[1]陈婧,李光炀,陈鲤文.面向仓库监控的改进式动态物体检测系统的设计[J].福建工程学院学报,2018,16(04):336-340.[doi:10.3969/j.issn.1672-4348.2018.04.006]
 CHEN Jing,LI Guangyang,CHEN Liwen.Design of an improved dynamic object detection system for warehouse monitoring[J].Journal of FuJian University of Technology,2018,16(04):336-340.[doi:10.3969/j.issn.1672-4348.2018.04.006]
点击复制

面向仓库监控的改进式动态物体检测系统的设计()
分享到:

《福建工程学院学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第16卷
期数:
2018年04期
页码:
336-340
栏目:
出版日期:
2018-08-25

文章信息/Info

Title:
Design of an improved dynamic object detection system for warehouse monitoring
作者:
陈婧李光炀陈鲤文
福建工程学院信息科学与工程学院
Author(s):
CHEN Jing LI Guangyang CHEN Liwen
School of Information Science and Engineering, Fujian University of Technology
关键词:
opencv 动态物体 混合高斯模型
Keywords:
opencv dynamic objects Gaussian Mixture Model
分类号:
TP277
DOI:
10.3969/j.issn.1672-4348.2018.04.006
文献标志码:
A
摘要:
采用混合高斯模型算法,以实现背景前景的分离,并利用前景目标的二值化图像计算其轮廓特性,对超过阈值的目标物体进行预警,同时系统为实现良好的可移植性及较快的硬件处理速率,采用软件分层的体系来实现动态物体检测,底层通过V4L2接口实现硬件视频帧的采集,顶层调用opencv视觉库实现混合高斯模型下的前景提取。最后系统实现良好的人机交互界面的设计。
Abstract:
The Gaussian Mixture Model algorithm was used to separate the background and the foreground. The contour features were calculated by using the binary image of the foreground target, and the target object that exceeded the threshold value was forewarned. Meanwhile, in order to achieve good portability and fast processing rate of the hardware, the system adopted a layered software system to realize dynamic object detection. The bottom layer realized the collection of hardware video frames through the V4L2 interface, and the top layer achieved the foreground extraction under the Gaussian Mixture Model by using the opencv visual library. Finally, the system realized the design of a good human-machine interaction interface.

参考文献/References:

[1] 刘升. 基于V4L2的嵌入式视频监控系统[J]. 微计算机应用, 2011, 32(1): 37-42.
[2] 曲国志, 肖作江. 基于Matlab的动态目标模拟发生技术研究[J]. 长春理工大学学报(自然科学版), 2010, 33 (3) : 130-132.
[3] 马森.动态背景下的动态物体检测[M].哈尔滨:哈尔滨工业大学,2015.
[4] HORN B, SCHUNCK B. Determining optical flow[C]∥Technical Symposium East, 1981: 319-331.
[5] SUN D, ROTH S, BLACK M. Secrets of optical flow estimation and their principles[C]∥IEEE Computer Society Conference on Computer Comparison of foreground results Vision and Pattern Recognition, 2010: 2432-2439.
[6] SUN D, ROTH S, LEWIS J P, et al. Learning optical flow[C]∥European Conference on Computer Vision(ECCV), 2008: 83-97.
[7] 张文强, 路红, 陈义东, 等. 动态场景中的自适应背景建模研究[J]. 中国图象图形学报, 2009, 14(12): 2627-2630.
[8] 李观金. 基于计算机互联网技术的智能远程视频监控系统设计[J]. 现代信息科技, 2017(6) : 83-85.
[9] ZHANG X, YANG Y H, HAN Z, et al. Object class detection: a survey[J]. Association for Computing Machinery Computing Surveys(CSUR), 2013, 46(1): 1311-1325.
[10] 韩国强. 浅谈智能视频监控技术及其主要应用[J]. 计算机与网络, 2014 (2): 62-65.

更新日期/Last Update: 2018-08-25