记忆分水岭圆盘梯度膨胀模板运动视频跟踪

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (2): 462-467.

记忆分水岭圆盘梯度膨胀模板运动视频跟踪

魏巍, 吴孔平, 郭来功, 秦蒙

安徽理工大学电气与信息工程学院,安徽淮南 232001

收稿日期:2015-06-13 修回日期:2015-07-26 出版日期:2016-02-08 发布日期:2020-08-17
作者简介:魏巍(1981-),男,安徽淮南,硕士,讲师,高工,研究方向为计算机智能算法,数字图像处理。
基金资助:
安徽理工大学青年教师科学研究基金(QN201311); 安徽理工大学大学生创新创业训练计划项目(AH201410361178)

DGETMW: Motion Video Tracking Based on Memory Watershed Disc Gradient Expansion Template

Wei Wei, Wu Kongping, Guo Laigong, Qin Meng

School of Electrical and Information Engineering, Anhui University of Science & Technology, Huainan 232001, China

Received:2015-06-13 Revised:2015-07-26 Online:2016-02-08 Published:2020-08-17

摘要/Abstract

摘要： 为进一步提高运动视频中目标跟踪检测的准确度,提出记忆分水岭圆盘梯度膨胀模板运动视频跟踪算法。对于运动视频图像采用异向扩散对运动视频图像执行预处理,降低运动目标跟踪检测存在的噪声干扰,并利用差分操作和形态学操作对运动物体外形轮廓进行提取和操作;针对分水岭算法存在的过分割问题,基于特征记忆实现分水岭算法的目标标记与分割,并基于圆盘梯度膨胀模板,实现运动目标精确检测;通过实验对比显示,所提算法在运动目标的复杂背景检测应用中,不仅可实现运动目标的检测精度提升,同时可实现算法计算速度的大幅提升。

关键词: 视频跟踪, 记忆, 分水岭, 圆盘梯度, 膨胀

Abstract: In order to obtain ideal detection results of moving object, a new video moving object detection algorithm based on labeling watershed and detection algorithm and morphology were proposed. The image was pre-processed by diffusion model to eliminate noise interference on object detection, and the difference algorithm was used to extract outline of moving object.. Morphological operations were used to process the target outline, and marked watershed algorithm was used to segment moving object and performance was tested by simulation experiments. The simulation results show that the proposed algorithm can prevent over segmentation problems and accurately detect moving object from complex background, not only improve the detection accuracy but accelerate the speed of moving object detection.

Key words: video tracking, memory, watershed, disc gradient, expansion

中图分类号:

TP391

魏巍, 吴孔平, 郭来功, 秦蒙. 记忆分水岭圆盘梯度膨胀模板运动视频跟踪[J]. 系统仿真学报, 2016, 28(2): 462-467.

Wei Wei, Wu Kongping, Guo Laigong, Qin Meng. DGETMW: Motion Video Tracking Based on Memory Watershed Disc Gradient Expansion Template[J]. Journal of System Simulation, 2016, 28(2): 462-467.

参考文献 15

[1]	王相海, 方玲玲, 丛志环. 基于MSPF的实时监控多目标跟踪算法研究[J]. 自动化学报, 2012, 38(1): 139-144.
[2]	Zivovic Z, Ferdinand H.Efficient adaptive density estimation per image pixel for the task of background subtraction[J]. Pattern Recognition Letters (S0167-8655), 2006, 7(26): 773-780.
[3]	Maddalena L, Petrosino A.A self-organizing approach to background subtraction for visual surveillance applications[J]. IEEE Transactions on Image Processing (S1057-7149), 2008, 17(7): 1168-1177.
[4]	Li S X, Chang H X, Zhu C F.Adaptive pyramid mean shift for global real-time visual tracking[J]. Image and Vision Computing (S0262-8856), 2010, 28(3): 424-437.
[5]	Lee S, Lee J, Hayes M H, et al.Adaptive background generation for automatic detection of initial object region in multiple color-filter aperture camera-based surveillance system[J]. IEEE Transations on Consumer Electronics (S0098-3063), 2012, 58(1): 104-110.
[6]	Jeyakar J, Babu R V, Ramakrishnan K R.Robust object tracking with background-weighted local kernels[J]. Computer Vision and Image Understanding (S1077-3142), 2008, 112(3): 296-309.
[7]	Lin H H, Chuang J H, Liu T L.Regularized background adaptation: a novel learning rate control scheme for gaussian mixture modeling[J]. IEEE Transactions on Image Processing (S1057-7149), 2011, 20(3): 822-836.
[8]	Leichter I, Lindenbaum M, Rivlin E.Mean shift tracking with multiple references color histograms[J]. Computer Vision and Image Understanding (S1077-3142), 2010, 114(3): 400-408.
[9]	吴敏, 吴宏刚, 姚辉. 一种自适应的双门限场面运动目标检测方法[J]. 计算机科学, 2015, 42(1): 312-317.
[10]	Bleyer M, Gelantz M.Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions[J]. Signal Proceedings: Image Communication, Special Issue on Three-Dimensional Video and Television (S0923-5965), 2007, 22(2): 127-149.
[11]	郑锦, 李波. 基于三阶中心矩区域分类的视频运动目标检测[J]. 计算机辅助设计与图形学学报, 2015, 27(5): 832-840.
[12]	Chinchkhede D W, Uke N J.Image segmentation in video sequences using modified background subtraction[J]. International Journal of Computer Science & Information Technology (S2091-1610), 2012, 4(1): 93-104.
[13]	D F Shen, M T Huang.A watershed-based image segmentation using JND property[C]// Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Hong Kong, China. USA: IEEE, 2003: 377-380
[14]	Wang X J, Yuan D, Li D K.Moving Target Classification Technique in Video Sequence [C]// Proceedings of International Conference of Information Technology. USA: IEEE Press, 2011: 362-365.
[15]	Shen C, Brooks M, Van Den Hengel A. Fast global kernel density mode seeking: Applications to localization and tracking[J]. IEEE, Transactions on Image Processing (S1057-7149), 2007, 16(5): 1457-1469.