Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Machine vision
Computer Vision and Image Understanding
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Adaptation on the Evolutionary Time Scale: A Working Hypothesis and Basic Experiments
AE '97 Selected Papers from the Third European Conference on Artificial Evolution
Integrated Surface, Curve and Junction Inference from Sparse 3-D Data Sets
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Dynamic flies: a new pattern recognition tool applied to stereo sequence processing
Pattern Recognition Letters
Dynamic Flies: Using Real-Time Parisian Evolution in Robotics
Proceedings of the EvoWorkshops on Applications of Evolutionary Computing
Robust Multiscale Affine 2D-Image Registration through Evolutionary Strategies
PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Parisian evolution with honeybees for three-dimensional reconstruction
Proceedings of the 8th annual conference on Genetic and evolutionary computation
EvoWorkshops '09 Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG
Mobile robot sensor fusion using flies
EvoWorkshops'03 Proceedings of the 2003 international conference on Applications of evolutionary computing
The honeybee search algorithm for three-dimensional reconstruction
EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing
Hi-index | 0.00 |
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.