Abstract
We propose and demonstrate a compressive temporal imaging system based on pulsed illumination to encode temporal dynamics into the signal received by the imaging sensor during exposure time. Our approach enables >10x increase in effective frame rate without increasing camera complexity. To mitigate the complexity of the inverse problem during reconstruction, we introduce two keyframes: one before and one after the coded frame. We also craft what we believe to be a novel deep learning architecture for improved reconstruction of the high-speed scenes, combining specialized convolutional and transformer architectures. Simulation and experimental results clearly demonstrate the reconstruction of high-quality, high-speed videos from the compressed data.
Original language | English (US) |
---|---|
Pages (from-to) | 39201-39212 |
Number of pages | 12 |
Journal | Optics Express |
Volume | 31 |
Issue number | 23 |
DOIs | |
State | Published - Nov 6 2023 |
ASJC Scopus subject areas
- Atomic and Molecular Physics, and Optics
Fingerprint
Dive into the research topics of 'Compressive video via IR-pulsed illumination'. Together they form a unique fingerprint.Datasets
-
Test dataset for Compressive video via IR-pulsed illumination
Guzmán, F. (Contributor), Skowronek, J. (Creator), Vera, E. (Creator) & Brady, D. J. (Creator), University of Arizona Research Data Repository, 2023
DOI: 10.25422/azu.data.24455137.v1, https://arizona.figshare.com/articles/dataset/Test_dataset_for_Compressive_video_via_IR-pulsed_illumination/24455137/1
Dataset