您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (2): 63-70.doi: 10.6040/j.issn.1672-3961.0.2016.174

• 机器学习与数据挖掘 • 上一篇    下一篇

基于小波域特征和贝叶斯估计的目标检测算法

刘英霞1,王希常2,唐晓丽3,常发亮4   

  1. 1. 山东传媒职业学院, 山东 济南 250200;2. 山东省教育招生考试院, 山东 济南 250011;3. 纪念斯隆-凯特琳癌症中心医学物理学部, 纽约 西哈里森10606 美国;4. 山东大学控制科学与工程学院, 山东 济南 250011
  • 收稿日期:2016-05-23 出版日期:2017-04-20 发布日期:2016-05-23
  • 作者简介:刘英霞(1973— ),女,山东文登人,教授,工学博士,主要研究方向为计算机视觉.E-mail:liuyingxia228@163.com
  • 基金资助:
    山东省教育科学“十二五”规划资助项目(ZK1437B015);国家自然科学基金资助项目(60975025,61273277)

Object detection algorithm based on Bayesian probability estimation in wavelet domain

LIU Yingxia1, WANG Xichang2, TANG Xiaoli3, CHANG Faliang4   

  1. 1. Shandong Communication and Media College, Jinan 250200, Shandong, China;
    2. Shandong Province Academy of Education Recruitment and Examination, Jinan 250011, Shandong, China;
    3. Department of Medical Physics, Memorial Sloan Kettering Cancer Center, West Harrison 10606, New York, America;
    4. School of Control Science and Engineering, Shandong University, Jinan 250011, Shandong, China
  • Received:2016-05-23 Online:2017-04-20 Published:2016-05-23

摘要: 为了改进目标检测算法,在小波域建立基于贝叶斯概率估计的模型,得到一个自适应最佳阈值,并利用该阈值得到待检测的目标。对待检测的图像序列进行基于滑动窗口的双Haar小波变换,对小波变换后的低频分量建立基于核密度函数的贝叶斯概率估计模型,通过训练和学习,得到自适应的最佳阈值,利用该阈值对低频分量进行判别,得到只含有目标的二值化图像。选取室内室外一个和多个运动目标的6个视频序列对该算法的有效性进行检验,并同其他算法相比,可以给出更好的检测结果。

关键词: 小波域, 贝叶斯概率估计, 目标检测, 动态背景

Abstract: In order to improve the detection algorithm, Bayesian probability estimation model in wavelet domain was built to get a robust threshold, and the detected object could be obtained with the adaptive threshold. Moving Window-Based Double Haar Wavelet Transform for detected image sequence was finished. Bayesian probobility estimation model based on kernel density function was built for low frequency part, and adaptive threshold could be obtained after training and studying. With the threshold to judge the low frequnency part, the binary image could be got. Six video sequences with one targe and multiple targets outdoor and indoor were employed to evaluate the effectiveness of presented algorithm. Experimental results showed that it could give a better detecting results.

Key words: Bayesian probability estimation, object detection, wavelet domain, dynamic background

中图分类号: 

  • TP181
[1] PANCHAL Payal, PRAJAPATI Gaurav, PAREL Savan, et al. A review on object detection and tracking methods[J]. International Journal for Research in Emerging Science and Technology, 2015, 2(1):7-12.
[2] KALIRAJAN K, SUDHA M. Moving object detection for video surveillance[J]. The Scientific World Journal, 2015, 2015:1-10.
[3] ZHAO T, NEVATIA R, WU B. Segmentation and tracking of multiple humans in crowded environments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 30(7):1198-1211.
[4] HU Weiming, ZHOU Xue, LI Wei, et al. Active contour-based visual tracking by integrating colors, shapes, and motions[J]. IEEE Transactions on Image Processing, 2013, 22(5):1778-1792.
[5] SANKARALINGAM E, MAADI A, MALDAGUE X. Outdoor infrared video surveillance: a novel dynamic technique for the subtraction of a changing background of IR images[J]. Infrared Physics & Technology, 2007, 49(3): 261-265.
[6] MEHDI A, GGHOLAM R. A new real-time target tracking algorithm in image sequences based on wavelet transform[C] //Proceedings of the 14th International CSI Computer Conference.[S.l.] :IEEE, 2009:512-517.
[7] UNAL G, KRIM H, YEZZI A. Fast incorporation of optical flow into active polygons[J]. IEEE Transactions on Image Processing, 2005, 14(6):745-759.
[8] GHOSH A, SUBUDHI B N, GHOSH S. Object detection from videos captured by moving camera by fuzzy edge incorporated markov random field and local histogram matching[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2012, 22(8):1127-1135.
[9] ZHOU S K, CHELLAPPA R, MOGHADDAM B. Visual tracking and recognition using appearance-adaptive models in particle filters[J]. IEEE Transactions on Image Processing, 2004, 13(11):1491-1506.
[10] LATECKI L J, LI Q N, BAI X, et al. Skeletonization using SSM of the distance transform[J]. IEEE Transactions Conference on Image Processing, 2007, 5(9):349-352.
[11] CHEN C T, SU C Y, KAO W C. An enhanced segmentation on vision-based shadow removal for vehicle detection[C] //International Conference on Green Circuits and systems.[S.l.] :IEEE, 2010:679-682.
[12] SHEIKH Yaser, SHAH Mubarak. Bayesian modeling of dynamic scenes for object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(11): 1778-1792.
[13] HARDAS Adesh, BADE Dattatray, WALI Vibha. Moving object detection using background subtraction shadow removal and post processing[J]. European Journal of Pharmaceutical Sciences, 2000, 12(1):41-50.
[14] SAKHARKAR Sanjay S, KAMBLE S D, KHOBRAGADE A S. Object detection and tracking using particle filtering[J]. International Journal of Computer Trends and Technology, 2015, 22(1):16-19.
[15] 赵宏伟,冯嘉,臧雪柏,等. 一种实用的运动目标检测和跟踪算法[J]. 吉林大学学报(工学版),2009, 39(2):386-390. ZHAO Hongwei, FENG Jia, ZANG Xuebai, et al. Practical moving target detection and tracking algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2009, 39(2):386-390.
[16] SHEIKH Yaser, SHAH Mubarak. Bayesian modeling of dynamic scenes for object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(11):1778-1792.
[17] HSIA Chih Hsien, CHIANG Jen Shiun, GUO Jingming. Multiple moving objects detection and tracking using discrete wavelet transform[M] //Computer and Information Science. Shanghai:[s.n.] , 2011:297-320.
[18] CHENG F, CHEN Y L. Real time multiple object tracking and identification based on discrete wavelet transform[J]. Pattern Recognition, 2006, 39(6):1126-1139.
[19] SHARMA M, KULKARNI A, PUNTAMBEKAR S. Wavelet based adaptive tracking control for uncertain nonlinear systems with input constraints[J]. Nonlinear Dynamics & Systems Theory, 2012, 12(3):279-287.
[20] WANG Xin. Moving window-based double Haar wavelet transform for image processing[J]. IEEE Transactions on Image Processing, 2006, 15(9):2771-2779.
[21] LAI Qing, LIN Yijie. A novel network intrusion detection system based on Bayesian inference: IDS-BI[J]. Journal of Information & Computational Science, 2015, 12(11):4369-4376.
[22] NGUYEN Vu, PHUNG Dinh, PHAM Duc-Son, et al. Bayesian nonparametric approaches to abnormality detection in video surveillance[J]. Annals of Data Science, 2015, 2(1):21-41.
[23] 王星. 非参数估计[M].北京:中国人民大学出版社,2000.
[1] 惠开发,成科扬,詹永照. 基于改进ViBe算法的视频浓缩[J]. 山东大学学报(工学版), 2017, 47(3): 43-48.
[2] 邱晓欣1,2,张文强1,2*,秦晋贤1,2,杜正阳1,2,张德峰1,2. 恶劣环境下多目标实时跟踪算法研究[J]. 山东大学学报(工学版), 2014, 44(2): 21-27.
[3] 杨健梅1,黄添强1,2*,江伟坚1. 基于人脸色温的拼接图像篡改检测[J]. 山东大学学报(工学版), 2013, 43(5): 24-30.
[4] 王秀芬,王汇源,王松. 基于背景差分法和显著性图的海底目标检测方法[J]. 山东大学学报(工学版), 2011, 41(1): 12-16.
[5] 乔伟1,王汇源1,2,吴晓娟1,刘鹏威1. 基于混沌动力学模型的群体目标检测与分类[J]. 山东大学学报(工学版), 2010, 40(2): 19-23.
[6] 吕行,史忠科 . DirectShow框架下实时运动目标检测与跟踪方法的研究与应用[J]. 山东大学学报(工学版), 2007, 37(6): 5-9 .
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!