[1]陈柏生,陈锻生.采用梯度滤波方法的夜间车辆检测[J].华侨大学学报(自然科学版),2009,30(1):42-44.[doi:10.11830/ISSN.1000-5013.2009.01.0042]
　CHEN Bai-sheng,CHEN Duan-sheng.Nighttime Vehicle Detection Based on Grad-Filtering[J].Journal of Huaqiao University(Natural Science),2009,30(1):42-44.[doi:10.11830/ISSN.1000-5013.2009.01.0042]
点击复制

采用梯度滤波方法的夜间车辆检测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第30卷
期数:
2009年第1期
页码:
42-44
栏目:
出版日期:
2009-01-20

文章信息/Info

Title:
Nighttime Vehicle Detection Based on Grad-Filtering
文章编号:
1000-5013(2009)01-0042-03
作者:
陈柏生; 陈锻生
华侨大学计算机科学与技术学院
Author(s):
CHEN Bai-sheng;  CHEN Duan-sheng
College of Computer Science and Technology, Huaqiao University, Quanzhou 362021, China
关键词:
夜间视觉;  交通监控;  梯度滤波;  三帧差分;  级联形态学滤波
Keywords:
nighttime visual;  traffic surveillance;  grad-filtering;  three-frame difference;  cascaded morphological filtering
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.2009.01.0042
文献标志码:
A
摘要:
研究视觉交通监控的夜间车辆检测问题,提出一种基于视频图像处理提取夜间交通车辆完整轮廓的方法.通过梯度滤波消除路面反光的干扰,然后对经过预处理的相邻视频帧图像实行三帧差分分割运动区域,最后设计级联形态学滤波器对获得的车辆轮廓进行规整.多段典型的夜间交通视频测试结果表明,方法能有效地消除路面反光和环境光照的干扰,准确地提取夜间交通车辆的完整轮廓.
Abstract:
To study the nighttime vehicle detection of the visual traffic surveillance,a real-time scheme to abstract vehicles′ contour at night for visual traffic surveillance system is proposed in this paper.Firstly,a preprocessing based on grad-filtering is employed to eliminate the influence of the reflection of the road.Foreground is then detected by three-frame differencing.Moreover,a post-processing based on a cascaded morphology filter is exploited to exclude the noises and fill the holes resulting from the operator of inter-frame differencing.Experiments are done on several video sequences representing typical night traffic scene.Results show the presented method is able to eliminate the influence of the reflection of the road effectively,and abstract vehicles′ contour exactly.

参考文献/References:

[1] SCHREINER K. Night vision:Infrared takes to the road [J]. IEEE Computer Graphics and Applications, 1999(5):6-10.doi:10.1109/38.788791.
[2] TSUJI T, HATTORI H, WATANABE M. Development of night-vision system [J]. IEEE Transactions on Intelligent Transportation Systems, 2002(3):203-209.
[3] TAKTAK R, DUFAUT M, HUSSON R. Vehicle detection at night using image processing and pattern recognition [M]. Austin:IEEE Computer Society Press, 1994.296-300.
[4] RITA C, MASSIMO P, PAOLA M. Image analysis and rule-based reasoning for a traffic monitoring system [J]. IEEE Transactions on Intelligent Transportation Systems, 2000(2):119-130.doi:10.1109/6979.880969.
[5] 刘勃, 周荷琴, 魏铭旭. 基于颜色和运动信息的夜间车辆检测方法 [J]. 中国图象图形学报A, 2005(2):187-189.doi:10.3969/j.issn.1006-8961.2005.02.009.

备注/Memo

备注/Memo:
福建省自然科学基金资助项目(A0510020)
更新日期/Last Update: 2014-03-23