| Project/Area Number |
18K11372
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61010:Perceptual information processing-related
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
Goto Tomio 名古屋工業大学, 工学(系)研究科(研究院), 准教授 (20324478)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2021: ¥130,000 (Direct Cost: ¥100,000、Indirect Cost: ¥30,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2018: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | ブラインド画像復元 / 内視鏡カメラ映像 / ぼけ・ぶれ補正 / FPGA実装 / 医用カメラ |
|---|
| Outline of Final Research Achievements |
Real-time blind image restoration process on a workstation is realized, and the algorithm for estimating the blur and blur coefficient (PSF) of medical images is estimated from the reduced image, and the estimated The PSF is enlarged as the initial value and gradually enlarged from the reduced image to the original image to maintain the estimation accuracy and increase the speed. In addition, we confirmed that parallel processing can be achieved by implementing the algorithm for ideal image estimation and PSF estimation independently during PSF estimation, thereby realizing real-time processing.
In addition, by implementing the real-time blind image restoration algorithm implemented on a workstation on three FPGAs and operating them in parallel in a cooperative manner Real-time blind image restoration processing was achieved.
|
| Academic Significance and Societal Importance of the Research Achievements |
筆者らは先行研究において提案したぼけ・ぶれ画像のブラインド画像復元アルゴリズムにおいて、TV正則化およびShockフィルタという非線形信号処理を適用させることで、世界最高性能を有するブラインド画像復元手法であることをIEEE国際会議の画像処理関連のトップカンファレンスであるICIP2017において証明し、多くの研究者から高く評価された。このアルゴリズムを内視鏡カメラに応用し、リアルタイム動作させることで、医療分野における映像のぼけ・ぶれ補正が実現でき、多くの治療において使われる映像の高画質化・高精細化を実現することが可能となり、産業的な側面だけでなく、医療行為の質の向上にも繋がる。
|
