| Project/Area Number |
15K16023
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
Fukushima Norishige 名古屋工業大学, 工学(系)研究科(研究院), 准教授 (80550508)
|
|---|
| Research Collaborator |
MATSUO Takuya
KIMURA Makoto
Takeuchi Kouta
|
|---|
| Project Period (FY) |
2015-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2015: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | 乱択エッジ保存平滑化フィルタ / バイラテラルフィルタ / 乱択バイラテラルフィルタ / 乱択DCTデノイジング / 乱択アルゴリズム / 並列化 / ベクトル化 / SIMD / 乱択フィルタ / エッジ保存平滑化フィルタ / GPU / コンピュテーショナルフォトグラフィ / 並列画像処理 / 画像処理プログラミング |
|---|
| Outline of Final Research Achievements |
We research acceleration of edge-preserving filtering using randomized algorithms. For acceleration, information is sub-sampled.
Instead of using periodical sub-sampling, we optimize sub-sampling patterns with sufficient randomness to realize a more accurate filter even with the same number of samples. Also, the sub-sampling method is extended to the Monte Carlo algorithm the Las Vegas algorithm in the randomized algorithm for broad usages of applications. On the implementation side of the algorithm, we investigate implementation methods that can perform filtering with randomized sub-sampling in a vector operation environment, such as SIMD or SIMT. We implemented it in the AVX environment of CPU and a modern GPU, and verified the implementation had high efficiency.
|
