基于图像纹理的散料装车料位识别试验研究

中国机械工程 ›› 2013, Vol. 24 ›› Issue (07): 910-914.

基于图像纹理的散料装车料位识别试验研究

田明锐1;胡永彪1;金守峰2

1.长安大学道路施工技术与装备教育部重点实验室,西安,710064
2.西安工程大学,西安,710048

出版日期:2013-04-10 发布日期:2013-04-27
基金资助:
中央高校基本科研业务费专项资金资助项目（CHD2010ZY011）
Fundamental Research Funds for the Central Universities( No. CHD2010ZY011)

Experimental Study on Level Detection of Bulk Material Entrucking Based on Image Texture

Tian Mingrui1;Hu Yongbiao1;Jin Shoufeng2

1.Key Laboratory of Highway Construction Technology & Equipment,Ministry of Education,Chang'an University,Xi'an,710064
2.Xi'an Polytechnic University,Xi'an,710048

Online:2013-04-10 Published:2013-04-27
Supported by:
Fundamental Research Funds for the Central Universities( No. CHD2010ZY011)

摘要/Abstract

摘要：

针对散料自动装车中超声波料位检测方法不能反映料堆实际形态的缺点,提出了基于图像纹理识别的料位检测方法。首先,对原图像进行同态滤波及二值化预处理,以增强图像纹理并减小纹理特征提取计算量;然后,计算装车图像的共生矩阵纹理特征,并对所计算的特征进行主成分分析降维;最后,利用决策树分类算法对装车料位图像进行分块识别并拟合出直线料位。试验结果表明,所提方法料位识别平均偏差为6.5像素,料位识别率为96%,每帧图像处理时间约0.2s。算法基本满足散料装车料位实时检测的要求。

关键词: 机器视觉, 散料装车, 料位识别, 纹理特征

Abstract:

In order to solve the problem that the ultrasonic level detection cannot reflect the actual level of bulk material entrucking, a new method was presented based on image texture recognition. First, the image was enhanced with the homomorphic filter, and the binarization processing was applied to cut down the amount of calculation of the texture features extracting. Then, the co-occurrence matrix texture features were calculated, and principal component analysis method was used to reduce the dimensionality of the feature space. Finally, the image partitions were recognized by decision tree, and the level was linear fitted by the image segmentation result. Experimental results indicate that the mean error is as 6.5 pixels, and the recognition rate is as 96%. The processing time is as 0.2 seconds per frame. It can satisfy the real-time level detection of bulk material entrucking.

Key words: machine vision, bulk material entrucking, level detection, texture feature

中图分类号:

TP391.4

田明锐1, 胡永彪1, 金守峰2. 基于图像纹理的散料装车料位识别试验研究[J]. 中国机械工程, 2013, 24(07): 910-914.

TIAN Meng-Dui-1, HU Yong-Biao-1, JIN Shou-Feng-2. Experimental Study on Level Detection of Bulk Material Entrucking Based on Image Texture[J]. China Mechanical Engineering, 2013, 24(07): 910-914.

参考文献

[1]王芳,江剑,石秀东,等.沥青混凝土成品装车指挥仪的研制[J].微计算机信息,2009,25(29):14-15.
Wang Fang, Jiang Jian, Shi Xiudong, et al. Development of the Director in the Load of Finished Asphalt Concrete[J]. Microcomputer Information, 2009,25(29):14-15.
[2]吴延明,郝晓弘.平硐矿车智能装车系统的研究与实现[J].工矿自动化,2008(4):106-107.
Wu Yanming, Hao Xiaohong. Research and Implementation of the Intelligence Adit Harvester Loading System[J].Industry and Mine Automation, 2008(4):106-107.
[3]刘学东.选煤厂自动装车系统控制过程分析[J].选煤技术,2008(6):55-58.
Liu Xuedong. The Analysis of Control Process of Automatic Loading System in Coal Preparation Plant[J]. Coal Preparation Technology, 2008(6):55-58.
[4]Murtagh F，Qiao Xiaoyu，Walsh P.Grading of Construction Aggregate through Machine Vision: Results and Prospects[J].Computers in Industry,2005,56(8):905-917.
[5]于桂君，习重华.机器视觉应用于混凝土加料的对接定位方法[J].工业控制计算机,2005,18(5):59-60.
Yu Guijun, Xi Chonghua.Automatic Dock of Cement Mixing Station Using Computer Vision[J]. Industrial Control Computer,2005,18(5):59-60.
[6]潘国林，高幼年.基于机器视觉煤仓料位测量方法的研究[J].上海电力学院学报,2007,23(2):176-178.
Pan Guolin, Gao Younian.A Level Measurement Method for Coal Warehouse Based on Machine Vision[J]. Journal of Shanghai University of Electric Power,2007,23(2):176-178.
[7]向长波,宋明,宋建中,等.光切法测量运动车厢中煤堆的体积[J].光学技术,2009,35(2):225-228.
Xiang Changbo, Song Ming, Song Jianzhong,et al. Coal Volume Measuring in Mobile Carriage with Light-sectioning Method[J]. Optical Technique,2009,35(2):225-228.
[8]Haralick R M, Shanmugam K, Dinstein I. Texture Features for Image Classification[J]. IEEE Transaction on Systems, Man and Cybernetics, 1973, 3(6): 610-621.
[9]刘丽,匡纲要.图像纹理特征提取方法综述[J]. 中国图象图形学报，2009,14(4):622-635.
Liu li, Kuang Gangyao. Overview of Image Textural Feature Extraction Methods[J].Journal of Image and Graphics,2009,14(4):622-635.
[10]扈静,刘明周,龚任波,等.基于主成分分析的汽车操纵力舒适性分析与评价[J].中国机械工程,2011,22(20):2456-2459.
Hu Jing, Liu Mingzhou,Gong Renbo,et al.Evaluation of Vehicle Operating Force Comfort Based on Principal Component Analysis[J]. China Mechanical Engineering,2011,22(20):2456-2459.
[11]王峻峰,史铁林,刘世元,等.基于主分量分析的信号白化解相关处理[J].中国机械工程,2005,16(21):1954-1956.
Wang Junfeng, Shi Tielin, Liu Shiyuan, et al. PCA-based Signal Whitening Decorrelation[J].China Mechanical Engineering, 2005,16(21):1954-1956.
[12]王志芳,严新平,袁成清,等.基于决策树的摩擦学系统状态辨识的知识获取方法研究[J].中国机械工程,2007,18(16):1962-1965.
Wang Zhifang, Yan Xinping, Yuan Chengqing,et al. Study on Knowledge Acquisition Approach in Tribological Systemic Condition Identification Using Decision Trees[J].China Mechanical Engineering, 2007,18(16):1962-1965.

[1]	李茂月;吕虹毓;王飞;贾冬开. 基于机器视觉的智能车辆鲁棒车道线识别方法[J]. 中国机械工程, 2021, 32(02): 242-251.
[2]	陈天凡, 高诚辉, 何炳蔚. 自遮挡物体线激光测量视点规划[J]. 中国机械工程, 2016, 27(10): 1370-1376.
[3]	田明锐, 胡永彪, 金守峰. 结合SVM后验概率的散料料位识别试验研究[J]. 中国机械工程, 2016, 27(05): 646-651.
[4]	郑金驹, 李文龙, 王瑜辉, 罗明成. QFP芯片外观视觉检测系统及检测方法[J]. 中国机械工程, 2013, 24(3): 290-294,301.
[5]	杨庆华1, 陈亮1, 荀一1, 陈文彪2. 基于机器视觉的PCB裸板缺陷自动检测方法[J]. 中国机械工程, 2012, 23(22): 2661-2666.
[6]	陈天凡1, 2, 高诚辉1, 何炳蔚1. 物体三维数字化中消除遮挡孔洞的视点规划方法研究[J]. 中国机械工程, 2012, 23(21): 2585-2590.
[7]	周博文, 王耀南, 张辉, 葛继. 基于机器视觉的酒液智能检测系统研究与开发 [J]. 中国机械工程, 2010, 21(7): 766-772,821.
[8]	张辉;王耀南;葛继;周博文;. 液体药品异物检测智能机器人系统的设计[J]. 中国机械工程, 2009, 20(20): 0-2519.
[9]	伍济钢;宾鸿赞;. 薄片零件机器视觉图像亚像素边缘检测[J]. J4, 2009, 20(03): 0-266.
[10]	何博侠;张志胜;徐孙浩;史金飞;. 大尺寸机械零件的机器视觉高精度测量方法[J]. J4, 2009, 20(01): 0-14,1.
[11]	陈自新;黄仁;史金飞;张志胜;. 一种基于阈值的粗糙度评定新方法[J]. J4, 2008, 19(24): 0-2903.
[12]	窦燕;孔令富;. 一种基于视觉注意机制的刀具检测方法[J]. J4, 2008, 19(17): 0-2089.
[13]	邹欣珏, 熊振华, 王禹林, 丁汉. 基于机器视觉的激光植球系统标定[J]. 中国机械工程, 2007, 18(19): 2340-2345.