首页 > 论文 > 激光与光电子学进展 > 55卷 > 9期(pp:91005--1)

基于PCA-LDA与SVM的AGV多分支路径识别与跟踪

Recognition and Tracking of AGV Multi-Branch Path Based on PCA-LDA and SVM

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对自动引导车(AGV)视觉引导过程中多分支路径识别与跟踪的实时性与稳健性要求, 提出一种主成分分析(PCA)-线性判别分析(LDA)与支持向量机(SVM)相结合的路径识别算法。首先对AGV行驶过程中拍摄的图像进行预处理, 并用PCA与LDA对处理后的图像进行降维和特征提取, 再利用灰狼优化算法优化后的SVM分类器对图像进行识别。在路径跟踪方面, 利用最小二乘拟合方法计算横向偏差与航向偏差。实验表明, PCA-LDA与SVM相结合能够使路径识别率达到99.3%, 并且满足实时性要求, 路径跟踪误差在20 mm以内, 满足一般工业环境需求。

Abstract

An algorithm combining principal component analysis (PCA)-linear discriminant analysis (LDA) with support vector machine (SVM) is proposed for the real-time and robustness requirements of multi-branch path identification and tracking in the process of automated guided vehicle(AGV) visual guidance. Firstly, the image features are obtained by image preprocessing algorithm and PCA-LDA algorithm. Next, the image is identified by SVM classifier, which is optimized by gray wolf optimization algorithm. In the aspect of path tracking, the lateral deviation and course deviation are calculated by using the least square fitting method. The experimental results show that the rate of path recognition is 99.3% and real-time requirements are achieved by using the algorithm combining PCA-LDA with SVM, and the path tracking error is within 20 mm to meet the general industrial environmental needs.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/lop55.091005

所属栏目:图像处理

基金项目:国家自然科学基金(60973095)、江苏省产学研联合创新资金——前瞻性联合研究项目(BY2015019-29)

收稿日期:2018-03-27

修改稿日期:2018-04-12

网络出版日期:2018-04-17

作者单位    点击查看

茅正冲:江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122
陈强:江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122

联系人作者:陈强(2358041226@qq.com)

【1】Verma N K, Nama P, Kumar G, et al. Vision based object follower automated guided vehicle using compressive tracking and stereo-vision[C]∥2015 IEEE Bombay Section Symposium, September 10-11, 2015, Mumbai, India. New York: IEEE, 2016: 1-6.

【2】Yu J, Chen Y, Ouyang L, et al. An image enhancement method for non-uniform illumination with illumination constraints for vision-guided AGV[C]∥2016 IEEE International Conference on Advanced Mechatronic Systems, November 30-December 3, 2016, Melbourne, VIC, Australia. New York: IEEE, 2017: 148-153.

【3】Draganjac I, Mikli D, Kovai Z, et al. Decentralized control of multi-AGV systems in autonomous warehousing applications[J]. IEEE Transactions on Automation Science and Engineering, 2016, 13(4): 1433-1447.

【4】Ye A, Zhu H, Xu Z, et al. A vision-based guidance method for autonomous guided vehicles[C]∥2012 IEEE International Conference on Mechatronics and Automation, August 5-8, 2012, Chengdu, China. New York: IEEE, 2012: 2025-2030.

【5】Liu H Q. Research on path tracking of visual navigation AGV based on Bessel trajectory[J]. China Measurement & Test, 2017, 43(8): 113-118.
刘海芹. 基于贝塞尔轨迹的视觉导引AGV路径跟踪研究[J]. 中国测试, 2017, 43(8): 113-118.

【6】Wu X, Shen W L, Lou P H, et al. Robust feature recognition and precise path tracking for vision-guided AGV[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(7): 48-56.
武星, 沈伟良, 楼佩煌, 等. 视觉导引AGV鲁棒特征识别与精确路径跟踪研究[J]. 农业机械学报, 2016, 47(7): 48-56.

【7】Zheng S H, Li W G, Liu W M, et al. The research of fast multi-path detection algorithm for visual AGV[J]. Electronic Design Engineering, 2016, 24(11): 177-180.
郑少华, 李伟光, 刘维民, 等. 视觉导航AGV多路径快速检测算法研究[J]. 电子设计工程, 2016, 24(11): 177-180.

【8】Yu J, Lou P H, Wu X, et al. Automated guided vehicle cross path recognition based on rough set and hierarchical support vector machine[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2013, 45(1): 62-69.
喻俊, 楼佩煌, 武星, 等. 基于粗糙集和分层支持向量机的AGV多分支路径识别[J]. 南京航空航天大学学报, 2013, 45(1): 62-69.

【9】Wang Z J, Yu Z J, Ma K, et al. An image filtering algorithm based on adaptive median and gradient inverse weight[J]. Laser & Optoelectronics Progress, 2017, 54(12): 121001.
王志军, 于之靖, 马凯, 等. 一种自适应中值梯度倒数加权的图像滤波算法[J]. 激光与光电子学进展, 2017, 54(12): 121001.

【10】Yu Z J, Wang S B. Improved PCA-SIFT algorithm for matching stereo system [J]. Laser & Optoelectronics Progress, 2016, 53(3): 031501.
于之靖, 王韶彬. 改进PCA-SIFT算法的立体匹配系统[J]. 激光与光电子学进展, 2016, 53(3): 031501.

【11】Wu J, Yang H. Linear regression-based efficient SVM learning for large-scale classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(10): 2357-2369.

【12】Guo Z Z, Liu R, Gong C Q, et al. Study on improvement of gray wolf algorithm[J]. Application Research of Computers, 2017, 34(12): 3603-3606, 3610.
郭振洲, 刘然, 拱长青, 等. 基于灰狼算法的改进研究[J]. 计算机应用研究, 2017, 34(12): 3603-3606, 3610.

【13】Guo K Y, Guo X L, Wang Y W. Analysis and strategy for parameter optimization methods of SVM[J]. Computer Measurement & Control, 2016, 24(6): 255-259.
郭克友, 郭晓丽, 王艺伟. SVM参数优化方法分析与决策[J]. 计算机测量与控制, 2016, 24(6): 255-259.

【14】Park J, Park Y, Kim S W. AGV parking system using artificial visual landmark[J]. International Conference on Control, Automation and Systems 2008, Oct. 14-17, 2008, Seoul, Korea. Seoul: Institute of Control, Robotics and Systems, 2008, 1579-1582.

【15】Wang B X, Song B, Wang S A, et al. The research on visual navigation of AGV in outdoor environment[J]. Applied Mechanics and Materials, 2014, 536/537: 993-998.

【16】Lu S P, Xu C, Zhong R Y. An active RFID tag-enabled locating approach with multipath effect elimination in AGV[J]. IEEE Transactions on Automation Science and Engineering, 2016, 13(3): 1333-1342.

【17】Tang H, Liu Y H. A fully automatic calibration algorithm for a camera odometry system[J]. IEEE Sensors Journal, 2017, 17(13): 4208-4216.

引用该论文

Mao Zhengchong,Chen Qiang. Recognition and Tracking of AGV Multi-Branch Path Based on PCA-LDA and SVM[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091005

茅正冲,陈强. 基于PCA-LDA与SVM的AGV多分支路径识别与跟踪[J]. 激光与光电子学进展, 2018, 55(9): 091005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF