研究課題/領域番号 |
22K12101
|
研究種目 |
基盤研究(C)
|
配分区分 | 基金 |
応募区分 | 一般 |
審査区分 |
小区分61010:知覚情報処理関連
|
研究機関 | 法政大学 |
研究代表者 |
周 金佳 法政大学, 理工学部, 准教授 (50723392)
|
研究分担者 |
谷口 一徹 大阪大学, 大学院情報科学研究科, 准教授 (40551453)
|
研究期間 (年度) |
2022-04-01 – 2025-03-31
|
研究課題ステータス |
交付 (2022年度)
|
配分額 *注記 |
4,160千円 (直接経費: 3,200千円、間接経費: 960千円)
2024年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
2023年度: 1,560千円 (直接経費: 1,200千円、間接経費: 360千円)
2022年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
|
キーワード | Image sensing / Deep learning / Compressive sensing |
研究開始時の研究の概要 |
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.
|
研究実績の概要 |
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.
|
現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
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.
|
今後の研究の推進方策 |
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.
|