计算机科学 ›› 2017, Vol. 44 ›› Issue (Z6): 224-228.doi: 10.11896/j.issn.1002-137X.2017.6A.051

• 模式识别与图像处理 • 上一篇    下一篇

基于改进ViBe算法的园林游客检测研究

刘璎瑛,程顺,丁绍刚,陆攀,孙元昊   

  1. 江苏省智能化农业装备重点实验室南京农业大学工学院 南京210031,江苏省智能化农业装备重点实验室南京农业大学工学院 南京210031,南京农业大学园艺学院 南京210031,南京农业大学园艺学院 南京210031,江苏省智能化农业装备重点实验室南京农业大学工学院 南京210031
  • 出版日期:2017-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受2013年国家自然科学基金项目:基于“驻点”分布规律的江南私家园林空间路径量化研究(0601602)资助

Garden Tourist Detection Based on Improved ViBe Algorithm

LIU Ying-ying, CHENG Shun, DING Shao-gang, LU Pan and SUN Yuan-hao   

  • Online:2017-12-01 Published:2018-12-01

摘要: 传统的视觉背景提取算法中存在阴影敏感、前景点误判、前景空洞等问题。为了更好地提取园林游客的前景,在研究分析多种背景建模方法的基础上,提出一种Lab颜色空间下改进的ViBe游客检测算法,对算法的准确性和鲁棒性进行了测试。实验结果表明,该算法通过建立实时更新的背景模型,提高了游客检测的准确率,能够有效地适应光照变化并且能够去除阴影。针对园林内不同地点的复杂场景,改进的ViBe算法具有更好的检测效果。

关键词: 图像处理,改进的ViBe,游客检测,算法准确性,鲁棒性

Abstract: There are several problems in traditional visual background extraction algorithm,such as sensitivity to sha-dow of light,the wrong judged points of prospect,the hole of prospect and so on.In order to better segment the prospects of garden tourists,based on the analysis of a variety of building background model methods,this paper presented an improved tourist detection algorithm ViBe in Lab color space,and also tested the accuracy and robustness of improved ViBe algorithm.The results showed that the algorithm built an updated background model to improve the accuracy of tourist detection,it adapted to the change of light effectively and removed the shadow.By the analysis of dif-ferent locations’ video of garden,the improved ViBe algorithm has better detection results.

Key words: Image processing,Improved ViBe,Tourists segmentation,Algorithm accuracy,Robustness

[1] 霍东海,杨丹,张小洪,等.一种基于主成分分析的Codebook背景建模算法[J].自动化学报,2012(4):591-600.
[2] 解文华,易本顺,肖进胜,等.基于像素与子块的背景建模级联算法[J].通信学报,2013,4(4):194-200.
[3] 张水发,丁欢,张文生.双模型背景建模与目标检测研究[J].计算机研究与发展,2011,8(11):1983-1990.
[4] STAUFFER C,GRIMSON W E L.Adaptive background mixture models for real-time tracking[J].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1999,22(8):747-757.
[5] MADDALENA L,PETROSINO A.A self-organizing approach to background subtraction for visual surveillance applications[J].IEEE Transactions on Image Processing,2008,7(7):1168-1177.
[6] MADDALENA L,PETROSINO A.The SOBS algorithm:What are the limits?[C]∥Computer Vision and Pattern Recognition Workshops.IEEE,2012:21-26.
[7] 周俊,王明军,邵乔林.农田图像绿色植物自适应分割方法[J].农业工程学报,2013,8:163-170.
[8] DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005(CVPR 2005).IEEE,2005:886-893.
[9] JIANG H,TANG,OUYANG F.A New Method for the Prediction of the Gasoline Yield of the MIP Process[J].Petroleum Science and Technology,2015,3(20):1713-1720.
[10] 蔡灿辉,朱建清.采用Gentle AdaBoost和嵌套级联结构的实时人脸检测[J].信号处理,2013,9(8):956-963.
[11] 肖永刚.基于梯度特征和级联分类的快速行人检测[D].天津:天津大学,2010.
[12] BARNICH O,DROOGENBROECK M V.ViBe:A universalbackground subtraction algorithm for video sequences[J].IEEE Trans.Image Process,2011,20(6):1709-1724.
[13] 丁莹,钱锋,范静涛,等.基于不同颜色空间的运动目标检测算法分析[J].长春理工大学学报(自然科学版),2012,35(4):1-4.
[14] 张志斌,罗锡文,臧英,等.基于颜色特征的绿色作物图像分割算法[J].农业工程学报,2011,7(7):183-189.
[15] 韩殿元,黄心渊,付慧.基于彩色通道相似性图像分割方法的植物叶面积计算[J].农业工程学报,2012,8(6):179-183.
[16] 刁智华,王欢,宋寅卯,等.复杂背景下棉花病叶害螨图像分割方法[J].农业工程学报,2013,9(5):147-152.
[17] 胡小冉,孙涵.一种新的基于ViBe的运动目标检测方法[J].计算机科学,2014,1(2):149-152.
[18] 余烨,曹明伟,岳峰.EVibe:一种改进的Vibe运动目标检测算法[J].仪器仪表学报,2014,5(4):924-931.
[19] 仇春春,王恬,程海粟,等.基于改进Vibe算法的行人目标检测[J].信息技术,2016,2(3):6-9,14.
[20] KANG J M,COHEN I,MEDIONI G.Tracking Objects from Multiple Stationary and Moving Cameras[C]∥The Institution of Electrical Engineers.England,2004:31-35.
[21] 苏延召,李艾华,姜柯,等.改进视觉背景提取模型的运动目标检测算法[J].计算机辅助设计与图形学学报,2014(2):232-240.
[22] 王辉,宋建新.一种基于阈值的自适应Vibe目标检测算法[J].计算机科学,2015,2(S1):154-157.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!