作者: A. de la Escalera , J.Ma Armingol , M. Mata
DOI: 10.1016/S0262-8856(02)00156-7
关键词:
摘要: Abstract This paper deals with object recognition in outdoor environments. In this type of environments, lighting conditions cannot be controlled and predicted, objects can partially occluded, their position orientation is not known a priori. The chosen traffic or road signs, due to usefulness for sign maintenance, inventory highways cities, Driver Support Systems Intelligent Autonomous Vehicles. A genetic algorithm used the detection step, allowing an invariance localisation changes position, scale, rotation, weather conditions, partial occlusion, presence other same colour. neural network achieves classification. global system only recognises but also provides information about its condition state.