WEKO3
アイテム
Compressive sensing for video acquisition
https://ipsj.ixsq.nii.ac.jp/records/225945
https://ipsj.ixsq.nii.ac.jp/records/225945eaf6003d-d7c3-4f0d-bf1d-b9643fd79856
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-CVIM23234001.pdf (11.4 MB)
2025年5月11日からダウンロード可能です。
|
Copyright (c) 2023 by the Information Processing Society of Japan
|
|
| 非会員：¥660, IPSJ:学会員：¥330, CVIM:会員：¥0, DLIB:会員：¥0 | ||
| Item type | SIG Technical Reports(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2023-05-11 | |||||||||
| タイトル | ||||||||||
| タイトル | Compressive sensing for video acquisition | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Compressive sensing for video acquisition | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | D論セッション | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||||||
| 資源タイプ | technical report | |||||||||
| 著者所属 | ||||||||||
| Shizuoka University | ||||||||||
| 著者所属 | ||||||||||
| Osaka University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Shizuoka University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Osaka University | ||||||||||
| 著者名 |
Michitaka, Yoshida
× Michitaka, Yoshida
× Hajime, Nagahara
|
|||||||||
| 著者名(英) |
Michitaka, Yoshida
× Michitaka, Yoshida
× Hajime, Nagahara
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | A camera captures multidimensional information of the real world by convolving it into two dimensions using a sensing matrix. The original multidimensional information is then reconstructed from captured images. Traditionally, multidimensional information has been captured by uniform sampling, but by optimizing the sensing matrix, we can capture images more efficiently and reconstruct multidimensional information with high quality. We fabricated a prototype complementary metal-oxide-semiconductor (CMOS) image sensor with quasi-pixel-wise exposure timing that can realize nonuniform space-time sampling. We also propose an end-to-end learning approach that jointly optimizes the sampling pattern as well as the reconstruction decoder. We applied this deep sensing approach to the video compressive sensing problem. We modeled the spatio-temporal sampling using a convolutional neural network constrained by hardware limitations during network training. | |||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | A camera captures multidimensional information of the real world by convolving it into two dimensions using a sensing matrix. The original multidimensional information is then reconstructed from captured images. Traditionally, multidimensional information has been captured by uniform sampling, but by optimizing the sensing matrix, we can capture images more efficiently and reconstruct multidimensional information with high quality. We fabricated a prototype complementary metal-oxide-semiconductor (CMOS) image sensor with quasi-pixel-wise exposure timing that can realize nonuniform space-time sampling. We also propose an end-to-end learning approach that jointly optimizes the sampling pattern as well as the reconstruction decoder. We applied this deep sensing approach to the video compressive sensing problem. We modeled the spatio-temporal sampling using a convolutional neural network constrained by hardware limitations during network training. | |||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AA11131797 | |||||||||
| 書誌情報 |
研究報告コンピュータビジョンとイメージメディア（CVIM） 巻 2023-CVIM-234, 号 1, p. 1-16, 発行日 2023-05-11 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 2188-8701 | |||||||||
| Notice | ||||||||||
| SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. | ||||||||||
| 出版者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
