 . A video playback method executed by a computer, the method comprising:
predicting a future throughput for a future first time interval by using a past throughput value, the future first time interval including m future unit time intervals;
configuring a search space for identifying a quality adaptation schedule, the search space being defined by k quality values, and a second time interval including a current unit time interval, the m future unit time intervals, and n past unit time intervals;
extracting a plurality of paths in the search space, each path of the plurality of paths being obtained by selecting one quality level from the k quality levels for each unit time interval included in the second time interval;
estimating, based on the future throughput, a quality of experience value for each path of the extracted plurality of paths;
identifying a path corresponding to a highest quality of experience value from among the estimated quality of experience values, as the quality adaptation schedule;
determining, based on the quality adaptation schedule, a quality value of a chunk to be requested for the future unit time interval subsequent to the current unit time interval;
requesting the chunk with the determined quality value; and
receiving the chunk with the determined quality value.
7 . The video playback method executed by a computer according to claim 6 , wherein the extracting extracts (2×A+1) m paths in the m future unit time intervals by allowing, as a difference between quality levels in two adjacent unit time intervals, only the difference that is less than or equal to A levels.
8 . The video playback method executed by a computer according to claim 6 , wherein the predicting the future throughput uses a throughput measured in the n past unit time intervals to predict the throughput for the m future unit time intervals.
9 . The video playback method executed by a computer according to claim 6 , wherein the predicting the future throughput uses a throughput of another video that is previously watched or a preset low throughput.
10 . The video playback method executed by a computer according to claim 6 , wherein the estimating the quality of experience value uses a predetermined quality of experience model to evaluate the quality of experience value.
11 . A non-transitory computer readable recording medium storing a video playback program, wherein, when the video playback program is executed by a computer, the program causes the computer to execute the following steps:
predicting a future throughput for a future first time interval by using a past throughput value, the future first time interval including m future unit time intervals;
configuring a search space for identifying a quality adaptation schedule, the search space being defined by k quality values, and a second time interval including a current unit time interval, the m future unit time intervals, and n past unit time intervals,
extracting a plurality of paths in the search space, each path of the plurality of paths being obtained by selecting one quality level from the k quality levels for each unit time interval included in the second time interval;
estimating, based on the future throughput, a quality of experience value for each path of the extracted plurality of paths;
identifying a path corresponding to a highest quality of experience value from among the estimated quality of experience values, as the quality adaptation schedule;
determining, based on the quality adaptation schedule, a quality value of a chunk to be requested for the future unit time interval subsequent to the current unit time interval;
requesting the chunk with the determined quality value; and
receiving the chunk with the determined quality value.
12 . The computer-readable non-transitory recording medium according to claim 11 wherein the video playback program further comprises:
the extracting extracts (2×A+1) m paths in the m future unit time intervals by allowing, as a difference between quality levels in two adjacent unit time intervals, only the difference that is less than or equal to A levels.
13 . The computer-readable non-transitory recording medium according to claim 11 wherein the video playback program further comprises:
the predicting the future throughput uses a throughput measured in the n past unit time intervals to predict the throughput for the m future unit time intervals.
14 . The computer-readable non-transitory recording medium according to claim 11 wherein the video playback program further comprises:
the predicting the future throughput uses a throughput of another video that is previously watched or a preset low throughput.
15 . The computer-readable non-transitory recording medium according to claim 11 wherein the video playback program further comprises:
the estimating the quality of experience value uses a predetermined quality of experience model to evaluate the quality of experience value.