基于改进ViBe的室外行人检测方法

doi:10.3969/j.issn.1006-2475.2018.03.006

计算机与现代化

基于改进ViBe的室外行人检测方法

(广州中国科学院软件应用技术研究所,广东广州511458)

收稿日期:2017-07-05 出版日期:2018-04-03 发布日期:2018-04-03
作者简介:崔莹(1987-),女(朝鲜族),黑龙江大庆人,广州中国科学院软件应用技术研究所工程师,硕士,研究方向:图像处理,模式识别; 陈升东(1982-),男,工程师,学士,研究方向:模式识别,数据挖掘; 袁峰(1977-),男,副研究员,博士,研究方向:智慧城市,物联网; 李引(1981-),男,高级工程师,博士,研究方向:大数据应用,数据挖掘。
基金资助:
广东省科技项目(2016108101009); 广州市科技计划项目(201604016104,2016201604030087,201604020101); 湖北省中国科学院科技合作专项项目; 广东省物联网专项资金项目

Outdoor Pedestrian Detection Method Based on Improved ViBe

(Institute of Software Application Technology, Guangzhou & Chinese Academy of Sciences , Guangzhou 511458, China)

Received:2017-07-05 Online:2018-04-03 Published:2018-04-03

摘要/Abstract

摘要： 室外动态环境的行人监控检测一直是研究的难点，存在光照变化、树叶摇晃、小动物经过等复杂干扰。本文提出一种基于改进视觉背景抽取法(Visual Background Extractor，ViBe)的室外行人检测方法，该方法采用基于区域的改进ViBe更新策略，该策略在加快鬼影消除速度的同时，提高了行人目标提取的完整度，然后在前景目标提取的过程中通过背景差的方法过滤复杂背景导致的误报区域，最后在此基础上根据一定的逻辑规则执行行人检测。实验结果表明，该方法既可以提高鬼影消除速度，也有效降低复杂多变背景的干扰，在室外场景进行行人检测具有较高的准确性、鲁棒性。

关键词: 视觉背景抽取法, 鬼影, 室外复杂环境, 行人检测

Abstract: Outdoor pedestrian detection has always been research challenges because of the complex background, such as light mutations, shaking leaves, passing of small animals and other complex noises. Regarding this fact, this paper proposes a pedestrian detection method based on improved ViBe(Visual Background Extractor) method. This method first uses the region-based improved ViBe update strategy, which improves the completion rate of the extraction of pedestrian-target-region while accelerates the elimination rate of the ghost-region. Then, the background difference method is used to filter the false area which caused by complex background. Finally, on this basis, according to certain logical rules, the method presented in this paper performs pedestrian detection selectively. The experimental results show that this method can not only accelerate the elimination rate of the ghost-region, but also reduce the interference of complex variable background. This method has high accurateness and robustness for outdoor pedestrian detection.

Key words: ViBe algorithm, ghost-region, outdoor complex scene, pedestrian detection

中图分类号:

TP391.41

崔莹,陈升东,袁峰,李引. 基于改进ViBe的室外行人检测方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.03.006.

CUI Ying, CHEN Sheng-dong, YUAN Feng, LI Yin. Outdoor Pedestrian Detection Method Based on Improved ViBe[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.03.006.

参考文献

［1］黄凯奇,陈晓棠,康运锋,等. 智能视频监控技术综述［J］. 计算机学报, 2015,38(6):1093-1118.
［2］ Dalal N, Triggs B. Histograms of oriented gradients for human detection［C］// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005:886-893.
［3］朴春赫,潘怡霖,赵海,等. 基于改进ViBe的多行人检测方法［J］. 东北大学学报(自然科学版), 2016,37(4):481-485.
［4］张慧,郑爱华,涂铮铮,等．基于背景差与HOG-LBP的快速运动人体检测［J］. 计算机技术与发展, 2015,25(2):47-51.
［5］汪成亮,周佳,黄晟. 基于高斯混合模型与PCA-HOG的快速运动人体检测［J］. 计算机应用研究, 2012,29(6):2156-2160.
［6］ Tekalp A M. Digital Video Processing［M］. Pearson Education, 2015.
［7］ Haritaoglu I, Harwood D, Davis L S. W4: Who? When? Where? What? A real time system for detecting and tracking people［C］// Proceedings of the 3rd International Conference on Face & Gesture Recognition. 1998:222-227.
［8］ Papenberg N, Bruhn A, Brox T, et al. Highly accurate optic flow computation with theoretically justified warping［J］. International Journal of Computer Vision, 2006,67(2):141-158.
［9］ Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):747-757.
［10］Barnich O, Droogenbroeck M V. ViBe: A powerful random technique to estimate the background in video sequences［C］// 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. 2009：945-948.
［11］吴建胜，徐博．动态阈值的Vibe运动目标检测［J］．计算机工程与应用, 2017,53(11):182-186.
［12］Tajbakhsh T, Grigat R R. Illumination flicker frequency classification in rolling shutter camera systems［C］// Proceedings of the 9th IASTED International Conference on Signal and Image Processing. 2007:288-293.
［13］赵光明,韩光,李晓飞,等．基于融合帧间差的改进Vibe方法［J］. 计算机技术与发展, 2015(3):76-80.
［14］吴剑舞,翁玲瑜,童怀．一种基于改进ViBe的运动目标检测方法［J］. 计算机与现代化, 2015(7):50-54.
［15］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(3):6-9.
［16］徐久强,江萍萍,朱宏博,等. 面向运动目标检测的ViBe算法改进［J］. 东北大学学报(自然科学版)， 2015,36(9):1227-1231.
［17］Manzanera A, Richefeu J C. A new motion detection algorithm based on Σ-Δ, background estimation［J］. Pattern Recognition Letters, 2007,28(3):320-328.
［18］孙水发,覃音诗,马先兵,等. 室外视频前景检测中的形态学改进ViBe算法［J］. 计算机工程与应用, 2013，49(10):159-162.
［19］Droogenbroeck M V, Paquot O. Background subtraction: Experiments and improvements for ViBe［C］// 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2012,71(8):32-37.
［20］Joshi K A, Thakore D G. A survey on moving object detection and tracking in video surveillance system［J］. International Journal of Soft Computing & Engineering, 2012,2(3):44-48.

[1]	谢辉, 师后勤, 齐宇霄, 陈瑞, 童莹. 基于注意力机制子网络的时空跌倒检测算法[J]. 计算机与现代化, 2022, 0(03): 70-75.
[2]	郑钦浩, 杨贞, 杨振 . 面向车辆和行人检测的KM-SSD方法[J]. 计算机与现代化, 2021, 0(03): 51-56.
[3]	杨磊1,王少云2,刘力冉1,龚永富1. 一种智能视频监控系统中的行人检测方法[J]. 计算机与现代化, 2019, 0(11): 69-.
[4]	曹瑞，王敏，段潇潇. 密集人群场景下的行人检测与跟踪[J]. 计算机与现代化, 2017, 0(1): 75-78.
[5]	胡鹏程1,张超1,鲍丙计1,吴小培1,王营冠2. 基于车载视频的行人预警系统[J]. 计算机与现代化, 2016, 0(11): 43-52.
[6]	张雪松. 基于广义霍夫变换的室外场景行人检测研究[J]. 计算机与现代化, 2015, 0(4): 70-73,77.
[7]	张桂宁. 基于改进HOG特征值的行人检测[J]. 计算机与现代化, 2015, 0(2): 52-.
[8]	李熙莹;卢林;陈玲. 汽车客运站出入口监控系统中行人检测与跟踪方法[J]. 计算机与现代化, 2013, 1(8): 15-18.
[9]	胡江华汤进;李成龙罗斌;. 视频监控系统中行人的自动分割算法[J]. 计算机与现代化, 2013, 1(8): 7-10.

基于改进ViBe的室外行人检测方法

Outdoor Pedestrian Detection Method Based on Improved ViBe

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价