A Combination of Multiple Deep Learning Methods Applied to Small-Sample Space Objects Classification
DENG Shi-yu1, 2, LIU Cheng-zhi1, 4*, TAN Yong3*, LIU De-long1, ZHANG Nan1, KANG Zhe1, LI Zhen-wei1, FAN Cun-bo1, 4, JIANG Chun-xu3, LÜ Zhong3
1. Changchun Observatory of National Astronomical Observators, Chinese Academy of Sciences, Changchun 130117, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. School of Science, Changchun University of Science and Technology, Changchun 130022, China
4. Key Laboratory of Space Object & Debris Observation, PMO, CAS, Nanjing 210008, China
Abstract：With the continuous improvement of the sensitivity, accuracy and easy use of spectral detection instruments in recent years, spectral technology has penetrated the identification and analysis of material components in all walks of life. Spectral observation of space targets is one of the important extensions of traditional optical observations. It has attracted much attention due to its non-contact and damage-free advantages. However, due to the limited observation conditions, the amount of spectral data of space targets is minimal. Traditional methods cannot achieve better results in classification analysis. In this paper, Firstly, the hyperspectral image of the space target is obtained through the spectroscopic camera terminal mounted on the 1.2 m space target optical telescope; Secondly, the one-dimensional spectral data of the space target is extracted through the astronomical photometric IRAF method; Finally, the combination of multiple deep learning methods, classify the spectral data of space targets. Accordingly, this paper proposes a combination of multiple deep learning methods to solve small sample data’s spatial object classification problem. This method uses Density Clustering method to roughly classify spatial targets, one-dimensional Generative Adversarial Network method to generate spatial target data, one-dimensional Convolutional Neural Network method to finely classify spatial targets, the combination of three methods can achieve relatively good experimental results and overall accuracy is about 79.1% (Based on the combination of Density Clustering, Oversampling, one-dimensional Convolutional Neural Network methods; Based on the combination of K-means, one-dimensional Generative Adversarial Network, one-dimensional Convolutional Neural Network methods; Based on the combination of K-means, Oversampling, One-dimensional Convolutional Neural Network methods, the overall accuracy is about 78.4%, 77.9%, 77.2%). In the rough classification model, the overall accuracy of the Density Clustering method is about 0.67% higher than the K-means method; In the data augmentation model, the overall accuracy of the one-dimensional Generative Adversarial Network method is about 1.52% higher than the Oversampling method; In the fine classification model, the two-layer network of the one-dimensional Convolutional Neural Network method has an average accuracy of only about 0.003% higher than the three-layer network, but the calculation time is longer. The accuracy of the four combined methods are higher than the single method. The experimental results show that the combination method proposed in this paper can achieve fine classification and high accuracy when the small sample space target category is unknown. It provides a certain reference value for realizing the integrated analysis of the map under the minimal data volume of the space target.
Key words：Space targets; Spectral data; Density based spatial clustering of applications with noise; Generative adversarial networks; Convolutional neural networks
邓诗宇，刘承志，谭 勇，刘德龙，张 楠，康 喆，李振伟，范存波，姜春旭，吕 众. 多种深度学习方法组合应用于小样本空间目标分类研究[J]. 光谱学与光谱分析, 2022, 42(02): 609-615.
DENG Shi-yu, LIU Cheng-zhi, TAN Yong, LIU De-long, ZHANG Nan, KANG Zhe, LI Zhen-wei, FAN Cun-bo, JIANG Chun-xu, LÜ Zhong. A Combination of Multiple Deep Learning Methods Applied to Small-Sample Space Objects Classification. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(02): 609-615.
[1] Kim K J, Cho S. Pattern Analysis & Applications, 2015，(18): 553. [2] YAO Yan, SHEN Xiao-min, QIU Qian, et al(姚 燕, 沈晓敏, 邱 倩, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(6): 1857.
[3] Mohiuddin A, Raihan S, Syed M S I. Electronics, 2020, 9(8): 1295.
[4] Rodriguez, Alex, Laio, et al. Science, 2014, 344(6191): 1492.
[5] Rudolf S, Kristian S. Advances in Data Analysis and Classification, 2020，15(1)：83.
[6] LI Yan-xia, CHAI Yi, HU You-qiang, et al(李艳霞, 柴 毅, 胡友强, 等). Control and Decision(控制与决策), 2019, 34(4): 673.
[7] Ghahramani Z, Welling M, Cortes C. NIPS，2014，(2): 2672.
[8] Wang Z, She Q, Ward T E. Generative Adversarial Networks: A Sarvey and Taxonomy, 2019, arXiv: 1906.01529[CS.LG].
[9] Koziarski M, Krawczyk B, Wozniak M. Neurocomputing, 2019，(343): 19.
[10] LeCun Y, Bottou L, Bengio Y, et al. Proceedings of the IEEE, 1998，(86): 2278.
[11] Zheng Z P, Qiu B, Luo A L, et al. Publications of the Astronomical Society of the Pacific, 2020, 132(1008): 024504.
