基于朴素贝叶斯分类的路面积雪状态检测

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 380-383.

基于朴素贝叶斯分类的路面积雪状态检测

孙中华, 蒋斌, 贾克斌

北京工业大学电子信息与控制工程学院,北京 100124

收稿日期:2012-11-26 发布日期:2013-06-01
作者简介:孙中华(1978-),男,讲师.研究方向:视频信息检索.E-mail:sunzh@bjut.edu.cn
基金资助:
北京市教委科研计划资助项目(00200054K1006).

Detection of the road snow coverage status based on naive Bayesian classifier

SUN Zhong-hua, JIANG Bin, JIA Ke-bin

College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China

Received:2012-11-26 Published:2013-06-01

摘要/Abstract

摘要：

为解决路面积雪状态(轻微、严重)检测问题以保证行车安全,利用监控视频得到路面实时状态,采用朴素贝叶斯分类方法进行积雪状态检测。首先利用机器视觉和视频目标分割方法提取视频中路面视觉特征,然后采用朴素贝叶斯分类方法进行路面积雪状态分类,通过实验,综合比较了朴素贝叶斯分类与KNN分类、人工神经网络(ANN)、支撑向量机(SVM)在路面积雪状态检测问题中的有效性,结果表明,朴素贝叶斯分类器更适合积雪状态的分类。

关键词: 路面积雪覆盖, 特征信息, 朴素贝叶斯分类, 视频目标分割

Abstract:

In order to detect the snow coverage status such as mild or heavy coverage on road to keep car running safe,snow coverage detection method together with naive Bayesian classification algorithm was proposed.Firstly,road visual feature was extracted from the video by the method of machine vision and video object segmentation.Then the road snow coverage status was classified with naive Bayesian classifier.The performance of KNN,ANN and SVM classifier for road snow coverage problem were compared.

Key words: road snow coverage, texture information, naive Bayesian classifier, video object segmentation

中图分类号:

TP37

孙中华, 蒋斌, 贾克斌. 基于朴素贝叶斯分类的路面积雪状态检测[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 380-383.

SUN Zhong-hua, JIANG Bin, JIA Ke-bin. Detection of the road snow coverage status based on naive Bayesian classifier[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 380-383.

参考文献

[1] Magagi R,Bernier M.Optimal conditions for wet snow detection using RADARSAT SAR data [J].Remote Sensing of Environment,2003,84:221-233.

[2] Jonsson P.Remote sensor for winter road surface status detection[C]//IEEE Sensors,Limerick,2011:1285-1288.

[3] Bossu J,Hautiere N,Tarel J-P.Rain or snow detection in image sequence through use of a hisogram of orientation of streaks[J].International Journal of Computer Vision,2011,93:348-367.

[4] Brewer N,Liu N.Using the shape characteristics of rain to identify and remove rain from video[C]//2008 Joint IAPR International Workshop on Structrual,Syntactic,and Statistical Pattern Recognition,Berlin,Heidelberg,2008:451-458.

[5] Sakaino H,Shen Y,Pang Y,et al.Falling snow motion estimation based on a semi-transparent and particle trajectory model[C]//IEEE International Conference on Image Processing,2009:1609-1612.

[6] Shen Y,Ma L Z,Liu H,et al.Detecting and extracting natural snow from videos[J].Information Processing Letters,2010,110:1124-1130.

[7] McFall K,Niitula T.Results of audio-visual winter road condition sensor prototype[C]//11th Standing International Road Weather Congress,Sapporo,Japan,2002.

[8] Omer R,Fu L.An automatic image recognition system for winter road surface condition classification[C]//The 13th International Conference on Intelligent Transportation Systems (ITSC),Waterloo,2010:1375-1379.

[9] 田洪宁,贾克斌.一种改进的适用复杂场景的运动目标检测算法[J].计算机仿真,2011,28(8):233-237. TIAN Hong-ning,JIA Ke-bin.Improved algorithm of motion detection in complicated environment[J].Computer Simulation,2011,28(8):233-237.

[10] Chen S Y,Ma S Y,Chen L G.Effective moving object segmentation algorithm using background registration technique[J].IEEE Transaction on Circuits and System for Video Technology,2002,12(7):577-585.

[11] Freund Y,Schapire R E.A decision-theoretic generation of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1995,55:119-139.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed