基于特征子模式典型相关分析的热释电红外信号识别

龚卫国; 王林泓; 贺莉芳

doi:10.3788/OPE.20111904.0884

您当前的位置：

首页 >

文章列表页 >

基于特征子模式典型相关分析的热释电红外信号识别

信息科学 | 更新时间：2020-08-12

- 基于特征子模式典型相关分析的热释电红外信号识别
- Pyroelectric infrared signal recognition based on feature sub-pattern canonical correlation analysis
- 光学精密工程 2011年19卷第4期页码：884-891
- 作者机构：
  
  1. 重庆大学光电技术及系统教育部重点实验室重庆,400044
  2. 重庆电子工程职业学院电子信息系,重庆 401331
- 作者简介：
- 基金信息：
  
  公安部应用创新项目(No.2010YYCXCQSJ074)();国防基础研究基金资助项目(No.CS-OC2)();重庆市重大科技攻关项目(No.CSTC2009AB0
- DOI：10.3788/OPE.20111904.0884
  中图分类号： TP3941.4;TN215
- 收稿日期：2010-02-08，
  
  修回日期：2010-07-16，
  
  网络出版日期：2011-04-26，
  
  纸质出版日期：2011-04-26
- 稿件说明：
移动端阅览
龚卫国, 王林泓, 贺莉芳. 基于特征子模式典型相关分析的热释电红外信号识别[J]. 光学精密工程, 2011,19(4): 884-891

GONG Wei-guo, WANG Lin-hong, HE Li-fang. Pyroelectric infrared signal recognition based on feature sub-pattern canonical correlation analysis[J]. Editorial Office of Optics and Precision Engineering, 2011,19(4): 884-891
龚卫国, 王林泓, 贺莉芳. 基于特征子模式典型相关分析的热释电红外信号识别[J]. 光学精密工程, 2011,19(4): 884-891 DOI： 10.3788/OPE.20111904.0884.

GONG Wei-guo, WANG Lin-hong, HE Li-fang. Pyroelectric infrared signal recognition based on feature sub-pattern canonical correlation analysis[J]. Editorial Office of Optics and Precision Engineering, 2011,19(4): 884-891 DOI： 10.3788/OPE.20111904.0884.

摘要

为使现有热释电红外(PIR)探测器具有识别检测区域内红外辐射源的功能

提出一种基于典型相关分析(CCA)特征融合的人体和非人体PIR信号识别方法。该方法首先提取PIR信号的频谱和小波包熵特征

然后对频谱进行子模式划分

并分别与小波包熵特征进行CCA融合

把融合后的结果作为判别信息

从而实现了特征融合且消除了特征之间的信息冗余。最后通过多数投票方式融合判别结果。作为子模式CCA特征融合的一种特殊情况

文中分析了特征与自身子模式特征CCA融合的分类性能。实验结果表明

当频谱分为5个子模式时

能有效地对人体和非人体红外辐射源进行识别

识别率可达95.2%

比直接采用频谱与小波包熵CCA融合的识别率提高了2.7%。而采用小波包熵与自身子模式特征CCA融合的识别率最高为90.7%

比单独采用小波包熵的识别率提高了2.3%。

Abstract

To improve the recognition ability of a pyroelectric infrared (PIR) detector for different infrared radiation sources

a method for human and non-human recognition based on Canonical Correlation Analysis (CCA) was proposed. Firstly

the frequency spectrum and wavelet packet entropy were extracted as features

and the spectrum was divided into sub-patterns. Then

each sub-pattern and wavelet packet entropy were fused with CCA method

and the fused feature was employed as classification information. By this way

the feature fusion was realized and the redundant information among the features was also eliminated. Finally

the recognition results were obtained by a majority voting method. As a special case of the sub-pattern fusion

the classification abilities of the features fused with their own sub-pattern were also studied in the paper. Experimental results show when the fre quency is divided into 5 sub-patterns

the recognition rate can reach 95.2%

which is higher 2.7% than that of only fusing the frequency and the wavelet packet entropy.Moreover

the recognition rate of wavelet packet entropy fused with its own sub-pattern is 90.7%

which is higher 2.3% than that of wavelet packet entropy.

关键词

Keywords

references

FANG J S, HAO Q, BRADY D J, et al.. Path-dependent human identification using a pyroelectric infrared sensor and Fresnel lens arrays [J]. Optics Express, 2006,14(2):609-624.[2] FANG J S, HAO Q, BRADY D J, et al.. Real-time human identification using a pyroelectric infrared detector array and hidden Markov models [J]. Optics Express, 2006,14(15):6643-6658.[3] FANG J S, HAO Q, BRADY D J, et al.. A pyroelectric infrared biometric system for real-time walker recognition by use of a maximum likelihood principal components estimation (MLPCE) method [J]. Optics Express, 2007,15(6):3271-3284.[4] 王林泓,龚卫国,刘晓莹,等. 基于小波熵的低误报率人体热释电红外信号识别[J]. 仪器仪表学报,2009,30(12):2485-2490. WANG L H, GONG W G, LIU X Y, et al.. Low false alarm rate human body recognition using pyroelectric infrared signal [J]. Chinese Journal of Scientific Instrument, 2009,30(12):2485-2490. (in Chinese)[5] SUN Q S, ZENG S G, HENG P A, et al.. A new method of feature fusion and its application in image recognition [J]. Pattern Recognition, 2005,38(12):2437-2448.[6] 孙权森,曾生根,王平安,等. 典型相关分析的理论及其在特征融合中的应用[J]. 计算机学报, 2005, 28(9):1524-1533. SUN Q S, ZENG S G, HENG P A, et al.. The theory of canonical correlation analysis and its application to feature fusion [J]. Chinese journal of computers, 2005,28(9):1524-1533. (in Chinese)[7] SUN Q S, ZENG S G, LIU Y, et al.. Feature fusion method based on canonical correlation analysis and handwritten character recognition . Proceedings of the 8th IEEE International Conference on Control, Automation, Robotics and Vision, Kunming, China, 2004:1547-1552.[8] 洪泉,陈松灿,倪雪蕾. 子模式典型相关分析及其在人脸识别中的应用[J]. 自动化学报,2008,34(1):21-30. HONG Q, CHEN S C, NI X L. Sub-pattern canonical correlation analysis with application in face recognition [J]. Acta Automatica Sinica, 2008,34(1):21-30. (in Chinese)[9] AVCI E. A new optimum feature extraction and classification method for speaker recognition: GWPNN [J]. Expert Systems with Applications, 2007,32(2):485-498.[10] AVCI E, AKPOLAT Z H. Speech recognition using a wavelet packet adaptive network based fuzzy inference system [J]. Expert Systems with Applications, 2006,31(3):495-503.[11] AVCI E, TURKOGLU I, POYRAZ M. Intelligent target recognition based on wavelet packet neural network [J]. Expert Systems with Applications, 2005,29(1):175-182.[12] 高印寒,马喜来,何丽桥,等. 基于小波包分解的阈值消噪在车载CAN总线上的应用[J]. 光学精密工程,2007,15(3):434-439. GAO Y H, MA X L, HE L Q, et al.. Application of threshold denoising based on wavelet packet decomposition to vehicular CAN-bus [J]. Opt. Precision Eng.,2007,15(3):434-439. (in Chinese)[13] 于晓波,盛磊. 靶场测量中多镜头大视场视频图像的拼接[J]. 光学精密工程,2008, 16(11):2145-2150. YU X B, SHENG L. Image stitching of multi-lens with large visual field in range instrumentation [J]. Opt. Precision Eng., 2008, 16(11):2145-2150.[14] ROSSO O A, BLANCO S, YORDANOVA J, et al.. Wavelet entropy: a new tool for analysis of short duration brain electrical signals [J]. Journal of Neuroscience Methods, 2001,105(1):65-75.[15] COIFMAN R R, WICKERHAUSER M V. Entropy-based algorithms for best basis selection [J]. IEEE Transactions on Information Theory, 1992,38(2):713-718. [16] KREUTZ-DELGADO K, RAO B D. Measures and algorithms for best basis selection . Proceeding on Acoustics, Speech and Signal Processing Conference, 1998:1881-1884.[17] DE BRUIN M G, KAMMINGA C. The effect of signal normalization on entropy sums [J]. Pattern Recognition Letters, 1998, 19,(5-6):415-423.[18] GUO Q L, WANG K Q , ZHANG D Y, et al.. A wavelet packet based pulse waveform analysis for cholecystitis and nephrotic syndrome diagnosis . Proceeding on Wavelet Analysis and Pattern Recognition Conference, 2008:30-31.

浏览量

522

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

强化边缘特征提取的双分支融合真实图像去雾

基于混合时空卷积的轻量级视频超分辨率重建

联合自注意力和分支采样的无人机图像目标检测

多维注意力机制与选择性特征融合的图像超分辨率重建

动态特征优化机制下的跨尺度红外行人检测