Abstract—Paper describes the design of extended model for
tracking and locating object in multi-cameras environment with
controlling the streams from multiple angles in real time.
Proposed and experimentally implemented solution is
attempting to deliver via streaming technology of the only
specific shot from scene that has the best view on tracked object
in real time. Measurement of the best shot for the tracking
object is based on proposed evaluation metric, consisting of
dimensional, locational and reliability parameters gathered
from object tracking methods. For latency optimization and
accuracy of evaluation the prediction of evaluation metric was
outlined. Solution is experimentally tested in standard and
mobile environment as well. Approach described in this paper is
innovative regarding the content related video stream delivery.
Index Terms—Computer vision, live streaming,
multi-cameras systems, object tracking.
The authors are with the Computer Networks Laboratory at Technical
University of Kosice, Slovakia (e-mail: {david.cymbalak, ondrej.kainz,
frantisek.jakab}@cnl.sk).
[PDF]
Cite:Dávid Cymbalák, Ondrej Kainz, and František Jakab, "Extended Object Tracking and Stream Control Model Based on Predictive Evaluation Metric of Multiple-Angled Streams," International Journal of Computer Theory and Engineering vol. 7, no. 5, pp. 343-348, 2015.
