采用MSBN多智能体协同推理的智能农业车辆环境识别
|
摘要
为了解决智能农业车辆对所处复杂农田环境的识别信度定量分析困难的问题,提出了基于多连片贝叶斯网(MSBN)多智能体协同推理的目标识别算法.该方法把多智能体图像采集系统的局部信息表征在MSBN模型中,在观测不完备条件下,虽然单个智能体仅拥有目标的局部观测信息,但利用重叠子域信息的更新可以进行子网间消息的传播.利用MSBN局部推理和子网间信度通信的全局推理对多源信息进行融合,以提高识别性能.实验结果表明,与传统神经网络或BN方法相比,基于MSBN目标识别算法有效地对多源信息进行了补充,可以提高农业车辆在复杂环境进行识别的准确性.
In order to solve the problem existing in the agricultural environment recognition of intelligent vehicles,due to the difficulty of conducting quantitative analysis of the reliability of such recognition,a target recognition algorithm for multi-agent cooperative inference based on the multiply sectioned Bayesian network( MSBN) has been proposed. This method characterizes local information of the multi-agent image acquiring system with MSBN model.In the circumstance of incomplete observations,although each single agent may only capture some local observation information from the target,the message propagation among subnets can be achieved by information update in the overlapping sub-domains. By combining the local inference and global inference of reliability communication between subnets in MSBN,the multi-source information was merged to enhance recognition performance. By comparing the traditional neural network and BN method,experimental results illustrate that,the target recognition algorithm based on MSBN can effectively supplement multi-source information,and thus,can improve the recognition accuracy of agricultural vehicles in the complicated environment.
In order to solve the problem existing in the agricultural environment recognition of intelligent vehicles,due to the difficulty of conducting quantitative analysis of the reliability of such recognition,a target recognition algorithm for multi-agent cooperative inference based on the multiply sectioned Bayesian network( MSBN) has been proposed. This method characterizes local information of the multi-agent image acquiring system with MSBN model.In the circumstance of incomplete observations,although each single agent may only capture some local observation information from the target,the message propagation among subnets can be achieved by information update in the overlapping sub-domains. By combining the local inference and global inference of reliability communication between subnets in MSBN,the multi-source information was merged to enhance recognition performance. By comparing the traditional neural network and BN method,experimental results illustrate that,the target recognition algorithm based on MSBN can effectively supplement multi-source information,and thus,can improve the recognition accuracy of agricultural vehicles in the complicated environment.
引文
[1]BAKKER T,WOUTERS H,ASSELT K,et al.A vision based row detection system for sugar beet[J].Computers and Electronics in Agriculture,2008,60(1):87-95.
[2]GOTTSCHALK R,BURGOS-ARTIZZU X P,RIBEIRO A,et al.Real-time image processing for the guidance of a small agricultural field inspection vehicle[J].International Journal of Intelligent Systems Technologies and Applications,2010,8(1):434-443.
[3]王典,刘晋浩,王建利.基于系统聚类的林地内采育目标识别与分类[J].农业工程学报,2011,27(12):173-177.WANG Dian,LIU Jinhao,WANG Jianli.Identification and classification of scanned target in forest based on hierarchical cluster[J].Transactions of the Chinese Society of Agricultural Engineering,2011,27(12):173-177.
[4]ROVIRA-MA F,ZHANG Q,REID J F,et al.Hough-transform-based vision algorithm for crop row detection of an automated agricultural vehicle[J].Journal of Automobile Engineering,2005,219(8):999-1010.
[5]赵博,王猛,毛恩荣,等.农业车辆视觉实际导航环境识别与分类[J].农业机械学报,2009,40(7):166-170.ZHAO Bo,WANG Meng,MAO Enrong,et al.Recognition and classification for vision navigation application environment of agricultural vehicle[J].Transactions of the Chinese Society for Agricultural Machinery,2009,40(7):166-170.
[6]PEARL J.Causality:models,reasoning and inference[M].2nd ed.Cambridge,UK:Cambridge University Press,2009.
[7]TANG Zheng,GAO Xiaoguang.Research on the self-defence electronic jamming decision-making based on the discrete dynamic Bayesian network[J].Journal of Systems Engineering and Electronics,2008,19(4):702-708.
[8]XIANG Y,SMITH J,KROES J.Multiagent Bayesian forecasting of structural time-invariant dynamic systems with graphical models[J].International Journal of Approximate Reasoning,2011,52(7):960-977.
[9]XIANG Yang.Probabilistic reasoning in multiagent systems:a graphical models approach[M].Cambridge,UK:Cambridge University Press,2002.
[10]田凤占,张宏伟,陆玉昌,等.多模块贝叶斯网络中推理的简化[J].计算机研究与发展,2003,40(8):1230-1237.TIAN Fengzhan,ZHANG Hongwei,LU Yuchang,et al.Simplification of inferences in multiply sectioned Bayesian networks[J].Journal of Computer Research and Development,2003,40(8):1230-1237.
[11]郭文强,高晓光,侯勇严.复杂系统的图模型多智能体协同故障诊断[J].计算机应用,2010,30(11):2916-2919.GUO Wenqiang,GAO Xiaoguang,HOU Yongyan.Graphical model-based multi-agent coordination fault diagnosis for complex system[J].Journal of Computer Applications,2010,30(11):2916-2919.
[12]XIANG Yang,JENSEN F V,CHEN Xiaoyun.Inference in multiply sectioned Bayesian networks:methods and performance comparison[J].IEEE Transactions on Systems,Man,and Cybernetics—Part B:Cybernetics,2006,36(6):546-558.
[2]GOTTSCHALK R,BURGOS-ARTIZZU X P,RIBEIRO A,et al.Real-time image processing for the guidance of a small agricultural field inspection vehicle[J].International Journal of Intelligent Systems Technologies and Applications,2010,8(1):434-443.
[3]王典,刘晋浩,王建利.基于系统聚类的林地内采育目标识别与分类[J].农业工程学报,2011,27(12):173-177.WANG Dian,LIU Jinhao,WANG Jianli.Identification and classification of scanned target in forest based on hierarchical cluster[J].Transactions of the Chinese Society of Agricultural Engineering,2011,27(12):173-177.
[4]ROVIRA-MA F,ZHANG Q,REID J F,et al.Hough-transform-based vision algorithm for crop row detection of an automated agricultural vehicle[J].Journal of Automobile Engineering,2005,219(8):999-1010.
[5]赵博,王猛,毛恩荣,等.农业车辆视觉实际导航环境识别与分类[J].农业机械学报,2009,40(7):166-170.ZHAO Bo,WANG Meng,MAO Enrong,et al.Recognition and classification for vision navigation application environment of agricultural vehicle[J].Transactions of the Chinese Society for Agricultural Machinery,2009,40(7):166-170.
[6]PEARL J.Causality:models,reasoning and inference[M].2nd ed.Cambridge,UK:Cambridge University Press,2009.
[7]TANG Zheng,GAO Xiaoguang.Research on the self-defence electronic jamming decision-making based on the discrete dynamic Bayesian network[J].Journal of Systems Engineering and Electronics,2008,19(4):702-708.
[8]XIANG Y,SMITH J,KROES J.Multiagent Bayesian forecasting of structural time-invariant dynamic systems with graphical models[J].International Journal of Approximate Reasoning,2011,52(7):960-977.
[9]XIANG Yang.Probabilistic reasoning in multiagent systems:a graphical models approach[M].Cambridge,UK:Cambridge University Press,2002.
[10]田凤占,张宏伟,陆玉昌,等.多模块贝叶斯网络中推理的简化[J].计算机研究与发展,2003,40(8):1230-1237.TIAN Fengzhan,ZHANG Hongwei,LU Yuchang,et al.Simplification of inferences in multiply sectioned Bayesian networks[J].Journal of Computer Research and Development,2003,40(8):1230-1237.
[11]郭文强,高晓光,侯勇严.复杂系统的图模型多智能体协同故障诊断[J].计算机应用,2010,30(11):2916-2919.GUO Wenqiang,GAO Xiaoguang,HOU Yongyan.Graphical model-based multi-agent coordination fault diagnosis for complex system[J].Journal of Computer Applications,2010,30(11):2916-2919.
[12]XIANG Yang,JENSEN F V,CHEN Xiaoyun.Inference in multiply sectioned Bayesian networks:methods and performance comparison[J].IEEE Transactions on Systems,Man,and Cybernetics—Part B:Cybernetics,2006,36(6):546-558.