基于局部特征提取的目标自动识别

贾平; 徐宁; 张叶

doi:10.3788/OPE.20132107.1898

您当前的位置：

首页 >

文章列表页 >

基于局部特征提取的目标自动识别

信息科学 | 更新时间：2020-08-12

- 基于局部特征提取的目标自动识别
- Automatic target recognition based on local feature extraction
- 光学精密工程 2013年21卷第7期页码：1898-1905
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所中国科学院航空光学成像与测量重点实验室,吉林长春,130033
  2. 中国科学院大学北京,100039
- 作者简介：
- 基金信息：
  
  国家科学自然基金青年基金()
- DOI：10.3788/OPE.20132107.1898
  中图分类号： TP391
- 收稿日期：2012-04-26，
  
  修回日期：2012-08-06，
  
  网络出版日期：2013-07-15，
  
  纸质出版日期：2013-07-15
- 稿件说明：
移动端阅览
贾平徐宁张叶. 基于局部特征提取的目标自动识别[J]. 光学精密工程, 2013,21(7): 1898-1905

JIA Ping Ning Xu ZHANG Ye. Automatic target recognition based on local feature extraction[J]. Editorial Office of Optics and Precision Engineering, 2013,21(7): 1898-1905
贾平徐宁张叶. 基于局部特征提取的目标自动识别[J]. 光学精密工程, 2013,21(7): 1898-1905 DOI： 10.3788/OPE.20132107.1898.

JIA Ping Ning Xu ZHANG Ye. Automatic target recognition based on local feature extraction[J]. Editorial Office of Optics and Precision Engineering, 2013,21(7): 1898-1905 DOI： 10.3788/OPE.20132107.1898.

摘要

提出一种基于局部特征提取的目标识别方法，用于自动识别不同尺度，视角和照度条件下的目标。首先

建立图像的尺度空间；结合海森矩阵和Harris算法提取局部特征点，计算该特征区域的方向和灰度梯度及方向；统计出每块子区域的标准灰度梯度直方图，得到128维的特征向量。然后，基于主成分分析的降维算法来降低特征向量的维数，加快识别的计算速度。最后，采用特征空间分类器增加目标识别的速度。实验结果表明：基于局部特征提取的目标识别达到了较高的识别率，在视角、尺度和照度变化下的识别率分别为61.9%， 80.5%和84.4%，平均识别时间为130.9 ms。与尺度不变特征变换（SIFT）和加速鲁棒特征（SURF）算法相比，本算法不仅在不同的视角，目标尺度及照度条件下具有较高识别率，而且识别速度比SIFT方法高。

Abstract

A target recognition method was proposed to recognize targets with different scales

view-points and illuminations automatically. First

a scale space of images was established

and the local key points in the scale space were extracted by incorporating the Hessian and Harris scale-space detectors. Then

the main orientations of the key points and orientation histograms were calculated and 128 element feature vectors for each key point were established

in which these feature vectors were invariant in different rotations and illuminants. To reinforce the performance

principle component analysis was incorporated to reduce the dimensionality of feature vectors and improve calculating speeds for the recognition. The nearest feature space classifier was used for increasing the recognition speeds in robustness. Experiment results show that this proposed method achieves a significant improvement in automatic target recognition rate

and the recognition rates for varied view-points

scales and illuminations are 61.9%

80.5%

and 84.4%

respectively. Compared with the Scale Invariant Feature Transform(SIFT) and Speeded Up Robust Features (SURF)

the proposed method achieves a significant improvement in automatic target recognition rate in presence of varying viewpoints

scales and illuminations.

关键词

Keywords

references

RATCHES J A. Review of current aided/automatic target acquisition technology for military target acquisition tasks [J]. Optical Engineering, 2011, 50(7): 072001-8.[2]RATCHES J A, WALTERS CP, BUSER R C, et al.. Aided and automatic target recognition based upon sensory inputs from image forming systems [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(9): 1004-1019.[3]SAUL M D, KOBER V. Nonlinear synthetic discriminant function filters for illumination-invariant pattern recognition [J]. Optical Engineering, 2008, 47(6): 067201-9.[4]ZHANG ZH X, HUANG K Q, WANG Y H, et al.. Three-dimensional deformable-model-based localization and recognition of road vehicles [J]. IEEE Transactions on Image Processing, 2012, 21(1): 1-13.[5]DING Y, JIN W Q, WANG H. A target recognition algorithm based on a support vector machine \[C\]. 2008 International Conference on Optical Instruments and Technology: Optical Systems and Optoelectronic Instruments, 2008, 7156.[6]OVEISI F. Tree-structured feature extraction using mutual information[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(1): 127-137.[7]FENG Z Z. XIAN D, YA F H. Gabor filter approach to joint feature extraction and target recognition [J]. IEEE Transactions on Aerospace and Electronic Systems, 2009, 45(1): 17-30.[8]JI Y, GAOYUN W A, QIU Q R. Independent gabor analysis of discriminant features fusion for face recognition[J]. Signal Processing Letters, IEEE, 2009, 16(2): 97-100.[9]KEMBHAVI A, HARWOOD D, DAVIS L S. Vehicle detection using partial least squares [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(6): 1250-1265.[10]SCHEIRER W J. Meta-recognition: the theory and practice of recognition score analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1689-1695.[11]YAN W P. Fast haar transform based feature extraction for face representation and recognition [J]. IEEE Transactions on Information Forensics and Security, 2009, 4(3): 441-450.[12]CUI CH H,NGAN K N. Scale- and affine-invariant fan feature[J]. IEEE Transactions on Image Processing, 2011, 20(6): 1627-1640.[13]CHEN W T, LIU W CH, CHEN M S. Adaptive color feature extraction based on image color distributions [J]. IEEE Transactions on Image Processing, 2010, 19(8): 2005-2016.[14]LEPETIT V, FUA P. Keypoint recognition using randomized trees [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(9): 1465-1479.[15]SEDAGHAT A, MOKHTARZADE M, EBADI H. Uniform robust scale-invariant feature matching for optical remote sensing images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(11): 4516-4527.[16]LOWE D. Distinctive image feature from scale-invariant keypoints, cascade filtering approach [J]. IJCV,2004,(60):91-110.[17]BAY H. Speeded-up robust feature(SURF) [J]. Comput. Vis. Image Understand., 2008,110(3):346-359.[18]Qiaoliang, L., et al.. Robust scale-invariant feature matching for remote sensing image registration[J]. Geoscience and Remote Sensing Letters, IEEE, 2009. 6(2): 287-291.[19]SERRE T. Robust object recognition with cortex-like mechanisms [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(3): 411-426.[20]DHIR C S, YOUNG L S, Discriminant independent component analysis[J]. IEEE Transactions on Neural Networks, 2011, 22(6): 845-857.[21]CHEN X H, SCHMID N A. Empirical capacity of a recognition channel for single- and multipose object recognition under the constraint of PCA encoding [C]. IEEE Transactions on Image Processing, 2009, 18(3): 636-651.[22]YOU D, HAMSICI O C, MARTINEZ A M. Kernel optimization in discriminant analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3): 631-638.[23]HARRIS C, STEPHENS M. A combined corner and edge detector \[C\]. In Proceedings of The Fourth Alvey Vision Conference, 1988, 147-151. [24]YAN K, SUKTHANKAR R. PCA-SIFT: a more distinctive representation for local image descriptors. in computer vision and pattern recognition \[C\]. Proceedings of the 2004 Conference on IEEE Computer Society, CVPR 2004.[25]LI S Z, LU J. Face recognition using the nearest feature line method [J]. IEEE Transactions on Neural Networks, 1999.[26]CHIEN J T, WU C C. Discriminant waveletfaces and nearest feature classifiers for face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(12): 1644- 1649.

浏览量

112

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据