Improved methods for fundamental matrix estimation based on evolutionary agents [computer vision applications]

This paper presents two evolutionary agent-based approaches to fundamental matrix estimation. In order to improve the search ability and computational efficiency of the simple evolutionary agent, new methods, the competitive evolutionary agent (CEA) and finite multiple evolutionary agent (FMEA), are proposed by applying better evolutionary strategies and decision rules. CEA mainly focuses on the reproduction behavior and FMEA concentrates on the diffusion process. Experiments show that the improved approaches perform better than the original one in terms of accuracy and speed, and are more robust to noise and outliers.