一种航天器图像分类模型快速学习方法
|
摘要
为了有效分类空间目标,提出了一种航天器图像分类模型快速学习方法。分类模型的学习过程利用了分治思想,首先利用无监督聚类方法将图像数据集散列为类别桶,然后利用每个类别桶中的图像样本训练支持向量机完成学习过程。分类时利用支持向量机对待分类图像样本进行分类。实验结果表明,所提方法具有较好的实时性和准确率,能够为空间应用打下良好基础。
A fast learning method is proposed for spacecraft image classification. Dividing and conquering strategy is introduced at the learning process. Images are firstly hashed into different bins by the unsupervised clustering method. Then support vector machine(SVM) is trained by the bins to finish the learning progress. SVM is used to directly classify the images. Experimental results indicate that the proposed method features real time classification and high accuracy, which provides a good fundamental for future spacial application.
A fast learning method is proposed for spacecraft image classification. Dividing and conquering strategy is introduced at the learning process. Images are firstly hashed into different bins by the unsupervised clustering method. Then support vector machine(SVM) is trained by the bins to finish the learning progress. SVM is used to directly classify the images. Experimental results indicate that the proposed method features real time classification and high accuracy, which provides a good fundamental for future spacial application.
引文
[1] 李洪.智慧火箭发展路线思考[J].宇航总体技术,2017,1(1):1-7.
[2] 高庆,刘金国,张飞宇,等.面向月面探测的空间机器人-航天员手势交互方法的研究[J].载人航天,2018(3):321-326.
[3] 陈洋波,窦鹏,张涛.基于Landsat的多分类器集成遥感影像分类[J].测绘科学,2018(8):97-103.
[4] 兰巍,贾素玲,宋世民,等.基于随机森林的航天器电信号多分类识别方法[J].北京航空航天大学学报,2017(9):1773-1778.
[5] 姚远,姜志国,张浩鹏.基于层次化分类器的遥感图像飞机目标检测[J].航天返回与遥感,2014,35(5):88-94.
[6] 刘鹏,叶志鹏,赵巍,等.一种多层次抽象语义决策图像分类方法[J].自动化学报,2015,41(5):960-969.
[7] Jin W,Li Z J,Wei L S,et al.The improvements of BP neural network learning algorithm[C].Proceedings of the 5th International Conference on Signal Processing.16th World Computer Congress,2000:3:1647-1649.
[8] Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[9] Hinton G E,Osindero S,Teh Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[10] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[11] Li L J,Wang G,Li F F.Optimol:automatic online picture collection via incremental model learning[C].IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8.
[12] Everingham M,Van Gool L,Williams C K,et al.The pascal visual object classes (voc) challenge[J].International Journal of Computer Vision,2010,88(2):303-338.
[13] Li F F,Fergus R,Perona P.Learning generative visual models from few training examples:An incremental bayesian approach tested on 101 object categories[J].Computer Vision and Image Understan-ding,2007,106(1):59-70.
[14] Fan R E,Chang K W,Hsieh C J,et al.LIBLINEAR:a library for large linear classification[J].Journal of Machine Learning Research,2008,9(9):1871-1874.
[2] 高庆,刘金国,张飞宇,等.面向月面探测的空间机器人-航天员手势交互方法的研究[J].载人航天,2018(3):321-326.
[3] 陈洋波,窦鹏,张涛.基于Landsat的多分类器集成遥感影像分类[J].测绘科学,2018(8):97-103.
[4] 兰巍,贾素玲,宋世民,等.基于随机森林的航天器电信号多分类识别方法[J].北京航空航天大学学报,2017(9):1773-1778.
[5] 姚远,姜志国,张浩鹏.基于层次化分类器的遥感图像飞机目标检测[J].航天返回与遥感,2014,35(5):88-94.
[6] 刘鹏,叶志鹏,赵巍,等.一种多层次抽象语义决策图像分类方法[J].自动化学报,2015,41(5):960-969.
[7] Jin W,Li Z J,Wei L S,et al.The improvements of BP neural network learning algorithm[C].Proceedings of the 5th International Conference on Signal Processing.16th World Computer Congress,2000:3:1647-1649.
[8] Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[9] Hinton G E,Osindero S,Teh Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[10] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[11] Li L J,Wang G,Li F F.Optimol:automatic online picture collection via incremental model learning[C].IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8.
[12] Everingham M,Van Gool L,Williams C K,et al.The pascal visual object classes (voc) challenge[J].International Journal of Computer Vision,2010,88(2):303-338.
[13] Li F F,Fergus R,Perona P.Learning generative visual models from few training examples:An incremental bayesian approach tested on 101 object categories[J].Computer Vision and Image Understan-ding,2007,106(1):59-70.
[14] Fan R E,Chang K W,Hsieh C J,et al.LIBLINEAR:a library for large linear classification[J].Journal of Machine Learning Research,2008,9(9):1871-1874.