Name
Abstract | ||
|---|---|---|
Cameras face a fundamental trade-off between spatial and temporal resolution. Digital still cameras can capture images with high spatial resolution, but most high-speed video cameras have relatively low spatial resolution. It is hard to overcome this trade-off without incurring a significant increase in hardware costs. In this paper, we propose techniques for sampling, representing, and reconstructing the space-time volume to overcome this trade-off. Our approach has two important distinctions compared to previous works: 1) We achieve sparse representation of videos by learning an overcomplete dictionary on video patches, and 2) we adhere to practical hardware constraints on sampling schemes imposed by architectures of current image sensors, which means that our sampling function can be implemented on CMOS image sensors with modified control units in the future. We evaluate components of our approach, sampling function and sparse representation, by comparing them to several existing approaches. We also implement a prototype imaging system with pixel-wise coded exposure control using a liquid crystal on silicon device. System characteristics such as field of view and modulation transfer function are evaluated for our imaging system. Both simulations and experiments on a wide range of scenes show that our method can effectively reconstruct a video from a single coded image while maintaining high spatial resolution. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TPAMI.2013.129 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
cmos image sensors,silicon device,image representation,digital still cameras,image coding,low spatial resolution,current image sensor,high spatial resolution,transfer functions,sparse reconstruction,learning (artificial intelligence),image resolution,temporal resolution,high-speed imaging,system characteristics,spatial resolution,high-speed video cameras,video cameras,dictionary learning,sampling function,modified control units,sparse video representation,prototype imaging system,image sampling,cmos image sensor,space-time volume reconstruction,high-speed video camera,cameras,hardware constraints,computational camera,space-time sampling,efficient space-time sampling,video patches,video reconstruction,pixel-wise coded exposure control,fundamental trade-off,liquid crystal,liquid crystals,pixel-wise coded exposure,single image coding,sparse representation,modulation transfer function,sampling scheme,learning artificial intelligence | Field of view,Computer vision,Optical transfer function,Pattern recognition,Image sensor,Computer science,Sparse approximation,Artificial intelligence,Pixel,Sampling (statistics),Temporal resolution,Image resolution | Journal |
Volume | Issue | ISSN |
36 | 2 | 1939-3539 |
Citations | PageRank | References |
22 | 1.18 | 20 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dengyu Liu | 1 | 37 | 2.76 |
| Jinwei Gu | 2 | 687 | 39.49 |
| Yasunobu Hitomi | 3 | 91 | 4.04 |
| Mohit Gupta | 4 | 489 | 31.55 |
| Tomoo Mitsunaga | 5 | 666 | 65.73 |
| Shree K. Nayar | 6 | 12394 | 1538.46 |