基于弹性网稀疏编码的空间目标识别

史骏; 姜志国; 冯昊; 张浩鹏; 孟钢

doi:10.7527/S1000-6893.2013.0202

航空学报 >

2013 , Vol. 34 >Issue 5: 1129 - 1139

DOI: https://doi.org/10.7527/S1000-6893.2013.0202

电子与控制

基于弹性网稀疏编码的空间目标识别

史骏 ,
姜志国 ,
冯昊 ,
张浩鹏 ,
孟钢

展开

1. 北京航空航天大学宇航学院, 北京 100191;
2. 数字媒体北京市重点实验室, 北京 100191;
3. 北京遥感信息研究所, 北京 100191

史骏男, 博士研究生。主要研究方向: 模式识别、机器学习和计算机视觉。 Tel: 010-82338061 E-mail: chris.shi331@gmail.com;姜志国男, 博士, 教授, 博士生导师。主要研究方向: 目标检测、跟踪与识别、遥感图像处理和医学图像分析。 Tel: 010-82338061 E-mail: jiangzg@buaa.edu.cn;冯昊男, 博士研究生。主要研究方向: 图像处理、机器学习和计算机视觉。 Tel: 010-82338061 E-mail: fenghao@sa.buaa.edu.cn;张浩鹏男, 博士研究生。主要研究方向: 图像处理、机器学习和计算机视觉。 Tel: 010-82338061 E-mail: buaazhp@126.com;孟钢男, 博士, 工程师。主要研究方向: 图像处理、模式识别、机器学习和嵌入式系统。 E-mail: menggangmark@126.com

收稿日期: 2012-06-11

修回日期: 2012-12-19

网络出版日期: 2013-01-09

基金资助

国家自然科学基金(61071137, 61071138, 61027004);国家"973"计划(2010CB327900)

收起

Elastic Net Sparse Coding-based Space Object Recognition

SHI Jun ,
JIANG Zhiguo ,
FENG Hao ,
ZHANG Haopeng ,
MENG Gang

Expand

1. School of Astronautics, Beihang University, Beijing 100191, China;
2. Beijing Key Laboratory of Digital Media, Beijing 100191, China;
3. Beijing Institute of Remote Sensing Information, Beijing 100191, China

Received date: 2012-06-11

Revised date: 2012-12-19

Online published: 2013-01-09

Supported by

National Natural Science Foundation of China (61071137, 61071138, 61027004); National Basic Research Program of China (2010CB327900)

Fold

摘要

传统的特征袋(BoF)模型在目标识别过程中假设每个局部特征点只关联特征词典中一个视觉单词。此外,l₁范数约束下的稀疏编码对于具有较强成对相关性的特征通常只选择一个特征,而不关注哪一个特征被选择。本文提出一种基于弹性网稀疏编码的特征袋模型。该模型利用尺度不变特征变换(SIFT)特征描述子构建特征字典,再通过弹性网回归模型求解每个描述子所对应的稀疏系数向量,最后将目标图像内的稀疏系数向量合并用于分类。与传统的特征袋模型和基于l₁范数稀疏编码的特征袋模型相比,该模型有较好的识别性能,并对视角变化具有较强的鲁棒性。在空间目标图像数据库上的实验验证了该模型的有效性。

关键词： 特征袋; l₁范数约束; 稀疏编码; 弹性网回归; 空间目标识别; 特征提取

本文引用格式

史骏 , 姜志国 , 冯昊 , 张浩鹏 , 孟钢 . 基于弹性网稀疏编码的空间目标识别[J]. 航空学报, 2013 , 34(5) : 1129 -1139 . DOI: 10.7527/S1000-6893.2013.0202

Abstract

The traditional bag-of-features (BoF) model for object recognition assumes each local feature point is related to only one visual word. Besides, sparse coding with l₁-norm constraint generally selects only one feature without concern for which one is selected. A novel bag-of-features model based on elastic net sparse coding is presented in this paper. The model uses scale invariant feature transform (SIFT) feature descriptors to construct a feature dictionary, and then applies an elastic net regression model to the solution of sparse-coefficient vectors. Finally the sparse-coefficient vectors in each object image are pooled for classification. Compared with the conventional BoF model and the BoF model based on l₁-norm sparse coding, our model achieves better recognition performance and is more robust to the variation of viewpoints. Experiments on the space object image database demonstrate the effectiveness of the proposed model.

Key words： bag-of-features; l₁-norm constraint; sparse coding; elastic net regression; space object recognition; feature extraction

参考文献

[1] Fan J, Li Y C, Sun H Y. The algorithm research of space object identification from multi-viewpoints. Journal of the Academy of Equipment Command & Technology, 2009, 20(6): 55-59. (in Chinese) 樊佳, 李迎春, 孙华燕. 多视点空间目标识别方法研究. 装备指挥技术学院学报, 2009, 20(6): 55-59.
[2] Lu D W, Ma J G, Zhao H K, et al. Space target recognition algorithm based on outline feature. Fire Control and Command Control, 2007, 32(5): 53-56. (in Chinese) 卢大威, 马君国, 赵宏坤, 等. 基于轮廓特征的空间目标识别算法. 火力与指挥控制, 2007, 32(5): 53-56.
[3] Lowe D G. Object recognition from local scale-invariant features. IEEE International Conference on Computer Vision (ICCV), 1999, 2: 1150-1157.
[4] Li F F, Perona P. A Bayesian hierarchical model for learning natural scene categories. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2005, 2: 524-531.
[5] Sharma G, Chaudhury S, Srivastava J B. Bag-of-features kernel eigen spaces for classification. 19th International Conference on Pattern Recognition (ICPR), 2008: 1-4.
[6] Wright J, Ma Y, Mairal J, et al. Sparse representation for computer vision and pattern recognition. Proceedings of the IEEE, 2010, 98(6): 1031-1044.
[7] Yang J C, Yu K, Gong Y H, et al. Linear spatial pyramid matching using sparse coding for image classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009: 1794-1801.
[8] Wang J J, Yang J C, Yu K, et al. Locality-constrained linear coding for image classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 3360-3367.
[9] Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[10] Zou H, Hastie T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2005, 67(2): 301-320.
[11] Tibshirani R. Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 1996, 58(1): 267-288.
[12] Zhang H P, Liu Z Y, Jiang Z G, et al. BUAA-SID1.0 space object image dataset. Spacecraft Recovery & Remote Sensing, 2010, 31(4): 65-71. (in Chinese) 张浩鹏, 刘正一, 姜志国, 等. BUAA-SID1.0空间目标图像数据库. 航天返回与遥感, 2010, 31(4): 65-71.
[13] Meng G, Jiang Z G, Liu Z Y, et al. Full-viewpoint 3D space object recognition based on kernel locality preserving projections. Chinese Journal of Aeronautics, 2010, 23(5): 563-572.
[14] Hu M K. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, 1962, 8(2): 179-187.
[15] Kauppinen H, Seppanen T, Pietikainen M. An experimental comparison of autoregressive and Fourier-based descriptors in 2D shape classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(2): 201-207.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献