[1]江 励,熊达明,汤健华,等.自然光线环境中的空间物体快速识别和定位算法研究[J].机械与电子,2022,(06):8-13.
 JIANG Li,XIONG Daming,TANG Jianhua,et al.Recognition and Positioning Algorithm of Space Objects in Natural Light Environment[J].Machinery & Electronics,2022,(06):8-13.
点击复制

自然光线环境中的空间物体快速识别和定位算法研究()
分享到:

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2022年06期
页码:
8-13
栏目:
设计与研究
出版日期:
2022-06-24

文章信息/Info

Title:
Recognition and Positioning Algorithm of Space Objects in Natural Light Environment
文章编号:
1001-2257(2022)06-0008-06
作者:
江 励熊达明汤健华黄 辉
五邑大学智能制造学部,广东 江门 529099
Author(s):
JIANG LiXIONG DamingTANG JianhuaHUANG Hui
(Faculty of Intelligent Manufacturing,Wuyi University,Jiangmen 529099,China)
关键词:
深度学习目标识别实例分割空间定位智能抓取
Keywords:
deep learningtarget recognitioninstance segmentationspatial positioningintelligent grasping
分类号:
TP242. 6
文献标志码:
A
摘要:
针对智能机械臂在自然光环境的三维空间中对目标物体的自主识别率和定位精度低的问题,提出了一种基于深度学习的视觉和光学雷达融合定位算法,实现自然光线下空间物体的高精度快速定位。首先,采集 RGB 图像和深度数据,利用深度学习算法对图像进行目标识别与实例分割;然后,将实例分割目标物的二维深度矩阵转换成三维空间点云;最后,用综合修正算法对位置修正,实现对目标物体在三维空间的抓取位置精准定位。 通过不同光照强度下的目标物体识别和定位实验验证了该算法的有效性和实用性,获取的目标物体的三维空间坐标较为精确,单位距离的定位误差在 0. 5%以内,受照明亮度影响较小,对机械臂智能抓取的研究具有较为重要的意义。
Abstract:
Aiming at the problem of low autonomous recognition rate and low positioning accuracy of target objects in the three-dimensional space of natural light environment,a deep learning-based vision and optical radar fusion positioning algorithm is proposed to achieve high precision of space objects and rapid positioning under natural light. Firstly,deep learning algorithms is adopted to perform target recognition and instance segmentation of the image by collecting RGB images and depth data. Then,the two-dimensional depth matrix of the instance segmentation target is converted into a three-dimensional point cloud. Finally,a comprehensive correction algorithm is applied to correct the position for achieving precise positioning of grasping position of the target object in three-dimensional space. The effectiveness and practicability of the proposed algorithm is verified through target object recognition and positioning experiments under different light intensities. The three dimensional space coordinates of the target object obtained are more accurate,and the positioning error per unit distance is within 0. 5%,which is less affected by illumination brightness. The research on intelligent grasping of robotic arms i of great significance.

参考文献/References:

[1] CHELLA A,DINDO H,MATRAXIA F,et al. Real-time visual grasp synthesis using genetic algorithms and neural networks[C]//Congress of the Italian Association for Artificial Intelligence on AI ? IA:Artificial Intelligence and Human-oriented Computing. Berlin:Springer-Verlag, 2007:567-578.

[2] WANGT,WANG W J,WEI F. An overview of control strategy and trajectory planning of visual servoing[M]. Singapore:Springer Singapore,2020:358-370.
[3] LIANG C C,ZHANG X D,DONG P,et al. Research of visual servo control system for space intelligent robot[C]//2015 IEEE Advanced InformationTechnology,Electronic and Automation Control Conference( IAEAC). New York:IEEE,2015:96-100.
[4] RUSU R B,COUSINS S. 3D is here:point cloud library(PCL)[C]//IEEE International Conference on Robotics and Automation. IEEE,2011:1-4.
[5] HAFIZ A M,BHAT G M. A survey on instance segmentation:state of the art[J]. International journal of multimedia information retrieval,2020,9:171-189.
[6] 彭秋辰,宋亦旭. 基于 Mask R-CNN 的物体识别和定位[J]. 清华大学学报(自然科学版),2019,59(2):135-141.
[7] EZRA E,SHARIR M,EFRAT A. On the performance of the ICP algorithm[J]. Computational geometry,2008,41(1/2):77-93.
[8] LIU F,ZHANG J X,WANG J,et al. The indoor localization of a mobile platform based on monocular vision and coding images[J]. International journal of geo-information,2020,9(2):122-143.
[9] RUAN D X,ZHANG W T,QIAN D. Feature-based autonomous target recognition and grasping of industrial robots[J]. Personal and ubiquitous computing,2021(1):1-13.
[10] QI C R,SU H,MO K C,et al. PointNet:deep learning on point sets for 3D classification and segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE,2017:77-85.
[11] QI C R,YI L,SU H,et al. PointNet++:deep hierarchical feature learning on point sets in a metric space[J]. arXiv preprint arXiv:1706. 02431,2017.
[12] HE K,GKIOXARI G,DOLLáR P,et al. Mask R-CNN[J]. IEEE Transactions on pattern analysis and machine intelligence,2020,42(2):2980-2988.
[13] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on pattern analysis and machine intelligence,2017,39(6):1137-1149.

相似文献/References:

[1]吴笛,陈丁,倪晋平.带有炸点识别的图像采集系统设计[J].机械与电子,2018,(12):14.
 WU Di,CHEN Ding,NI Jinping.Design of Image Acquisition System with Burst Point Recognition[J].Machinery & Electronics,2018,(06):14.
[2]王骁贤,张保华,陆思良.基于连续小波变换和卷积神经网络的无刷直流电机故障诊断[J].机械与电子,2018,(06):29.
 WANG Xiaoxian,ZHANG Baohua,LU Siliang.Fault Diagnosis of Brushless Direct Current Motor Based on Continuous Wavelet Transform and Convolutional Neural Network[J].Machinery & Electronics,2018,(06):29.
[3]刘志宇,黄亦翔.基于深度学习和迁移学习的液压泵健康评估方法[J].机械与电子,2018,(09):67.
 LIU Zhiyu,HUANG Yixiang.Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning[J].Machinery & Electronics,2018,(06):67.
[4]严 熠1,2,杨盛毅2,等.飞行器悬挂载荷的视觉位置测量方法[J].机械与电子,2019,(12):69.
 ,,et al.Position Measurement Method for Suspension Load of Aircraft by Monocular Vision[J].Machinery & Electronics,2019,(06):69.
[5]肖倩宏,康 鹏,杜 江,等.深度学习在电网智能调控系统中应用研究[J].机械与电子,2021,(01):38.
 XIAO Qianhong,KANG Peng,DU Jiang,et al.Research on the Application of Deep Learning Theory in Power Grid Intelligent Dispatching[J].Machinery & Electronics,2021,(06):38.
[6]许 哲,张少帅,郭 璐,等.无人机深度学习去雾算法[J].机械与电子,2021,(04):13.
 XU Zhe,ZHANG Shaoshuai,GUO Lu,et al. Deep Learning Defogging Algorithm for UAV[J].Machinery & Electronics,2021,(06):13.
[7]齐爱玲1,李 琳1,朱亦轩2,等.基于融合特征的双通道CNN滚动轴承故障识别[J].机械与电子,2021,(05):15.
 QI Ailing,LI Lin,ZHU Yixuan,et al.Dual Channel CNN Bearing Fault Identification Based on Fusion Feature[J].Machinery & Electronics,2021,(06):15.
[8]徐先峰,郑少杰,赵 依,等.基于数据分解与重构的光伏发电功率超短期预测[J].机械与电子,2022,(04):20.
 XU Xianfeng,ZHENG Shaojie,ZHAO Yi,et al.Ultra-short-term Prediction of Photovoltaic Power Generation Based on Data Decomposition and Deconstruction[J].Machinery & Electronics,2022,(06):20.
[9]王西志,管声启,张理博,等.基于视觉引导的工业棒材上料系统研究[J].机械与电子,2023,41(05):19.
 WANG Xizhi,GUAN Shengqi,ZHANG Libo,et al.Research on Industrial Bar Feeding System Based on Visual Guidance[J].Machinery & Electronics,2023,41(06):19.
[10]王 青,吕绪山,党 帅,等.基于深度学习的纱管识别方法研究[J].机械与电子,2023,41(12):20.
 WANG Qing,LYU Xushan,DANG Shuai,et al.Research on Yarn Bobbin Detection Method Based on Deep Learning[J].Machinery & Electronics,2023,41(06):20.

备注/Memo

备注/Memo:
收稿日期:2021-12-19
基金项目:国家自然科学基金青年基金项目(51905384);区域联合基金项目(2019A1515110258)
作者简介:江 励 (1984-),男,湖北黄石人,博士,副教授,研究方向为智能制造及机器人技术;熊达明 (1989-),男,湖南湘乡人,硕士,研究方向为智能制造及机器人技术;汤健华 (1984-),男,广东江门人,博士,讲师,研究方向为智能制造及机器人技术;黄 辉 (1980-),男,广东江门人,硕士,副教授,研究方向为电气设备在线监测和工业自动化控制。
更新日期/Last Update: 2022-06-23