Title :
Object color propagation in an unregistered distributed video sensor network
Author :
Venkataraman, Vijay ; Srinivasan, Subeshan ; Stefanidis, Antony
Author_Institution :
Dept. of Spatial Inf. Sci. & Eng., Maine Univ., Orono, ME, USA
Abstract :
In this paper we address the use of object color characteristics as a predominant linking parameter between disjoint video scenes in unregistered distributed video sensor networks. In our approach we proceed by tracking objects in high-resolution video scenes using accumulated frame differencing and morphological techniques. We continue by minimizing shadow effects in object tracking through background detection, in order to obtain more accurate object color signatures. These signatures are then used to link trajectory fragments across disjoint video feeds in a sensor network. We present experimental results to demonstrate the performance of our approach, especially addressing the effect of resolution in tracking, and the role of color signatures as a key linking element when video scene registration is not possible.
Keywords :
image colour analysis; image registration; image resolution; image sensors; object detection; accumulated frame differencing; background detection; disjoint video scene; high-resolution video scene; morphological technique; object color propagation; object color signature; object tracking; predominant linking parameter; unregistered distributed video sensor network; video scene registration; Cameras; Feeds; Intelligent networks; Joining processes; Layout; Motion analysis; Object detection; Optical sensors; Temperature sensors; Tracking;
Conference_Titel :
Image Processing, 2004. ICIP '04. 2004 International Conference on
Print_ISBN :
0-7803-8554-3
DOI :
10.1109/ICIP.2004.1421707