| Session: | Poster Session |
| Location: | Poster Area |
| Session Time: | Wednesday, June 27, 15:40 - 17:00 |
| Presentation Time: | Wednesday, June 27, 15:40 - 16:40 |
| Presentation: |
Poster
|
| Paper Title: |
PERCEPTUAL QUALITY DRIVEN ADAPTIVE VIDEO CODING USING JND ESTIMATION |
| Authors: |
Masaru Takeuchi; Waseda University, Japan | | |
| | Shintaro Saika; Waseda University, Japan | | |
| | Yusuke Sakamoto; Waseda University, Japan | | |
| | Tatsuya Nagashima; Waseda University, Japan | | |
| | Zhengxue Cheng; Waseda University, Japan | | |
| | Kenji Kanai; Waseda University, Japan | | |
| | Jiro Katto; Waseda University, Japan | | |
| | Kaijin Wei; Huawei Technologies, China | | |
| | Ju Zengwei; Huawei Technologies, China | | |
| | Xu Wei; Huawei Technologies, China | | |
| Abstract: |
We introduce a perceptual video quality driven video encoding solution for optimized adaptive streaming. By using multiple bitrate/resolution encoding like MPEG-DASH, video streaming services can deliver the best video stream to a client, under the conditions of the client’s available bandwidth and viewing device capability. However, conventional fixed encoding recipes (i.e. resolution-bitrate pairs) suffer from many problems, such as improper resolution selection and stream redundancy. To avoid these problems, we propose a novel video coding method, which generates multiple representations with constant Just-Notable Difference (JND) interval. For this purpose, we developed a JND scale estimator using Support Vector Regression (SVR), and designed a pre-encoder which outputs an encoding recipe with constant JND interval in an adaptive manner to input video. |