Research of camera calibration based on genetic algorithm BP neural network

摘要

Camera calibration is necessary in machine vision application field. Calibration model has nonlinear characteristics, and establishment of mathematical model is often a complicated process, but neural network can solve the complex nonlinear problem effectively, neural network has strong nonlinear approximation ability, adaptive network parameters and fast learning. This paper presents a neurocalibration approach about camera calibration based on back propagation (BP) neural network optimized by genetic algorithm (GA), GA can optimize net parameters about connection weights and threshold values. Making a comprehensive comparison between GA-BP neural network and BP neural network. The experimental results show that the GA-BP neurocalibration can be effective and feasible by this way.