2990

Real-Time Approaches to Computer Vision

Ron Tal
Human and Computer Vision Lab (Elderlab), York University, 4700 Keele Street, Toronto, Ontario, Canada, M3J 1P3
York University, Project CSE 5441, 2009

@article{tal2009real,

   title={Real-Time Approaches to Computer Vision},

   author={Tal, R.},

   year={2009}

}

Download Download (PDF)   View View   Source Source   

509

views

Perhaps the extensive reliance on our visual sensory inputs, makes the use of artificial visual sensors seem like an intuitive choice. Thus, Machine Vision or Computer Vision has become an exciting field of research, finding its way into many industrial applications. The results from Computer Vision research can be incorporated in autonomous machine navigation, industrial quality control, human computer interaction, and many more. However, vision sensors such as digital cameras provide us with a large matrix of measured data at regular sampling intervals often corrupted by noise due to badly understood processes. For this reason, many Computer Vision algorithms are stochastic in nature, often with unpredictable convergence times, and requiring complex computations on large matrices that are often time consuming. In this report, we provide a detailed survey of the various approaches that Computer Vision researchers have used in order to improve the performance of Vision systems with the ultimate goal of meeting soft or hard real-time requirements.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: