The “fly algorithm” is an individual evolution strategy developed for parameter space exploration in computer vision applications. In the application described, each individual represents a geometrical point in the scene and the population itself is used as a three-dimensional model of the scene. A fitness function containing all pixel-level calculations is introduced to exploit simple optical and geometrical properties and evaluate the relevance of each individual as taking part to the scene representation. Classical evolutionary operators (sharing, mutation, crossover) are used. The combined individual approach and low complexity fitness function allow fast processing. Test results and extensions to real-time image sequence processing, mobile objects tracking and mobile robotics are presented.