CAJ | 학술논문

在大视场光电测量系统中,由于光学系统畸变的影响使得目标在线阵CCD上的成像偏离了理论成像点,导致系统产生测量误差,为了提高测量精度,必须进行畸变校正.根据畸变光学原理,利用BP神经网络对非线性畸变进行良好的逼近,通过对由畸变测量装置获得的数据进行训练建立网络模型,从而建立整个视场畸变校正的数学模型.实验结果表明,当目标物高为200.115 mm时,利用BP神经网络方法,可将畸变误差从校正前的-2.080 mm提高到校正后的-0.104 mm,使得整体检测精度从1.039%提高到0.052%.
재대시장광전측량계통중,유우광학계통기변적영향사득목표재선진CCD상적성상편리료이론성상점,도치계통산생측량오차,위료제고측량정도,필수진행기변교정.근거기변광학원리,이용BP신경망락대비선성기변진행량호적핍근,통과대유기변측량장치획득적수거진행훈련건립망락모형,종이건립정개시장기변교정적수학모형.실험결과표명,당목표물고위200.115 mm시,이용BP신경망락방법,가장기변오차종교정전적-2.080 mm제고도교정후적-0.104 mm,사득정체검측정도종1.039%제고도0.052%.
In the big visual field photoelectric measuring system,distortion produced by optical system makes the image of objects on the linear CCD deviate from the theoretical point and lead to the system measuring error.In the practical measuring system,in order to improve measurement precision,distortion correction is necessary.According to optical theory of distortion and utilizing BP neural network to approach nonlinear distortion,distortion correction mathematic model of whole field was set up through training the distortion measurement data which were measured by distortion detection device.This device has eleven equidistance points of laser goals and is designed based on the basis of distortion mechanism and radical character.The distortion correction method based on BP neural network can realize high precision of correction without knowing the mathematic model.The experiment result shows that the device can reduce error obviously from -2.08 mm to -0.104 mm according to the BP neural network correction when the object height is 200.115 mm,and raise the whole systematic detection precision from 1.039% to 0.052%.