四元数和脉冲耦合神经网络应用于足球检测

doi:10.3969/j.issn.0255-8297.2013.02.013

应用科学学报 ›› 2013, Vol. 31 ›› Issue (2): 183-189.doi: 10.3969/j.issn.0255-8297.2013.02.013

四元数和脉冲耦合神经网络应用于足球检测

郑天宇，顾晓东

复旦大学电子工程系，上海200433

收稿日期:2011-09-26 修回日期:2011-12-09 出版日期:2013-03-25 发布日期:2011-12-09
通信作者: 顾晓东，博士后，副教授，研究方向：人工神经网络、图像处理、模式识别、生物建模等，E-mail：xdgu@fudan.edu.cn
作者简介:顾晓东，博士后，副教授，研究方向：人工神经网络、图像处理、模式识别、生物建模等，E-mail：xdgu@fudan.edu.cn
基金资助:
国家自然科学基金(No.61170207)资助

Soccer Detection in Images Based on Quaternion and Pulse Coupled Neural Network

ZHENG Tian-yu, GU Xiao-dong

Department of Electronic Engineering, Fudan University, Shanghai 200433, China

Received:2011-09-26 Revised:2011-12-09 Online:2013-03-25 Published:2011-12-09

摘要/Abstract

摘要： 提出一种基于四元数傅里叶变换注意力选择和脉冲耦合神经网络在图像中跟踪足球的方法. 首先进行图像预处理以去除球场以外的区域，用四元数注意力选择算法提取感兴趣区域，基于颜色、形状、面积等多种特征检测足球. 若检测失败，则采用卡尔曼滤波器预测足球位置. 仿真结果表明，与基于速度控制的动态卡尔曼滤波和实时足球检测两种方法相比，检测成功率分别提高9.6%和14.9%.

关键词: 足球检测, 四元数傅里叶变换, 脉冲耦合神经网络, 注意力选择, 卡尔曼滤波器

Abstract: This paper proposes a soccer detection method that combines the attention selection model of phase spectrum of quaternion Fourier transform (PQFT) and pulse coupled neural network (PCNN). In the preprocessing, the region outside the field is removed, and the region of interest extracted using PQFT. The
target is detected according to the physical characteristics such as color, shape and size. If no candidate or more than one are detected, a Kalman filter is used to make prediction. Simulation shows that the identification rate is improved by 9.6% and 14.9% respectively as compared to the dynamic Kalman filtering with velocity control and the real time ball detection framework introduced in the literature.

Key words: soccer detection, quaternion Fourier transform, pulse coupled neural network, attention selection, Kalman filter

中图分类号:

TP391.41

郑天宇，顾晓东. 四元数和脉冲耦合神经网络应用于足球检测[J]. 应用科学学报, 2013, 31(2): 183-189.

ZHENG Tian-yu, GU Xiao-dong. Soccer Detection in Images Based on Quaternion and Pulse Coupled Neural Network[J]. Journal of Applied Sciences, 2013, 31(2): 183-189.

参考文献

[1]     ProvosN. Defending against statistical steganalysis [C]//Proceedings of 10th USENIX Security Symp., Aug. 13-17, 2001: 323-335.
[2]     Westfeld A. High capacity despite better steganalysis (F5-A steganographic algorithm) [C]//Proceedings of Information Hiding, 4th Int. Workshop, ser. Lect. Notes comput. Sci., I. S. Moskowitz, Ed. New York: Springer-Verlag, Apr. 25-27, 2001, 2137: 289-302.
[3]     Sallee P. Model-based steganography [C]//Proceedings of 2nd Int. Workshop Digital Watermarking, Seoul, Korea, Oct. 20-22, 2003, 2939: 154-167.
[4]     Sallee P. Model-based methods for steganography and steganalysis [J]. International Journal of Image and Graphics, 2005, 5(1): 167-190.
[5]     Kodovský J, Fridrich J, Pevný T. Statistically undetectable JPEG steganography: Dead ends, challenges, and opportunities [C]//Proceedings of 9th ACM Multimedia & Security Workshop, Dallas, TX, Sep.20-21, 2007: 3-14.
[6]     Pevný T, Fridrich J. Merging Markov and DCT feature for multi-class JPEG steganalysis [C]//Proceedings of SPIE, Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents IX, San Jose, CA, Jan. 2007: 1-13.
[7]     Pevný T, Fridrich J. Multiclass detector of current steganographic methods for JPEG format [J]. IEEE Trans. Inf. Forensics Security, 2008, 3(4): 635-650.
[8]     Fu Dongdong, Shi Yunqing, Su Wei. A generalized Benford’s law for JPEG coefficients and its applications in image forensics [C]//Proceedings of SPIE, Security, Steganography and Watermarking of Multimedia Contents IX, San Jose, USA, Jan. 2007.
[9]     Fridrich J. Feature-based steganalysis for JPEG images and its implications for future design of steganographic schemes [C]// Proceedings of 6th Int. Workshop Information Hiding, LNCS 3200, 2004: 67-81.
[10]     The USDA NRCS photo gallery [DB/OL]. (2008-9-14) [2009-10-12]. http://photogallery.nrcs.usda.gov/.
[11]     Xia Zhihua, Sun Xingming, Liang Wei, Qin Jiaohua, Li Feng. JPEG image steganalysis using joint discrete cosine transform domain features [J]. Journal of Electronic Imaging, 2010, 19 (2): 1-13.

四元数和脉冲耦合神经网络应用于足球检测

Soccer Detection in Images Based on Quaternion and Pulse Coupled Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	王伟, 张金艺, 张洪辉, 蔡春艳, 李建宇. 异质双9轴MEMS惯性传感器数据互补-加权迭代融合算法[J]. 应用科学学报, 2015, 33(5): 491-501.
[2]	胡蓓1，隆霞1，胡超1，段盼2，唐若笠1，段其昌1. 改进脉冲耦合神经网络及二维Otsu算法的光伏阵列阴影检测[J]. 应用科学学报, 2013, 31(6): 613-618.
[3]	施俊，常谦，钟瑾. 基于三维脉冲耦合神经网络模型的医学图像分割[J]. 应用科学学报, 2010, 28(6): 609-615.