Work

Perceptual Optimizations for Video Capture, Processing, and Storage Systems

Year: 2020
Type: dissertation
Abstract: Visual media is the dominant form of content used in modern computing systems.Advances in machine learning, virtual reality, and display form factors drive demand for richer visual experiences, putting pressure on systems to efficiently use compute and storage infrastructure.At the same time, the rapid pace of performance and energy efficiency gains computer architects depended on to meet growing application requirements has slowed.Designing computer systems to meet the requirements of modern video-based applications requires specialization in compute design, using hardwaresoftware codesign techniques to closely optimize computer system performance for specific visual computing workloads.This thesis uses perceptual information to optimize the design of video capture, processing and storage systems.I describe system optimizations using three classes of perceptual cues: structure (e.g., color, depth); semantics (e.g., faces, objects); and saliency (e.g., human visual saliency, neural network feature saliency).This thesis demonstrates how perceptual information can be used in hardware accelerator designs on ASICs and FPGAs, and in cloud video storage infrastructure. To my parents.A new sense of the notion of information has been constructed around the photographic image.The photograph is a thin slice of space as well as time.In a world ruled by photographic images, all borders ("framing") seem arbitrary. . .The ultimate wisdom of the photographic image is to say: "There is the surface.Now think-or rather feel, intuit-what is beyond it, what the reality must be like if it looks this way." -
Language: English
Open Access status: green
OpenAlex ID: W3180198826
Cites: 148
Cited by: 1
Related to: 10