Moving vehicle object detection based on improved blocking matching algorithm

WEI Rong; SHEN Xi-bing; YANG Yi

doi:10.3788/YJYXS20163104.0410

您当前的位置：

首页 >

文章列表页 >

Moving vehicle object detection based on improved blocking matching algorithm

Display and Image | 更新时间：2020-08-12

- Moving vehicle object detection based on improved blocking matching algorithm
- Chinese Journal of Liquid Crystals and Displays Vol. 31, Issue 4, Pages: 410-414(2016)
- 作者机构：
  
  1. 钦州学院外国语学院,广西钦州,535000
  2. 钦州学院资源与环境学院,广西钦州,535000
  3. 广西科技大学软件学院,广西柳州,545006
- 作者简介：
- 基金信息：
  
  Supported by National Natural Science Foundation of China(No. 61201108)
- DOI：10.3788/YJYXS20163104.0410
  CLC： TP394.1
- Received：05 February 2015，
  
  Revised：25 June 2015，
  
  Published：05 April 2016
- 稿件说明：
移动端阅览
韦容, 申希兵, 杨毅. 一种基于改进块匹配算法的运动车辆检测[J]. 液晶与显示, 2016,31(4): 410-414

WEI Rong, SHEN Xi-bing, YANG Yi. Moving vehicle object detection based on improved blocking matching algorithm[J]. , 2016,31(4): 410-414
韦容, 申希兵, 杨毅. 一种基于改进块匹配算法的运动车辆检测[J]. 液晶与显示, 2016,31(4): 410-414 DOI： 10.3788/YJYXS20163104.0410.

WEI Rong, SHEN Xi-bing, YANG Yi. Moving vehicle object detection based on improved blocking matching algorithm[J]. , 2016,31(4): 410-414 DOI： 10.3788/YJYXS20163104.0410.

摘要

针对传统块匹配算法计算量大、光照变化较敏感和实时性差的缺陷

本文对块匹配算法进行了相关研究

提出了改进算法。首先把两幅彩色图像转化为灰度图像

并通过概率松弛标记算法获得边缘图像

计算相邻两幅图像的差分图像得到运动区域

然后将差分图像与边缘检测图像相与得到运动区域的边缘信息

再进行匹配得到位移矢量场并对其进行矢量中值滤波

最后通过顺序区域增长将运动车辆分割出来。实验结果表明:本文方法相对于传统方法平均检测时间降低约58 ms

而平均检测率提高了约6.7%。这种算法鲁棒性强、实时性好。

Abstract

For the imperfection of traditional block matching algorithm requiring large amount of computation

being more sensitive to light changes and having poor real-time

this paper conducts some related study about block-matching algorithm and proposes an improved algorithm. In this paper

block-matching algorithm is studied and an improved algorithm is proposed. First

two color images are converted to gray images

and the edge image is obtained by probabilistic relaxation labeling algorithm

to get the motion region by calculation difference image of two adjacent images. Then the edge information of moving region can be obtained by AND operation using the difference image with the edge detection image

and get the displacement vector by match operation

the vector median filtering is carried out. Finally

the moving vehicles can be obtained by region growing. Experimental results indicate that the average detection time of this method is reduced by about 58 ms compared with the traditional method

while the average detection rate is increased by about 6.7%. This algorithm has strong robustness

good real-time performance.

关键词

Keywords

references

FATHY M, SIYAL M Y. A window-based image processing technique for quantitative and qualitative analysis of road traffic parameters[J]. IEEE Transaction on Vehicular Technology, 2011, 47(4):1342-1349.

JI X P, WEI Z Q, FENG Y W. Effective vehicle detection technique for traffic surveillance systems[J]. Journal of Visual Communication and Image Representation, 2006, 17(3):647-658.

MICHALOPOULOS P G. Vehicle detection video through image processing:the autoscope system[J]. IEEE Transaction on Vehicular Technology, 1991, 40(1):21-29.

张小建, 徐慧. 基于视频处理的运动车辆检测算法的研究[J]. 液晶与显示, 2012, 27(1):108-113. ZHANG X J, XU H. Moving vehicle detection algorithm based on video processing[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(1):108-113. (in Chinese)

丁磊, 宫宁生. 基于改进的三帧差分法运动目标检测[J]. 电视技术, 2013, 37(1):151-153. DING L, GONG N S. Moving objects detection based on improved three frame difference[J]. Video Engineering, 2013, 37(1):151-153. (in Chinese)

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. YUAN G W, CHEN Z Q, GONG J, et al. A Moving object detection algorithm based on a combination of optical flow and three-frame difference[J]. Journal of Chinese Computer Systems, 2013, 34(3):668-671. (in Chinese)

胡学刚, 刘忠振. 基于高斯背景模型的车辆检测改进算法[J]. 计算机工程与设计, 2011, 32(12):4111-4114. HU X G, LIU Z Z. Improved vehicle detection algorithm based on Gaussian background model[J]. Computer Engineering and Design, 2011, 32(12):4111-4114. (in Chinese)

连静, 王珂, 杨兆升. 多尺度图像边缘检测技术在车辆识别中的应用[J]. 公路交通科技, 2007, 24(9):87-91. LIAN J, WANG K, YANG Z S. The technique of multi-scale image edge detection applying to vehicle recognition[J]. Journal of Highway and Transportation Research and Development, 2007, 24(9):87-91. (in Chinese)

刘鹏, 王国宇. 一种基于边缘信息的车辆检测和跟踪方法[J]. 中国海洋大学学报, 2007, 37(5):857-860. LIU P, WANG G Y. A Vehicle detection and tracking algorithm based on edge information[J]. Periodical of Ocean University of China, 2007, 37(5):857-860. (in Chinese)

ASTOLA J, HAAVISTO P, NEUVO Y. Vector median filters[J]. Proceedings of IEEE, 1990, 78(4):678-689.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰