基于非线性模型的神经网络非均匀性校正方法

在低照度成像的短波红外相机中, 像元响应存在非线性问题。为了克服传统的神经网络自适应校正方法只能进行线性校正的不足, 提出了一种基于非线性模型的 BP神经网络非均匀性校正算法, 针对单一像元通过隐含层多神经元拟合像元校正曲线, 有效降低拟合误差, 并通过实验验证了算法的合理性。结果表明, 改进算法在图像的局部非均匀性, 粗糙度方面相较于传统算法分别降低了 27%和 28%, 非线性响应像元校正曲线拟合误差降为传统算法的 30%。

Abstract

In most short-wave infrared imaging systems working at low irradiance conditions, pixels work in a nonlinear manner. Considering that the traditional neural network correction methods are only applicable to linear responses, a new back propagation neural network non-uniformity correction (NUC) algorithm was proposed based on a nonlinear model. The three layers of neural networks were used to fit the correction curve of one single pixel, which effectively reduced the fitting error. Experiments were performed to verify the rationality of the proposed algorithm. The results demonstrated that it outperformed the traditional method on the local non-uniformity, roughness, and fitting error of the correction curve by 27%, 28% and 30%, respectively, for a single pixel.

参考文献

[1] 曹杨, 金伟其, 王霞, 等. 短波红外焦平面探测器及其应用进展[J].红外技术, 2009, 31(2): 63-68.

CAO Yang, JIN Weiqi, WANG Xia, et al. Development in Shortwave Infrared Focal Plane Array and Application[J]. Infrared Technology, 2009, 31(2): 63-68.

[2] 周建勋, 王利平, 刘滨. 红外图像非均匀性产生原因分析[J]. 红外与激光工程, 1997, 26(3): 11-13.

ZHOU Jianxun, WANG Liping, LIU Bin. Analysis of the Cause for the Uniformity of Infrared Image[J]. Infrared and Laser Engineering, 1997, 26(3): 11-13.

[3] 袁红辉, 陈永平 . 非制冷红外探测器读出电路的非均匀性研究[J].物理学报, 2015, 64(11): 118503.

YUAN Honghui, CHEN Yongping. Non-uniformity study on readout circuit for uncooled IR detector[J]. Acta Phys. Sin., 2015, 64(11): 118503.

[4] 张学峰, 陈宝国, 樊养余, 等. 基于场景的红外非均匀性校正算法对比研究[J].红外技术, 2013, 35(9): 560-566.

ZHANG Xuefeng, CHEN Baoguo, FAN Yangyu, et al. Comparison of Scene-based IRFPA Nonuniformity Correction Algorithms[J]. Infrared Technology, 2013, 35(9): 560-566.

[5] 董立泉, 金伟其, 隋婧. 基于场景的红外焦平面阵列非均匀性校正算法综述[J].光学技术, 2008, 34: 113-122.

DONG Liquan, JIN Weiqi, SUI Jing, et al. Study on the scene-based non-uniformity correction algorithms for IRFPA[J]. Optical Technique, 2008, 34: 113-122.

[6] 石岩, 张天序, 李辉, 等. 一种考虑红外焦平面器件非线性响应的非均匀性校正方法[J].红外与毫米波学报, 2004, 23(4): 251-256.

SHI Yan, ZHANG Tianxu, LI Hui, et al. New Approach to Nonuniformity Correction of IRFPA with Nonlinear Response[J]. J. Infrared Millim. Waves, 2004, 23(4): 251-256.

[7] ZHOU H X, LAI R, LIU S Q, et al. New improved nonuniformity correction for infrared focal plane arrays[J]. Optics Communications, 2005, 245(1-6): 49-53.

[8] 周达标, 王德江, 霍丽君, 等. 基于梯度场景的非均匀校正方法[J].光学学报, 2017, 37(5): 028001.

ZHOU Dabiao, WANG Dejiang, HUO Lijun, et al. Nonuniformity Correction Method Based on Gradient Scenes[J]. Acta Optic Sinica, 2017, 37(5): 028001.

[9] Scribner D A, Sarkady K A, Caufield J T. Nonuniformity correction for staring IR focal plane arrays using scene-based techniques[C]// Proceeding of SPIE-The International Society for Optical Engineering, 1990, 1308: 224-233.

[10] 王建军, 徐宗本. 多元多项式函数的三层前向神经网络逼近方法[J]. 计算机学报, 2009, 32(12): 2482-2488.

WANG Jianjun, XU Zongben. Approximation Method of Multivariate Polynomials by Feed forward Neural Networks[J]. Chinese Journal of Computers, 2009, 32(12): 2482-2488.

[11] 崔坤, 陈凡胜, 苏晓峰, 等. 自适应积分时间改变的红外焦平面非均匀校正方法[J].红外与激光工程, 2017, 46(11): 1104001.

CUI Kun, CHEN Fansheng, SU Xiaofeng, et al. Adaptive non-uniformity correction method for IRFPA with integration time changing[J]. Infrared and Laser Engineering, 2017, 46(11): 1104001.

[12] SUI Jing, DONG Liquan, JIN Weiqi, et al. A new adaptive nonuniformity correction algorithm for infrared line scanner based on neural networks[J]. Chin. Opt. Lett., 2007, 5(2): 74-76.

程起森, 张元涛, 孙德新. 基于非线性模型的神经网络非均匀性校正方法[J]. 红外技术, 2018, 40(9): 868. CHENG Qisen, ZHANG Yuantao, SUN Dexin. An Improved Neural Network Non-uniformity Correction Algorithm Based on Non-linear Model[J]. Infrared Technology, 2018, 40(9): 868.

基于非线性模型的神经网络非均匀性校正方法

关于本站 Cookie 的使用提示

全站搜索

基于非线性模型的神经网络非均匀性校正方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索