基于神经网络的全天时天文导航图像去噪方法
|
摘要
全天时天文导航图像是在大气层内白天的条件下拍摄,因此图像具有强背景,低信噪比等特点,传统星点提取算法对图像星点的提取效果较差。为提高星点识别率,提出一种较准确的全天时天文导航图像模拟方法,并基于模拟星图训练了一种可加入图像降采样结构的卷积神经网络,有效抑制了星图噪声,并提高了星点信噪比。实验结果表明:本文方法得到的峰值信噪比平均提高了11.28 dB;在效果相同的条件下,本文方法的平均处理时间仅为0.2 s,远少于传统神经网络方法的处理时间。利用真实星图对网络进行测试,发现本文方法对星点信噪比的提升效果较常用算法提升了88.9倍。
Typically, star images captured in the atmosphere during daylight hours have a strong background and low signal-to-noise ratio(SNR), which makes it difficult for traditional algorithms to extract the star from the images. To improve the recognition rate, we propose an accurate method for simulating star images and train a deep convolutional neural network with a downsampling layer using the simulated images. The trained network can denoise and enhance the star images. Experimental results demonstrate that the proposed method improves the peak SNR by 11.28 dB within an average runtime of 0.2 s, which is significantly less than that of a traditional neural network. In addition, we test the proposed method on the trained network using real star images and find that the improved SNR is 88.9 times greater than that of the existing methods.
Typically, star images captured in the atmosphere during daylight hours have a strong background and low signal-to-noise ratio(SNR), which makes it difficult for traditional algorithms to extract the star from the images. To improve the recognition rate, we propose an accurate method for simulating star images and train a deep convolutional neural network with a downsampling layer using the simulated images. The trained network can denoise and enhance the star images. Experimental results demonstrate that the proposed method improves the peak SNR by 11.28 dB within an average runtime of 0.2 s, which is significantly less than that of a traditional neural network. In addition, we test the proposed method on the trained network using real star images and find that the improved SNR is 88.9 times greater than that of the existing methods.
引文
[1] Fan Q Y,Li X J.Selection of optical-system parameters for an all-day used star sensor[J].Acta Optica Sinica,2011,31(11):1122001.樊巧云,李小娟.全天时星敏感器光学系统设计参数选择[J].光学学报,2011,31(11):1122001.
[2] Liu Y,Dai D K,Ma L H,et al.A star sensor calibration method based on attitude correlated frame[J].Acta Optica Sinica,2017,37(11):1128003.刘宇,戴东凯,马丽衡,等.一种基于姿态关联帧的星敏感器标定方法[J].光学学报,2017,37(11):1128003.
[3] Xu Q,Zhao C H,Li X.Stellar radiation modeling and image simulation for airborne daytime star sensor[C]∥2016 IEEE International Conference on Signal and Image Processing (ICSIP),August 13-15,2016,Beijing,China.New York:IEEE,2016:630-635.
[4] Duncan T M.A daylight stellar sensor using a charge-coupled device[J].Proceedings of SPIE,1989,1111:2-14.
[5] Jiang P,Sun T F.Infrared star target detection based on maximum energy in daytime[J].Infrared,2013,34(6):34-38.姜鹏,孙腾飞.基于最大能量法的白天红外星目标检测[J].红外,2013,34(6):34-38.
[6] Hu X D,Hu Q,Lei X,et al.Method of star centroid extraction used in daytime star sensors[J].Journal of Chinese Inertial Technology,2014,22(4):481-485.胡晓东,胡强,雷兴,等.一种用于白天星敏感器的星点质心提取方法[J].中国惯性技术学报,2014,22(4):481-485.
[7] Wei W,Liu E H.Preprocessing of infrared star map and position accuracy analysis of star point[J].Infrared and Laser Engineering,2014,43(3):991-996.魏伟,刘恩海.红外星图预处理及星点定位精度分析[J].红外与激光工程,2014,43(3):991-996.
[8] Wang W J,Wei X G,Li J,et al.Noise suppression algorithm of short-wave infrared star image for daytime star sensor[J].Infrared Physics & Technology,2017,85:382-394.
[9] Han L,Cai H.Analysis of stargazing capability of star sensors from the atmosphere in daytime[J].Journal of Spacecraft TT & C Technology,2015,34(3):291-297.韩礼,蔡洪.白天大气层内星敏感器观星能力分析[J].飞行器测控学报,2015,34(3):291-297.
[10] Zhang K,Zuo W M,Chen Y J,et al.Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising[J].IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[11] Chen Y J,Pock T.Trainable nonlinear reaction diffusion:a flexible framework for fast and effective image restoration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1256-1272.
[12] Ioffe S,Szegedy C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]∥Proceedings of the 32nd International Conference on International Conference on Machine Learning,July 6-11,2015,Lille France.Cambridge:JMLR.org,2015,37:448-456.
[13] He K M,Zhang X Y,Ren S Q,et al.Identity mappings in deep residual networks[M]//Leibe B,Matas J,Sebe N,et al.Computer Vision-ECCV 2016.Cham:Springer,2016,9908:630-645.
[14] Shi W Z,Caballero J,Huszár F,et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition,June 27-30,2016,Las Vegas,NV,USA.New York:IEEE,2016:1874-1883.
[15] Zhang Y M,Chen T.Efficient inference for fully-connected CRFs with stationarity[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition,June 16-21,2012,Providence,RI,USA.New York:IEEE,2012:582-589.
[16] Dabov K,Foi A,Katkovnik V,et al.Image denoising by sparse 3-D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080-2095.
[17] Aharon M,Elad M,Bruckstein A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[2] Liu Y,Dai D K,Ma L H,et al.A star sensor calibration method based on attitude correlated frame[J].Acta Optica Sinica,2017,37(11):1128003.刘宇,戴东凯,马丽衡,等.一种基于姿态关联帧的星敏感器标定方法[J].光学学报,2017,37(11):1128003.
[3] Xu Q,Zhao C H,Li X.Stellar radiation modeling and image simulation for airborne daytime star sensor[C]∥2016 IEEE International Conference on Signal and Image Processing (ICSIP),August 13-15,2016,Beijing,China.New York:IEEE,2016:630-635.
[4] Duncan T M.A daylight stellar sensor using a charge-coupled device[J].Proceedings of SPIE,1989,1111:2-14.
[5] Jiang P,Sun T F.Infrared star target detection based on maximum energy in daytime[J].Infrared,2013,34(6):34-38.姜鹏,孙腾飞.基于最大能量法的白天红外星目标检测[J].红外,2013,34(6):34-38.
[6] Hu X D,Hu Q,Lei X,et al.Method of star centroid extraction used in daytime star sensors[J].Journal of Chinese Inertial Technology,2014,22(4):481-485.胡晓东,胡强,雷兴,等.一种用于白天星敏感器的星点质心提取方法[J].中国惯性技术学报,2014,22(4):481-485.
[7] Wei W,Liu E H.Preprocessing of infrared star map and position accuracy analysis of star point[J].Infrared and Laser Engineering,2014,43(3):991-996.魏伟,刘恩海.红外星图预处理及星点定位精度分析[J].红外与激光工程,2014,43(3):991-996.
[8] Wang W J,Wei X G,Li J,et al.Noise suppression algorithm of short-wave infrared star image for daytime star sensor[J].Infrared Physics & Technology,2017,85:382-394.
[9] Han L,Cai H.Analysis of stargazing capability of star sensors from the atmosphere in daytime[J].Journal of Spacecraft TT & C Technology,2015,34(3):291-297.韩礼,蔡洪.白天大气层内星敏感器观星能力分析[J].飞行器测控学报,2015,34(3):291-297.
[10] Zhang K,Zuo W M,Chen Y J,et al.Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising[J].IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[11] Chen Y J,Pock T.Trainable nonlinear reaction diffusion:a flexible framework for fast and effective image restoration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1256-1272.
[12] Ioffe S,Szegedy C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]∥Proceedings of the 32nd International Conference on International Conference on Machine Learning,July 6-11,2015,Lille France.Cambridge:JMLR.org,2015,37:448-456.
[13] He K M,Zhang X Y,Ren S Q,et al.Identity mappings in deep residual networks[M]//Leibe B,Matas J,Sebe N,et al.Computer Vision-ECCV 2016.Cham:Springer,2016,9908:630-645.
[14] Shi W Z,Caballero J,Huszár F,et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition,June 27-30,2016,Las Vegas,NV,USA.New York:IEEE,2016:1874-1883.
[15] Zhang Y M,Chen T.Efficient inference for fully-connected CRFs with stationarity[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition,June 16-21,2012,Providence,RI,USA.New York:IEEE,2012:582-589.
[16] Dabov K,Foi A,Katkovnik V,et al.Image denoising by sparse 3-D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080-2095.
[17] Aharon M,Elad M,Bruckstein A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.