Title :
Group stochastic search for object detection and tracking
Author :
Evans, Murray ; Ferryman, James
Author_Institution :
Sch. of Syst. Eng., Reading Univ., UK
Abstract :
A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320×240 resolution video at up to 15 fps.
Keywords :
image resolution; neural nets; object detection; stochastic processes; tracking; video signal processing; group stochastic search; histogram intersection technique; neural network; object detection; object tracking; Cameras; Histograms; Layout; Magnetic heads; Motion detection; Neural networks; Object detection; Stochastic processes; Stochastic systems; Target tracking;
Conference_Titel :
Advanced Video and Signal Based Surveillance, 2005. AVSS 2005. IEEE Conference on
Print_ISBN :
0-7803-9385-6
DOI :
10.1109/AVSS.2005.1577259
