|
|
论文:2012,Vol:30,Issue(6):886-891 |
|
|
引用本文： |
|
|
余瑞星, 袁博, 宋军艳. 一种新的时空局部特征提取方法及在目标识别中的应用[J]. 西北工业大学 |
|
|
Yu Ruixing, Yuan Bo, Song Junyan. A New and Effective Spatio-Temporal Local Feature Extraction Method and Its Application in Target Recognition[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 一种新的时空局部特征提取方法及在目标识别中的应用 |
|
| 余瑞星, 袁博, 宋军艳 |
|
| 西北工业大学 航天学院, 陕西 西安 710072 |
| 摘要: |
| 针对大多数特征提取算法忽略时间因素对识别精度影响这一问题,提出了一种新的时空局部特征提取方法。首先采用Harris算子提取关键点并估算出该关键点处的尺度,并使用无迹卡尔曼滤波器对关键点处的位置进行跟踪,获取不同时刻下的关键点簇;再采用小波系数描述关键点簇的特征区域、采用SSD衡量关键点簇上相邻两时刻特征向量的相似度,并保留随时间推移SSD值变化缓慢的关键点簇;最后使用高斯统计模型对这些关键点簇的特征向量进行统计建模,获取时空局部特征。实验结果表明,文中方法的目标识别精度高于基于SIFT的目标识别精度约10%。 |
| 关键词:
时空局部特征
高斯混合模型
无迹卡尔曼滤波器
目标识别
|
|
| A New and Effective Spatio-Temporal Local Feature Extraction Method and Its Application in Target Recognition |
|
| Yu Ruixing, Yuan Bo, Song Junyan |
|
| College of Astronautics,Northwestern Polytechnical University,Xi'an 710072,China |
| Abstract: |
| Almost all the feature extraction algorithms ignore that classification accuracy varies, though slowly,withtime. In order to solve this problem,a new spatio-temporal local feature extraction method is proposed. Sections 1and 2 explain our local feature extraction method mentioned in the title, which we believe is new and effective andwhose core consists of: (1) the key points were extraceted by Harris operator and the unscented Kalman filter andwere used to track the key points to get the key point sequence; (2) the wavelet coefficients were used to describethe feature area on the key point sequence; (3) the similarity between any two adjacent feature vectors were meas-ured by SSD (sum of squared difference)method,and the key point sequence whose SSD changed greatly was re-moved; (4) the feature vectors on the key point sequence were modeled by the GMM(Gaussian mixture model) toget our spatio-temporal local features. Finally, the experimental results, given in Fig. 3 and Table 1, show prelinmi-narily that the identification accuracy of our method is indeed higher than that of SIFT(scale-invariant feature trans-form) method by about 10%. |
| Key words:
classification(of information)
feature extraction
image recongnition
mathematical models
nonlin-ear systems
targets;GMM(Gaussian mixture model)
spatio-temporal local feature extraction
targetrecognition
|
|
| 收稿日期: 2011-12-15
修回日期:
|
| DOI: |
| 基金项目: 国家自然科学基金(61101191);西北工业大学基础研究基金(JC20120216);陕西省自然科学基金(2011JQ8016);西北工业大学种子基金资助 |
| 通讯作者:
Email： |
| 作者简介: 余瑞星(1978-)，女，西北工业大学副教授，主要从事图像处理、目标识别及仿生技术的研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 余瑞星 在本刊中的所有文章 |
| 袁博 在本刊中的所有文章 |
| 宋军艳 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Ivan Laptev.On Space-Time Interest Point.International Journal of Computer Vision, 2005, 64(2/3): 107-123
[2] 张博宇，刘家锋，唐降龙.一种基于时空兴趣点的人体动作识别方法.自动化技术与应用, 2009, 28(10): 75-78Zhang Boyu，Liu Jiafeng，Tang Xianglong.Human Motion Recognition Based on Spatio-Temporal Interest Point.Pattern Recog-nition and Simulation, 2009, 28(10): 75-78 (in Chinese)
[3] 韩 磊, 李君峰, 贾云得.基于时空单词的两人交互行为识别方法.计算机学报, 2010, 33(4): 776-783Han Lei，Li Junfeng，Jia Yunde.Human Interaction Recognition Using Spatio-Temporal Words.Chinese Journal of Computers，2010, 33(4): 776-783 (in Chinese)
[4] Harris C，Steven M.A Combined Corner and Edge Detector.Proceedings of the Conference on Alvey Vision, 1988, 189-192
[5] Lindeberg T.Feature Detection with Automatic Scale Selection.Technical Report，CVAP，Department of Numerical Analysisand Computing Science, 1998, 79-116
[6] Mallat S.A Theory for Multiresolution Signal Decomposition: the Wavelet Representation.IEEE Trans on Pattern Anal Mach In-tell, 1989, 11(7):674-693
[7] Wan E，Van R der Merwe.The Unscented Kalman Filter for Nonlinear Estimation.IEEE Symp on Adaptive Systems for SignalProcessing，Communication and Control, 2000, 153-158
[8] Roberts S J.Bayesian Approaches to Gaussian Mixture Modeling.IEEE Trans on Pattern Analysis and Machines Intelligence，1998, 20 (11): 1133-1142
[9] Lowe D.Distinctive Image Features from Scale-Invariant Keypoints.International Journal of Computer Vision，2004，60(2):91-110 |
|
|
|
|
|
|
|
