Abstract
Single-pixel cameras capture images without the requirement for a multi-pixel sensor, enabling the use of state-of-the-art detector technologies and providing a potentially low-cost solution for sensing beyond the visible spectrum. One limitation of single-pixel cameras is the inherent trade-off between image resolution and frame rate, with current compressive (compressed) sensing techniques being unable to support real-time video. In this work we demonstrate the application of deep learning with convolutional auto-encoder networks to recover real-time 128 × 128 pixel video at 30 frames-per-second from a single-pixel camera sampling at a compression ratio of 2%. In addition, by training the network on a large database of images we are able to optimise the first layer of the convolutional network, equivalent to optimising the basis used for scanning the image intensities. This work develops and implements a novel approach to solving the inverse problem for single-pixel cameras efficiently and represents a significant step towards real-time operation of computational imagers. By learning from examples in a particular context, our approach opens up the possibility of high resolution for task-specific adaptation, with importance for applications in gas sensing, 3D imaging and metrology.
Highlights
Single-pixel cameras capture images without the requirement for a multi-pixel sensor, enabling the use of state-of-the-art detector technologies and providing a potentially low-cost solution for sensing beyond the visible spectrum
In this work we demonstrate the application of deep learning with a deep convolutional auto-encoder to produce a novel algorithm capable of recovering real-time high-resolution (128 × 128 pixel) video at 30 fps from a single-pixel camera system employing, as a spatial light modulator, a high-speed digital micro-mirror device (DMD)
For each binary mask displayed on the DMD, the measured intensity corresponds to the correlation it has with the scene
Summary
Single-pixel cameras capture images without the requirement for a multi-pixel sensor, enabling the use of state-of-the-art detector technologies and providing a potentially low-cost solution for sensing beyond the visible spectrum. In this work we demonstrate the application of deep learning with convolutional auto-encoder networks to recover real-time 128 × 128 pixel video at 30 frames-persecond from a single-pixel camera sampling at a compression ratio of 2%. Dimension reduction in high-dimensional data can be achieved by training a multilayer neural network called an auto-encoder[9] Innovations such as convolutional layers[10] have further improved context learning and super-resolution[11]. An auto-encoder can be considered as a promising alternative to compressive sensing This insight motivated the work presented here, which demonstrates the use of a deep convolutional auto-encoder network (DCAN) to provide a computationally-efficient and data-efficient pipeline for solving the inverse problems with better quality, and importantly, in real-time
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
