首页 > 论文 > 激光与光电子学进展 > 55卷 > 11期(pp:111505--1)

复杂环境下异形多目标识别与点云获取算法

Multi-Shaped Targets Recognition and Point Clouds Acquisition Algorithm in Complex Environment

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

摘要

研究了复杂环境下不同形状物体的快速识别、定位以及表面检测,旨在满足智能机器在线作业时对复杂环境中的目标进行同步性抓取以及表面检测等需求,讨论了异形物体的多目标快速识别、定位、立体匹配及点云后处理算法。首先,基于稳健主成分分析识别出场景中的新增目标,再运用改进k均值聚类对各目标进行图像定位。然后,通过支持向量机筛选出感兴趣区域,并借助外极线约束进行一维搜索获取双目图像中的待匹配区域,快速获得局部三维点云。最后,进行特定的点云去噪处理以减小误差。实验结果表明,相比于传统方法,本文算法有效缩短了程序运行时间,并有效抑制了由复杂背景引起的各种噪声,提高了在复杂环境下获取点云的精度和自适应性,是一种稳健、有效、快速的三维点云获取算法。

Abstract

Fast recognizing, positioning and surface detection of multi-shaped objects in complex environment are studied to satisfy the requirement of smart machines, which is expected to grab the objects or inspect surface defection in complex environment in real time. Fast recognition, positioning, stereo matching and post-processing algorithm of point clouds are discussed. At first, new targets in the scene are recognized by robust principal component analysis, and the image location of the targets is accurately acquired by improved k-means clustering algorithm. Then, the region of interest is screened out by support vector machine, and one-dimensional searching is carried out by epipolar restriction to obtain the regions to be matched in binocular images, and local three-dimensional point clouds are quickly obtained. Finally, special denoising operation of point clouds is conducted to reduce the error. The experiment results indicate that the proposed algorithm effectively reduces the running time of the process and effectively reduces all the noises caused by complex backgrounds, and improves the accuracy and adaptability of point clouds acquisition in complex environment, and it is a robust, effective and fast algorithm for three-dimensional point clouds acquisition.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop55.111505

所属栏目:机器视觉

基金项目:国家自然科学基金(51578162)、广东省科技计划项目(2016B090912005)、国家重点科技计划(2017YFD0700100)

收稿日期:2018-04-20

修改稿日期:2018-05-20

网络出版日期:2018-05-29

作者单位    点击查看

陈明猷:华南农业大学工程学院, 广东 广州 510642
唐昀超:广东工业大学土木与交通工程学院, 广东 广州 510006
邹湘军:华南农业大学工程学院, 广东 广州 510642
黄矿裕:华南农业大学工程学院, 广东 广州 510642
冯文贤:广东工业大学土木与交通工程学院, 广东 广州 510006
张坡:华南农业大学工程学院, 广东 广州 510642

联系人作者:邹湘军(xjzou1@163.com)

【1】Liu N, Zou X J, Ye M, et al. Research of multiple workpieces positioning under complex environment[J]. Application of Electronic Technique, 2015, 41(12): 120-123, 128.
刘念, 邹湘军, 叶敏, 等. 复杂环境下的多工件定位研究[J]. 电子技术应用, 2015, 41(12): 120-123, 128.

【2】Li B, Chen Y, Zou X J, et al. Work-piece recognition of orientation chamfer matching based on twin-threshold segmentation[J]. Computer Engineering and Design, 2016, 37(3): 720-724.
李博, 陈燕, 邹湘军, 等. 基于二次阈值分割的方向倒脚匹配工件识别[J]. 计算机工程与设计, 2016, 37(3): 720-724.

【3】Zou X J, Lin G C, Tang Y C, et al. Sub-pixel object-image registration using improved iterative closest point method[J]. Journal of Computer-Aided Design & Computer Graphics, 2016, 28(8): 1242-1249.
邹湘军, 林桂潮, 唐昀超, 等. 改进迭代最近点法的亚像素级零件图像配准[J]. 计算机辅助设计与图形学学报, 2016, 28(8): 1242-1249.

【4】Wang X, Zhao Q C, Tan J P. Multiple circle location method using region estimation in complex background[J]. Journal of Central South University(Science and Technology), 2016, 47(7): 2266-2272.
王宪, 赵前程, 谭建平. 应用区域估计的复杂背景多圆快速定位方法[J]. 中南大学学报(自然科学版), 2016, 47(7): 2266-2272.

【5】Li J, Yuan Y. Weak and small target detection under complicated background[J]. Computer and Digital Engineering, 2015, 43(3): 408-411.
李静, 袁媛. 复杂背景下弱小目标的检测[J]. 计算机与数字工程, 2015, 43(3): 408-411.

【6】Wang Z Y, Hui Q. Design of processing technology of glass edging based on visual positioning[J]. Machine Tool & Hydraulics, 2017, 45(16): 29-31.
王再英, 惠强. 基于视觉定位的玻璃磨边加工工艺的设计[J]. 机床与液压, 2017, 45(16): 29-31.

【7】Sun L, Abolhasannejad V, Gao L, et al. Non-contact optical sensing of asphalt mixture deformation using 3D stereo vision[J]. Measurement, 2016, 85: 100-117.

【8】Mo S W, Deng X P, Wang S, et al. Moving object detection algorithm based on improved visual background extractor[J]. Acta Optica Sinica, 2016, 36(6): 0615001.
莫邵文, 邓新蒲, 王帅, 等. 基于改进视觉背景提取的运动目标检测算法[J]. 光学学报, 2016, 36(6): 0615001.

【9】Huang X Y, Xu J L, Guo G, et al. Real-time pedestrian reidentification based on enhanced aggregated channel features[J]. Laser & Optoelectronics Progress, 2017, 54(9): 091001.
黄新宇, 许娇龙, 郭纲, 等. 基于增强聚合通道特征的实时行人重识别[J]. 激光与光电子学进展, 2017, 54(9): 091001.

【10】Liu R, Wang D J, Jia P, et al. Point target detection based on omnidirectional morphological filtering and local characteristics criterion[J]. Acta Optica Sinica, 2017, 37(11): 1104001.
刘让, 王德江, 贾平, 等. 全方位形态学联合局部特征准则的点目标检测[J]. 光学学报, 2017, 37(11): 1104001.

【11】Candès E J, Li X D, Ma Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011, 58(3): 1-37.

【12】Lin Z, Chen M, Ma Y. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices[J]. arXiv, 2012: 1109.0367

【13】Wu C W, Cao J P, Zhu Y H, et al. The global convergence analysis of augmented lagrange multiplier method for nonlinear optimization[J]. Journal of Pingxiang College, 2013, 30(3): 13-17.
吴聪伟, 曹继平, 朱亚红, 等.基于约束优化问题乘子罚函数方法的全局收敛性分析[J]. 萍乡高等专科学校学报, 2013, 30(3): 13-17.

【14】Hou Y F. The research of sparse representation based on low-rank and eigenface for face recognition[D]. Hefei: Anhui University, 2015: 20-58.
侯义福. 基于低秩与特征脸的稀疏表示人脸识别研究[D]. 合肥: 安徽大学, 2015: 20-58.

【15】Rafael G, Richard W. Digital image processing[M]. Beijing: Publishing House of Electronics Industry, 2011: 66.

【16】Heo Y S, Lee K M, Lee S U. Robust stereo matching using adaptive normalized cross-correlation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(4): 807-822.

【17】Gray B, Adrian K. Learning OpenCV[M]. Beijing: Tsinghua University Press, 2012.

【18】Zhang Q. Research of visual recognition algorithm for service robot based on PCL[D]. Hefei: University of Science and Technology of China, 2014.
张强. 基于点云库的服务机器人视觉识别算法研究[D]. 合肥: 中国科学技术大学, 2014.

【19】Li R Z, Yang M, Ran Y, et al. Point cloud denoising and simplification algorithm based on method library[J]. Laser & Optoelectronics Progress, 2018, 55(1): 011008.
李仁忠, 杨曼, 冉媛, 等. 基于方法库的点云去噪与精简算法[J]. 激光与光电子学进展, 2018, 55(1): 011008.

【20】Tian Q H, Bai R L, Li D. Point cloud segmentation of scattered workpieces based on improved euclidean clustering[J]. Laser & Optoelectronics Progress, 2017, 54(12): 121503.
田青华, 白瑞林, 李杜. 基于改进欧氏聚类的散乱工件点云分割[J]. 激光与光电子学进展, 2017, 54(12): 121503.

引用该论文

Chen Mingyou,Tang Yunchao,Zou Xiangjun,Huang Kuangyu,Feng Wenxian,Zhang Po. Multi-Shaped Targets Recognition and Point Clouds Acquisition Algorithm in Complex Environment[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111505

陈明猷,唐昀超,邹湘军,黄矿裕,冯文贤,张坡. 复杂环境下异形多目标识别与点云获取算法[J]. 激光与光电子学进展, 2018, 55(11): 111505

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