Online Control of Active Camera Networks for Computer Vision Tasks

    Authors

    A. Ilie;G. Welch

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    ACM Trans. Sens. Netw.

    Keywords

    Algorithms; Experimentation; Measurement; Performance; Camera control; active camera networks; computer vision; surveillance; motion capture; 3D reconstruction; VISUAL OBJECT TRACKING; STATE ESTIMATION; SURVEILLANCE; SYSTEMS; Computer Science, Information Systems; Telecommunications

    Abstract

    Large networks of cameras have been increasingly employed to capture dynamic events for tasks such as surveillance and training. When using active cameras to capture events distributed throughout a large area, human control becomes impractical and unreliable. This has led to the development of automated approaches for online camera control. We introduce a new automated camera control approach that consists of a stochastic performancemetric and a constrained optimizationmethod. The metric quantifies the uncertainty in the state of multiple points on each target. It uses state-space methods with stochastic models of target dynamics and camera measurements. It can account for occlusions, accommodate requirements specific to the algorithms used to process the images, and incorporate other factors that can affect their results. The optimization explores the space of camera configurations over time under constraints associated with the cameras, the predicted target trajectories, and the image processing algorithms. The approach can be applied to conventional surveillance tasks (e. g., tracking or face recognition), as well as tasks employing more complex computer vision methods (e. g., markerless motion capture or 3D reconstruction).

    Journal Title

    Acm Transactions on Sensor Networks

    Volume

    10

    Issue/Number

    2

    Publication Date

    1-1-2014

    Document Type

    Article

    Language

    English

    First Page

    40

    WOS Identifier

    WOS:000330625100008

    ISSN

    1550-4859

    Share

    COinS