A swarm cognition realization of attention, action selection, and spatial memory
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Tracking natural trails with swarm-based visual saliency
Journal of Field Robotics
Neural-swarm visual saliency for path following
Applied Soft Computing
Hi-index | 0.00 |
A major obstacle in real-time performance of a visual tracking system is its initialization phase. Inspired by social behavior in fish and ant groups, a fast self-organization approach to active-contour initialization is proposed. Contours are emerged during two separate phases of aggregation and self-assembly. Aggregation is achieved by a superposition of simpler behaviors, hunting, avoidance, and opportunism. Self-assembly, which constitutes the explicit contour formation, occurs by mating behavior when the swarm becomes quite stable. Experiments indicate that the proposed method outperforms exhaustive image search for finding contours in high resolutions. © 2006 Wiley Periodicals, Inc. Complexity 12: 41–52, 2006This paper was submitted as an invited paper resulting from the “Understanding Complex Systems” conference held at the University of Illinois–Urbana Champaign, May 2005