[1]谢红,原博,解武.LK光流法和三帧差分法的运动目标检测算法[J].应用科技,2016,43(03):23-28,33.[doi:10.11991/yykj.201507021]
 XIE Hong,YUAN Bo,XIE Wu.Moving target detection algorithm based on LK optical flow and three-frame difference method[J].Applied science and technology,2016,43(03):23-28,33.[doi:10.11991/yykj.201507021]
点击复制

LK光流法和三帧差分法的运动目标检测算法(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第43卷
期数:
2016年03期
页码:
23-28,33
栏目:
现代电子技术
出版日期:
2016-06-05

文章信息/Info

Title:
Moving target detection algorithm based on LK optical flow and three-frame difference method
作者:
谢红 原博 解武
哈尔滨工程大学 信息与通信工程学院, 黑龙江 哈尔滨 150001
Author(s):
XIE Hong YUAN Bo XIE Wu
College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
关键词:
目标检测检测算法三帧差分法LK光流法抗噪性阈值分割区域分割
Keywords:
target detectiondetection algorithmthree-frame difference methodLK optical flow methodnoise immunitythreshold segmentationregion segmentation
分类号:
TP911.73
DOI:
10.11991/yykj.201507021
文献标志码:
A
摘要:
三帧差分法是目前较为常见的运动目标检测算法之一。它的执行速度较快,但是它会存在各种干扰以及易受到环境噪声的影响,而且容易在检测到的运动目标内部产生较大的空洞,以致影响到最后的检测效果。针对这些问题,将Lucas-Kanade光流法与三帧差分法进行结合。利用Lucas-Kanade光流法计算得到运动目标的大致矩形区域。在确定的区域内外通过选取不同的阈值利用三帧差分算法提取运动目标,构成一种分级阈值的三帧差分法。并且利用前面光流法计算得到的角点来完善目标轮廓。这样将传统三帧差分算法的阈值分割转换成阈值分割与区域分割相结合的模式。试验结果表明,该改进算法具有良好的抗噪性,能够得到比原算法更好的检测效果。
Abstract:
The three-frame difference method is one of the most common moving target detection algorithms at present. Its execution is quite fast, and there inevitable exists various disturbances, and it is susceptible to the environmental noise. This method is also likly to form large cavities inside the detected moving targets, which affects the final result of the detection. To solve these problems, this article combines the three-frame difference method with the Lucas-Kanade optical flow method. The Lucas-Kanade optical flow method is used to calculate and get the general rectangular areas containing the moving targets. Different thresholds are selected inside and outside the determined regions to extract the moving targets by the three-frame difference method, and then to constitute a kind of three-frame difference method that has rated thresholds. The corners calculated by the optical flow method are used to improve the contours of the targets. In this way, the threshold segmentation of the traditional three-frame difference method is converted into another mode, which combines the threshold segmentation with the region segmentation. The experimental results show that, the improved algorithm has good noise immunity and can get better detection results than the three-frame difference method.

参考文献/References:

[1] 贾艳丽. 基于视频图像序列的运动目标检测与跟踪[D]. 哈尔滨:哈尔滨工程大学, 2012:3-4.
[2] 余启明. 基于背景减法和帧差法的运动目标检测算法研究[D]. 赣州:江西理工大学, 2013:2-4.
[3] 赵建. 基于三帧差法的运动目标检测方法研究[D]. 西安:西安电子科技大学, 2013:2-4.
[4] 袁国武, 陈志强, 龚健, 等. 一种结合光流法与三帧差分法的运动目标检测算法[J]. 小型微型计算机系统, 2013, 34(3):668-671.
[5] HARRIS C, STEPHENS M. A combined corner and edge detector[C]//Proceedings of the 4th Alvey Vision Conference. Manchester, UK, 1988:147-151.
[6] SHI Jianbo, TOMASI C. Good features to track[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Seattle, USA, 1994:593-600.
[7] 李玲. 数字图像点特征及边缘特征提取方法的研究与实现[D]. 西安:西安科技大学, 2012:24-26.
[8] 孙波. 数字图像角点检测算法的研究[D]. 合肥:合肥工业大学, 2013:20-22.
[9] BRADSKI G, KAEHLER A. Learning openCV[M]. Sebastopol, USA:O’Reilly Media, 2009.
[10] 毛玉东. 复杂环境下的运动目标检测算法研究[D]. 长春:吉林大学, 2012:26-27.

相似文献/References:

[1]张文升,王立国,孟凡旺.基于嵌套窗口的高光谱图像目标检测[J].应用科技,2009,36(05):12.[doi:10.3969/j.issn.1009-671X.2009.05.004]
 ZHANG Wen-sheng,WANG Li-guo,MENG Fan-wang.Nested spatial window based target detection for hyperspectral images[J].Applied science and technology,2009,36(03):12.[doi:10.3969/j.issn.1009-671X.2009.05.004]
[2]赵春晖,王楠楠.基于背景抑制及顶点成分分析的[J].应用科技,2009,36(09):11.[doi:oi:10.3969/j.issn.1009-671X.2009.09.003]
 ZHAO Chun hui,WANG Nan nan.Anomaly detection of hyperspectral imagery based on background restrain and VCA[J].Applied science and technology,2009,36(03):11.[doi:oi:10.3969/j.issn.1009-671X.2009.09.003]
[3]徐俊红,李金,从望,等.基于静态背景下的视频多目标运动物体的提取[J].应用科技,2005,32(03):31.
[4]赵群.基于混合高斯模型的运动目标检测算法[J].应用科技,2015,42(01):19.
 ZHAO Qun.Moving object detection algorithm based on Gaussian mixture model[J].Applied science and technology,2015,42(03):19.

备注/Memo

备注/Memo:
收稿日期:2015-07-20。
基金项目:黑龙江省自然科学基金项目(F201339).
作者简介:谢红(1962-),女,教授、博士生导师;原博(1989-),男,硕士研究生.
通讯作者:原博,E-mail:2698779148@qq.com.
更新日期/Last Update: 2016-06-08