Graphics Reference
In-Depth Information
Chapter 12
Data-Driven Stream Mining Systems
for Computer Vision
Shuvra S. Bhattacharyya, Mihaela van der Schaar, Onur Atan, Cem Tekin
and Kishan Sudusinghe
Abstract
In this chapter, we discuss the state of the art and future challenges in
adaptive streammining systems for computer vision. Adaptive streammining in this
context involves the extraction of knowledge from image and video streams in
real-time, and from sources that are possibly distributed and heterogeneous. With
advances in sensor and digital processing technologies, we are able to deploy net-
works involving large numbers of cameras that acquire increasing volumes of image
data for diverse applications in monitoring and surveillance. However, to exploit the
potential of such extensive networks for image acquisition, important challengesmust
be addressed in efficient communication and analysis of such data under constraints
on power consumption, communication bandwidth, and end-to-end latency. We dis-
cuss these challenges in this chapter, and we also discuss important directions for
research in addressing such challenges using dynamic, data-driven methodologies.
12.1 Introduction
In this chapter, we address challenges involving the development of algorithms,
models, and design methods for distributed and adaptive real-time knowledge extrac-
tion of information from high volume image streams. We focus on an important
emerging class of “big data” systems called
adaptive stream mining
(
ASM
)systems,
B
·
S.S. Bhattacharyya (
K. Sudusinghe
University of Maryland, College Park, MD, USA
e-mail: ssb@umd.edu
K. Sudusinghe
e-mail: kishans@umd.edu
M. van der Schaar
)
C. Tekin
University of California, Los Angeles, CA, USA
e-mail: mihaela@ee.ucla.edu
O. Atan
e-mail: oatan@ucla.edu
C. Tekin
e-mail: cmtkn@ucla.edu
·
O. Atan
·
