|本期目录/Table of Contents|

[1]王海晖,刘洋,陶玲.低照度下运动车辆的检测方法[J].武汉工程大学学报,2013,(10):41-45.[doi:103969/jissn16742869201310009]
　WANG Hai\|hui,LIU Yang,TAO Ling.Moving vehicle detection in low light conditions[J].Journal of Wuhan Institute of Technology,2013,(10):41-45.[doi:103969/jissn16742869201310009]
点击复制

低照度下运动车辆的检测方法(/HTML)
分享到：

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
期数:
2013年10期
页码:
41-45
栏目:
机电与信息工程
出版日期:
2013-11-10

文章信息/Info

Title:
Moving vehicle detection in low light conditions
文章编号:
16742869(2013)10004105
作者:
王海晖1; 2; 刘洋1; 陶玲1
1.武汉工程大学计算机科学与工程学院，湖北 武汉 430205；2.武汉工程大学智能机器人湖北省重点实验室，湖北 武汉 430205
Author(s):
WANG Hai\|hui1; 2;  LIU Yang1;  TAO Ling1
1. School of Computer Science and Technology, Wuhan Institute of Technology, Wuhan 430205, China; 2. Hubei Provincial Key Laboratory of Intelligent Robot, Wuhan Institute of Technology,Wuhan 430205, China
关键词:
车辆检测; 低照度; Adaboost算法; 梯度方向直方图特征
Keywords:
vehicle detection;  low light;  Adaboost algorithm;  Histogram of Oriented Gradients feature
分类号:
TP317.4
DOI:
103969/jissn16742869201310009
文献标志码:
A
摘要:
针对一般车辆检测系统在夜间等低照度情况下检测能力急剧下降的问题，提出一种低照度下有效的基于Adaboost算法的检测方法.该方法通过提取训练样本的梯度方向直方图（HOG）特征，训练一个可用于分类的二类分类器，并采用Gamma校正法对当前帧作图像亮度处理，来降低低照度对特征提取的影响；再通过载入分类器在校正后的当前帧内作多尺度检测，最后用矩形框标识出检测出来的目标，统计车辆数目.实验表明，该方法对交通路口的车辆有较好的实时检测效果，在夜间、雾天及其他能见度低的天气等低照度状况下，也能保持较高的检测率.
Abstract:
As the general vehicle detection systems’ detection ability declines sharply in the night and low light conditions, this paper presents a detection system based on Adaboost algorithm. A two class cascaded classifier was trained by using Histogram of Oriented Gradients(HOG) features of the vehicle samples. The current frame was adjusted by the Gamma correction to reduce the effect of low light intensity on feature extraction. Then the classifier was loaded to do a multi\|scale detection in the adjusted current frame. Eventually the vehicles were counted by marking the detection results with rectangles. The results of experiments show that this system is capable of detecting the vehicles in effective area of the traffic intersection, and can keep a high detection rate in dark scene such as nights, foggy days and other low visibility weather.

参考文献/References:

［1］洪汉玉,王澍,朱浩,等. 低对比度嵌入型钢坯字符识别方法［J］. 武汉工程大学学报,2012,34（12）:38\|43.HONG Han\|yu,WANG Shu,ZHU Hao,et al. Recognition method for low\|contrast embedded billet characters［J］. Journal of Wuhan Institute of Technology,2012,34（12）:38\|43.（in Chinese）［2］洪汉玉,俞喆俊,章秀华. 复杂光照条件下钢坯字符检测方法［J］. 武汉工程大学学报,2012,34（6）:65\|68.HONG Han\|yu,YU Zhe\|jun,ZHANG Xiu\|hua. Detection of billet character in complex illumination conditions［J］. Journal of Wuhan Institute of Technology,2012,34（6）:65\|68.（in Chinese）［3］周良. 低照度图像的车牌检测与识别方法研究［D］. 合肥：合肥工业大学，2012.ZHOU Liang. The Research on License Plate Detection and Recognition for Low illumination Image［D］. Hefei：Hefei University of Technology,2012.(in Chinese)［4］欧志芳. 智能车辆中基于视频的车辆检测算法研究［D］. 长沙：湖南大学，2011.OU Zhi\|fang. Research of Video\|Based Vehicle Detection Algorithm for Intelligent Vehicle［D］. Changsha：Hunan University,2011.(in Chinese)［5］O’Malley R， Jones E， Glavin M. Rear\|lamp vehicle detection and tracking in low\|exposure color video for night conditions［J］. Intelligent Transportation Systems IEEE Transactions on，2010，11(2): 453\|462.［6］O’Malley R，Glavin M，Jones E. Vision\|based detection and tracking of vehicles to the rear with perspective correction in low\|light conditions［J］. IET Intelligent Transport Systems，2011，5(1): 1\|10.［7］Dalal N，Triggs B. Histograms of oriented gradients for human detection［C］. Computer Vision and Pattern Recognition， 2005. CVPR 2005. IEEE Computer Society Conference on. IEEE， 2005（1）: 886\|893.［8］闻帆. 基于视觉的交通路口车辆智能检测技术研究［D］. 哈尔滨：哈尔滨工业大学,2010.WEN fan. A Vision\|Based Intelligent Algorithm Research For Traffic Intersection Vehicle Detection［D］. Harbin：Harbin Institute of Technology,2010.（in Chinese）［9］Freund Y，Schapire R E. A decision\|theoretic Generalization of On\|Line Learning and an Application to Boosting. ［J］ Journal of Computer and System Sciences，1997，55(1): 119\|139.［10］杨述斌,金璐,章振保. 疲劳驾驶检测中的快速人眼定位方法［J］. 武汉工程大学学报,2013,35（6）:67\|72.YANG Shu\|bin,JIN Lu,ZHANG Zhen\|bao. Fast eye location method in driver fatigue detection［J］. Journal of Wuhan Institute of Technology,2013,35（6）:67\|72.（in Chinese）

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：20130907基金项目： 湖北省教育厅科学研究项目计划重点项目(D20111509)；武汉工程大学研究生教育创新基金项目(CX201273)作者简介：王海晖（1969\|），男，河北石家庄人，教授，博士.研究方向：图像处理、机器视觉、模式识别、智能交通控制等.
更新日期/Last Update: 2013-11-11