Graphics Reference
In-Depth Information
Chapter 13
Designing Vision Systems that See Better
Sek Chai, Sehoon Lim and David Zhang
Abstract
This chapter introduces computational sensing and imaging—a branch of
computer vision that deals with embedded processing for capturing higher quality
imagery, to the embedded vision developer. In this research domain, issues such as
exposure, motion blur, and dynamic range are addressed by fundamentally changing
how light is sensed, captured, and made available for downstream semantic process-
ing. Some important applications enabled are in digital photography and situational
awareness. We present several design examples on these camera platforms where
modifications of the image-capture process result in significant improvements in
image quality, allowing downstream vision analysis to perform better. Motivated by
example applications, we then describe the basic architecture of an embedded vision
system that dynamically tunes and adapts to the task at hand.
13.1 Computational Imaging Overview
Computational imaging refers to the capture, processing, and manipulation
techniques that improve or extend the quality of an image. Beyond just image
enhancements such as basic image processing, this field has evolved to include tech-
niques from computer vision, graphics, and applied optics to affect the output from
a traditional camera. Also commonly referred to as computational photography [
1
],
in this chapter we would adopt the term computational imaging instead because the
applications using this technology can extend beyond photography.
This growing area of research is important for embedded vision because it pro-
vides higher quality image data for downstream semantic processing, such as object
detection, tracking, and recognition. Very often semantic processing fails because
image quality is poor, noisy, blurry, or simply lacking desired features to segment
B
S. Chai (
D. Zhang
SRI International, Menlo Park, USA
e-mail: sek.chai@gmail.com
)
·
S. Lim
·
