Eighty five percent of images today are taken by cell phones. These images are not merely projections of light from the scene onto the camera sensor but result from a deep calculation. This calculation involves a number of computational imaging algorithms such as high dynamic range (HDR) imaging, panorama stitching, image deblurring and low-light imaging that compensate for camera limitations, and a number of deep learning based vision algorithms such as face recognition, object recognition and scene understanding that make inference on these images for a variety of emerging applications. However, because of their high computational complexity, mobile CPU or GPU based implementations of these algorithms do not achieve real-time performance. Moreover, offloading these algorithms to the cloud is not a viable solution because wirelessly transmitting large amounts of image data results in long latency and high energy consumption, making them unsuitable for mobile devices.

This work solves these problems by designing energy-efficient hardware accelerators targeted at these applications. It presents the architecture of two complete computational imaging systems for energy-constrained mobile environments: (1) an energy-scalable accelerator for blind image deblurring, with an on-chip implementation and (2) a low-power processor for real-time motion magnification in videos, with an FPGA implementation. It also presents a 3D imaging platform and image processing workflow for 3D surface area assessment of dermatologie lesions. It demonstrates that such accelerator-based systems can enable energy-efficient integration of computational imaging and vision algorithms into mobile and wearable devices. (Copies available exclusively from MIT Libraries, libraries.mit.edu/docs - docs mit.edu).