深層学習と圧縮センシングを融合した革新的超低消費電力イメージングシステムの実現
Project/Area Number |
22K12101
|
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 | Hosei University |
Principal Investigator |
周 金佳 法政大学, 理工学部, 准教授 (50723392)
|
Co-Investigator(Kenkyū-buntansha) |
谷口 一徹 大阪大学, 大学院情報科学研究科, 准教授 (40551453)
|
Project Period (FY) |
2022-04-01 – 2025-03-31
|
Project Status |
Granted (Fiscal Year 2022)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2024: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2023: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2022: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
Keywords | Image sensing / Deep learning / Compressive sensing |
Outline of Research at the Start |
This research proposes a new optical coding with AI based measurement coding and smart sparse recovery system that can greatly reduce the sensing power and compression power at the same time. It is the first time to design a sensing pattern that can efficiently compress the signal during sensing.
|
Outline of Annual Research Achievements |
The following tasks have been finished. 1) proposed a structural sensing pattern based optical coding and the intelligent corresponding measurement coding. One journal paper was submitted. 2) Deep learning technology was applied to detect the key information in the video and then compressed by the M coding system. Two papers were accepted by the International Data Compression Conference.
|
Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
As planned, the structural sensing pattern based optical coding and the intelligent corresponding measurement coding algorithm was developed and obtained good results. Moreover, the key information extraction algorithm also got good results. We will further improve it.
|
Strategy for Future Research Activity |
This project has three main tasks. The first task was already finished. For the second task, we have extracted the moving object as the key information in FY2022. We plan to further improve the key information extraction algorithms, and apply new algorithm to compress these information. Finally, we will start to design the whole system with power adaptive configuration.
|
Report
(1 results)
Research Products
(3 results)