Title :
A Stream Algebra for Computer Vision Pipelines
Author :
Helala, Mohamed A. ; Pu, Ken Q. ; Qureshi, Faisal Z.
Author_Institution :
Fac. of Sci., Univ. of Ontario, Oshawa, ON, Canada
Abstract :
Recent interest in developing online computer vision algorithms is spurred in part by a growth of applications capable of generating large volumes of images and videos. These applications are rich sources of images and video streams. Online vision algorithms for managing, processing and analyzing these streams need to rely upon streaming concepts, such as pipelines, to ensure timely and incremental processing of data. This paper is a first attempt at defining a formal stream algebra that provides a mathematical description of vision pipelines and describes the distributed manipulation of image and video streams. We also show how our algebra can effectively describe the vision pipelines of two state of the art techniques.
Keywords :
communicating sequential processes; computer vision; pipeline processing; video signal processing; video streaming; CSP; communicating sequential processes; computer vision pipelines; formal stream algebra; image streams; video streams; Algebra; Computer vision; Histograms; Pipelines; Silicon compounds; Streaming media; Videos; Computer Vision Pipelines; Image and Video Streams; Stream Algebra; Stream Operators;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPRW.2014.122