全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

采用不变矩傅氏级数表示的步态识别

DOI: 10.11834/jig.20081213

Keywords: 步态识别,特征提取,不变矩,遗传算法,kNN分类器

Full-Text   Cite this paper   Add to My Lib

Abstract:

步态作为唯一具备远距离识别能力的生物测量特征已经受到广泛的关注。步态序列包含人行走的静态和动态信息,综合利用这两方面信息是提高识别性能的关键。为了综合利用人行走的静态和动态信息来提高识别能力,提出了一种用步态的不变矩傅氏级数系数的幅值作为识别特征的步态识别方法。因为不变矩描述了人运动的静态信息,其在整个步态周期提取的特征则蕴含了人运动的动态信息,所以将不变矩作为识别特征用于步态识别。该方法首先计算每帧图像的不变矩;然后采用傅里叶级数来拟合整个不变矩系数序列,并用遗传算法搜索傅里叶级数系数;接着将这些系数的幅值表示为用于分类的特征向量;最后再用?k?近邻分类器对特征向量进行分类。通过对CMU步态数据库中的4种步态分别进行的实验结果表明,该方法对单独的矩可取得80%以上的识别率,而对级联的矩识别率则可达到90%以上。另外,该方法对部分遮挡也具有鲁棒性。实验结果和性能分析表明,这种结合静态和动态信息的识别方法是有效的。

References

[1]  Veres G V, Gordon L, Carter J N, et al. What image information is important in silhouette-based gait recognition [ A ]. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition [C], Washington, DC, USA, 2004: 776 - 782.
[2]  Hu Ming-kuei. Visual pattern recognition by moment invariants [J]. IRE Transactions on Information Techonogy, 1962, 8:179 - 187.
[3]  Papoulis A. Probability, Random Variables, and Stochastic Processes [M]. 3nd ed., New York, USA: McGraw-Hill, 1991, 115.
[4]  Angeloni C, Riley P O, Krebs D E. Frequency content of whole body gait kinematic data [J]. IEEE Transactions on Rehabilitation Engineering. 1994, 2 (1) : 40 -46.
[5]  叶波 文玉梅.基于人身份识别的步态识别技术综述[J].计算机应用,2005,25(11):2577-2580,2584.
[6]  Nixon M S, Carter J N, Nash J M, et al. Automatic gait recognition [ A ]. In : Proceedings of IEEE Conference on Colloquium : Motion Analysis and Tracking[C], London, UK, 1999, 3:1-6.
[7]  Nash Jason M, Carter Jhon N, Nixon Mark S. Extraction of moving articulated-objects by evidence-gathering -A]. In: Proceedings of the Ninth British Machine Vision Conference [C], Southampton, UK, 1998, 2:609 -618.
[8]  Nash Jason M, Carter Jhon N, Nixon Mark S. Dynamic feature extraction via the velocity hough transform [J]. Pattern Recognition Letters, 1997, 18(10) : 1035 - 1047.
[9]  Cunado David, Nash Jason M, Nixon Mark S, et al. Gait Extraction and Description by Evidence-Gathering [ A ]. In : Proceedings of the Second International Conference on Audio-and Video-Based Biometric Person Authentication [C] , Washington, DC, USA, 1999:43 -48.
[10]  Nash Jason M, Carter Jhon N, Nixon Mark S. Using gait as a hiometric, via phase-weighted magnitude spectra [ A ]. In: Proceedings of 1st International Conference on Audio-and Video- Based Biometrie Person Authentication [C], Crans Montana, Switzerland, 1997:95 - 102.
[11]  Nash Jason M, Nixon Mark S, Carter Jhon N. Automatic extraction and description of human gait models for recognition Purposes [J]. Computer Vision and Image Understanding, 2003, 90 (1) : 1 - 41.
[12]  Wang Liang, Tan Tie-niu, Hu Wei-ming, et al Automatic gait recognition based on statistical shape analysis [J]. IEEE Transactions on Image Processing, 2003, 12 (9) : 1120 - 1131.
[13]  Wang Liang, Tan Tie-niu, Ning Hua-zhong, et al. Silhouette analysis-based gait recognition for human recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12) :1505 - 1518.
[14]  Wang Liang, Hu Wei-ming, Tan Tie-niu. A new attempt to gait- based human identification [ A ]. In: Proceedings of the 16th International Conference on Pattern Recognition [C], Quebec, Canada,2002, 1 : 115 - 118.
[15]  Niyogi Sourabh A, Adelson Edward H. Analyzing and recognizing walking figures in XYT [ A ]. In : Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition [C], Seattle, WA, USA, 1994:469-474.
[16]  Huang Ping S, Harris Chris J, Nixon Mark S. A statistical approach for recognizing humans by gait using spatial-temporal templates [A]. in: Proceedings of International Conference on Systems,Man, and Cybernetics [C], San Diego, CA, USA, 1998: 4556 - 4561.
[17]  Zhao Guo-ying, Chen Rui, Liu Guo-yi, et al. Amplitude spectrum- based gait recognition [ A ]. In: Proceedings of the sixth IEEE International Conference on Automatic Face and Gesture Recognition [C], Seoul, Korea , 2004 : 23 - 28.
[18]  Phillips P Jonathon, Moon Hyeonjoon, Rizvi Syed A, et al. The FEBET evaluation methodology for facerecognition algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10) :1090 - 1104.
[19]  Rizvi Syed A, Phillips P Jonathon, Moon Hyeonjoon. The FERET verification testing protocol for face recognition algorithms [EB/OL]. http: // www. nist. gov/itl/div894/894. 03/pubs. him/# face. 1998.
[20]  Shutler Jamie D, Nixon Mark S, Harris Chris J. Statistical gait desefipition via temporal moments [ A ]. In: Proceedings of 4th IEEE Southwest Symposium on Image Analysis and Interpretation[C], Austin, Texas, USA, 2000:291 - 295.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133