层叠式SOM神经网络星图识别算法及FPGA验证

为了对空间天文望远镜精细导星仪获得的星图完成识别, 提出一种层叠式自组织映射(SOM)神经网络算法模型, 将该模型在硬件中实现星特征矢量匹配算法。首先, 针对精细导星仪的特点详细介绍了导航星库的建立、星特征矢量的构建和筛选方法; 其次, 建立层叠式 SOM神经网络模型, 对其权值进行在线训练; 最后, 设计算法离线运行硬件电路并将其在 FPGA中实现。仿真与测试结果表明, 基于层叠式自组织神经网络的星图识别算法识别率高、抗噪声能力强、识别速度快。星点位置噪声为 0.648., 星等噪声为 0.18视星等条件下星图识别成功率在 80%以上, 新算法在 FPGA中运行速度是 PC机上传统三角形法的 100倍。对精细导星仪星图识别算法的优化设计提供了合理可行的参考依据。

Abstract

Astacked SOM neural network algorithm model is proposed for star identification, which is needed by fine guidance sensors, and the model is implemented in hardware to implement the star feature vector matching algorithm. Firstly, the method of establishment of the navigation star library and the construction of the star feature vector are introduced in detail. Then, the stacked SOM neural network model is put forward and the weights are trained online. Finally, the hardware circuits of the new algorithm are designed and implemented in the FPGA. The simulation and test results show that the star pattern recognition algorithm based on the stacked SOM neural network has a high recognition rate, strong anti-noise capacity, and fast recognition speed. The star map recognition success rate under harsh conditions is more than 80%, and the recognition speed is 100 times more than that of traditional methods that run in PCs. This research provides a reference for the design of fine guidance sensor star image recognition algorithms.

参考文献

[1] 时圣革, 雷肖剑, 于长海. 星图识别三角形算法综述 [J].光电技术应用, 2014, 29(5): 1-6.

SHI Shengge, LEI Xiaojian, YU Changhai. Triangle algorithm overview of star pattern recognition[J]. Electro-optic TechnologyApplication, 2014, 29(5):1-6.

[2] Craig L. Cole, John L, Crassidis. Fast star pattern recognition using spherical triangles[J]. Providence RI:AIAA, 2004, 29(1): 64-71.

[3] 张磊, 何昕, 魏仲慧, 等. 三角形星图识别算法的改进 [J].光学精密工程, 2010, 18(2): 458-463.

ZHANG Lei, HE Xin, WEI Zhonghui, et al. Modification of triangle identification algorithm[J]. Optics and Precision Engineering, 2010, 18(2): 458-463.

[4] 李辉, 王安国, 张磊. 改进金字塔算法用于小视场星图识别 [J].应用光学, 2013, 34(2):267-272.

LI Hui, WANG Anguo, ZHANG Lei. Modified pyramid algorithm for small FOV star Image recognition[J]. Journal of Applied Optics, 2013, 34(2): 267-272.

[5] 钱华明, 孙龙, 蔡佳楠, 等. 星图识别的一种扩充栅格算法 [J].哈尔滨工业大学学报, 2015, 47(2):110-116.

QIAN Huaming, SUN Long, CAI Jianan, et al. An extended grid algorithm in star identification field[J]. Journal of Harbininstitute of Technology, 2015, 47(2):110-116.

[6] 张少迪, 王延杰, 孙宏海. 三角剖分以及径向基函数神经网络在星图识别中的应用[J].光学精密工程, 2012, 20(2): 395-402.

ZHANG Shaodi, WANG Yanjie, SUN Honghai. Application of triangulation and RBF neural network to star pattern recognition[J]. Optics and Precision Engineering, 2012, 20(2): 395-402.

[7] 江浩, 樊晓宇. 基于 FPGA 的局部天区星图识别技术 [J].导弹与航天运载技术, 2013, 20(1): 68-70.

Jiang Hao, Fan Xiaoyu. Local area star identification by FPGA[J]. Missiles AND Space Vehicles, 2013, 20(1): 68-70.

[8] 王一木, 潘赟, 龙彦辰, 等. 基于自组织映射的手写数字识别的并行实现[J].浙江大学学报: 工学版, 2014, 48(4): 742-747.

WANG Yimu, PAN Yun, LONG Yanchen, et al. Parallel implementation of handwritten digit recognition system using self-organizing map[J]. Journal of Zhejiang University: Engineering Science, 2014, 48(4): 742-747.

[9] 夏飞, 罗志疆, 张浩, 等. 混合神经网络在变压器故障诊断中的应用 [J].电子测量与仪器学报, 2017, 31(1): 118-124.

XIA Fei, LUO Zhijiang, ZHANG Hao, et al. Application of mixed neural network in transformer fault diagnosis[J]. Journal of Electronic Measurement and Instrumentation, 2017, 31(1): 118-124.

[10] 邹瑜, 帅仁俊. 基于改进的 SOM神经网络的医学图像分割算法 [J].计算机工程与设计, 2016, 37(9):2533-1537.

ZOU Yu, SHUAI Renjun. Improved segmentation algorithm of medical images based on SOM neural network[J]. Computer Engineering and Design, 2016, 37(9): 2533-1537.

郑天宇, 尹达一, 赵玥皎. 层叠式SOM神经网络星图识别算法及FPGA验证[J]. 红外技术, 2018, 40(3): 246. ZHENG Tianyu, YIN Dayi, ZHAO Yuejiao. Star Pattern Recognition Algorithm and FPGA Verification of Stacked SOM Neural Network[J]. Infrared Technology, 2018, 40(3): 246.

层叠式SOM神经网络星图识别算法及FPGA验证

关于本站 Cookie 的使用提示

全站搜索

层叠式SOM神经网络星图识别算法及FPGA验证

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索