首页 > 论文 > 光学学报 > 38卷 > 6期(pp:612004--1)

基于多特征的复杂场景运动目标检测

Detection of Moving Objects in Complex Scenes Based on Multiple Features

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为提高复杂场景下运动目标检测的完整性和准确性,提出了一种多特征结合的运动目标检测方法。提出了一种自适应的高斯混合建模算法对颜色特征进行建模;通过滞后多阈值建模的方法,同时利用颜色和改进的局域二值模式纹理特征对环境背景进行了建模,并采用邻域补偿策略将基于两种特征提取得到的目标区域进行了结合;采用结合Canny思想改进的Kirsch方法进行了边缘提取,消除了鬼影误识别像素,改善了前景目标边缘。实验结果表明,所提方法在运动目标检测的完整性、准确性等指标上优于传统算法的,实时性也较好。

Abstract

In order to enhance the integrity and accuracy of moving object detection in complex scenes, a multi-features-based moving object detection method is proposed. The color feature is modeled by using the proposed adaptive Gaussian mixture model (GMM) algorithm. A kind of hysteresis multi-thresholds modeling method is used to model the scene background by adopting the color and improved local binary pattern (LBP) texture feature simultaneously. A neighborhood compensation strategy is adopted to combine the object regions obtained by the two-features extraction. The improved Kirsch edge detection method combined with the Canny thoughts is adopted in the edge extraction which eliminates the mistakenly detected ghost pixels and improves the edges of foreground objects. The experimental results show that the proposed method is superior to the traditional algorithms in the detection integrity and accuracy, and the real-time performance is also better.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201838.0612004

所属栏目:仪器,测量与计量

基金项目:国家自然科学基金(61274125,61176012)

收稿日期:2017-12-27

修改稿日期:2018-01-31

网络出版日期:--

作者单位    点击查看

朱文杰:陆军工程大学纳米技术与微系统实验室, 河北 石家庄 050003
王广龙:陆军工程大学纳米技术与微系统实验室, 河北 石家庄 050003
田杰:陆军工程大学纳米技术与微系统实验室, 河北 石家庄 050003
乔中涛:陆军工程大学纳米技术与微系统实验室, 河北 石家庄 050003
高凤岐:陆军工程大学纳米技术与微系统实验室, 河北 石家庄 050003

联系人作者:王广龙(815427360@qq.com)

备注:朱文杰(1988-),男,博士研究生,主要从事运动目标检测方面的研究。E-mail: zwj_881218@126.com

【1】Cheng F C, Chen B H, Huang S. A hybrid background subtraction method with background and foreground candidates detection[J]. ACM Transactions on Intelligent Systems and Technology, 2015, 1(7): 1-14.

【2】Chen S Y, Xu T F, Li D Q, et al. Moving object detection using scanning camera on a high-precision intelligent holder[J]. Sensors, 2016, 16(10): 1758.

【3】Chen H Y, Qie L Z, Yang D D, et al. Visual background extraction algorithm based on superpixel information feedback[J]. Acta Optica Sinica, 2017, 37(7): 0715001.
陈海永, 郄丽忠, 杨德东, 等. 基于超像素信息反馈的视觉背景提取算法[J]. 光学学报, 2017, 37(7): 0715001.

【4】Kumar P, Singhal A, Mehta S, et al. Real-time moving object detection algorithm on high-resolution videos using GPUs[J]. Journal of Real-Time Image Processing, 2016, 11(1): 93-109.

【5】Chua T W, Leman K, Wang Y. Fuzzy rule-based system for dynamic texture and color based background subtraction[C]. IEEE International Conference on Fuzzy Systems, 2012, 7: 10-15.

【6】Song T, Li O, Cui H L. A moving object detection method based on scene perception[J]. Acta Electronica Sinica, 2016, 44(11): 2625-2632.
宋涛, 李鸥, 崔弘亮. 基于场景感知的运动目标检测方法[J]. 电子学报, 2016, 44(11): 2625-2632.

【7】Tu L F, Zhong S D, Peng Q. Moving object detection method based on complementary multi resolution background models[J]. Journal of Central South University, 2014, 21(6): 2306-2314.

【8】Prashant D, Pratik S, Suman K M. Fast and accurate foreground background separation for video surveillance[J]. Lecture Notes in Computer Science, 2015, 9124: 96-103.

【9】Lee I S, Tsai W H. Data hiding in grayscale images by dynamic programming based on a human visual model[J]. Pattern Recognition, 2009, 42(7): 1604-1611.

【10】Guo M, Hu L L, Zhao J T. Surface defect detection method of ceramic bowl based on Kirsch and Canny operator[J]. Acta Optica Sinica, 2016, 36(9): 0904001.
郭萌, 胡辽林, 赵江涛. 基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J]. 光学学报, 2016, 36(9): 0904001.

【11】Zou Y B, Zhou W L, Chen X Z. Research of laser vision seam detection and tracking system based on depth hierarchical feature[J]. Chinese Journal of Lasers, 2017, 44(4): 0402009.
邹焱飚, 周卫林, 陈向志. 基于深度分层特征的激光视觉焊缝检测与跟踪系统研究[J]. 中国激光, 2017, 44(4): 0402009.

【12】Wang Y, Yipierre J, Fatih P, et al. CDnet 2014: An expanded change detection benchmark dataset[C]. Computer Vision & Pattern Recognition Workshops, 2014: 14632506.

【13】Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction[C]. International Conference on Pattern Recognition, 2004, 8(2): 28-31.

【14】Heikkila M, Pietikainen M. A texture-based method for modeling the background and detecting moving objects[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2006, 28(4): 657-662.

【15】Schick A, Auml M B, Stiefelhagen R. Improving foreground segmentations with probabilistic superpixel Markov random fields[C]. Computer Vision & Pattern Recognition Workshops, 2012: 12865142.

【16】Barnich O, van Droogenbroeck M. ViBe: A universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011, 20(6): 1709-1724.

【17】Bloisi D D, Pennisi A, Iocchi L. Background modeling in the maritime domain[J]. Machine Vision and Applications, 2014, 25(5): 1257-1269.

引用该论文

Zhu Wenjie,Wang Guanglong,Tian Jie,Qiao Zhongtao,Gao Fengqi. Detection of Moving Objects in Complex Scenes Based on Multiple Features[J]. Acta Optica Sinica, 2018, 38(6): 0612004

朱文杰,王广龙,田杰,乔中涛,高凤岐. 基于多特征的复杂场景运动目标检测[J]. 光学学报, 2018, 38(6): 0612004

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF