Object recognition and pose estimation for industrial applications: A cascade system

The research work presented in this paper focuses on the development of a 3D object localization and recognition system to be used in robotics conveyor coating lines. These requirements were specified together with enterprises with small production series seeking a full robotic automation of their production line that is characterized by a wide range of products in simultaneous manufacturing. Their production process (for example heat or coating/painting treatments) limits the use of conventional identification systems attached to the object in hand. Furthermore, the mechanical structure of the conveyor introduces geometric inaccuracy in the object positioning. With the correct classification and localization of the object, the robot will be able to autonomously select the right program to execute and to perform coordinate system corrections. A cascade system performed with Support Vector Machine and the Perfect Match (point cloud geometric template matching) algorithms was developed for this purpose achieving 99.5% of accuracy. The entire recognition and pose estimation procedure is performed in a maximum time range of 3s with standard off the shelf hardware. It is expected that this work contributes to the integration of industrial robots in highly dynamic and specialized production lines.

[1]  Sebastian Thrun,et al.  3D shape scanning with a time-of-flight camera , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Gary R. Bradski,et al.  Fast 3D recognition and pose using the Viewpoint Feature Histogram , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Sergiu Nedevschi,et al.  Stereovision Approach for Obstacle Detection on Non-Planar Roads , 2004, ICINCO.

[4]  Jose-Juan Hernandez-Lopez,et al.  Detecting objects using color and depth segmentation with Kinect sensor , 2012 .

[5]  Nick G. Kingsbury,et al.  Rotation-invariant local feature matching with complex wavelets , 2006, 2006 14th European Signal Processing Conference.

[6]  Abdullah Ferikoglu,et al.  Development of a vision based object classification system for an industrial robotic manipulator , 2001, ICECS 2001. 8th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.01EX483).

[7]  J. Flusser,et al.  Moments and Moment Invariants in Pattern Recognition , 2009 .

[8]  Andreas Birk,et al.  On map merging , 2005, Robotics Auton. Syst..

[9]  Pedro Neto,et al.  A low-cost laser scanning solution for flexible robotic cells: spray coating , 2012, ArXiv.

[10]  Daniel N. Rockmore,et al.  The FFT: an algorithm the whole family can use , 2000, Comput. Sci. Eng..

[11]  Kpalma Kidiyo,et al.  A Survey of Shape Feature Extraction Techniques , 2008 .

[12]  Pinhas Ben-Tzvi,et al.  Extraction of 3D images using pitch-actuated 2D laser range finder for robotic vision , 2010, 2010 IEEE International Workshop on Robotic and Sensors Environments.

[13]  Christian Schlegel,et al.  Mobile Manipulation in Service Robotics: Scene and Object Recognition with Manipulator-Mounted Laser Ranger , 2010, ISR/ROBOTIK.

[14]  A. Paulo Moreira,et al.  Object recognition using laser range finder and machine learning techniques , 2013 .

[15]  Mohamed A. Khabou,et al.  Shape recognition using eigenvalues of the Dirichlet Laplacian , 2007, Pattern Recognit..

[16]  Jianwei Zhang,et al.  3D scene reconstruction based on a moving 2D laser range finder for service-robots , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[17]  Marcus Hutter,et al.  A Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation , 2011, 2011 International Conference on Digital Image Computing: Techniques and Applications.

[18]  Juan Pérez-Oria,et al.  Identification and Defect Inspection with Ultrasonic Techniques in Foundry Pieces , 1998, IEA/AIE.

[19]  Giovanna Sansoni,et al.  State-of-The-Art and Applications of 3D Imaging Sensors in Industry, Cultural Heritage, Medicine, and Criminal Investigation , 2009, Sensors.

[20]  Germano Veiga,et al.  Recognizing Industrial Manipulated Parts Using the Perfect Match Algorithm , 2013 .

[21]  Antonio Torralba,et al.  Object Detection and Localization Using Local and Global Features , 2006, Toward Category-Level Object Recognition.

[22]  Martin Lauer,et al.  Calculating the Perfect Match: An Efficient and Accurate Approach for Robot Self-localization , 2005, RoboCup.

[23]  Vincent Lepetit,et al.  Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes , 2012, ACCV.

[24]  Mandava Rajeswari,et al.  Neural network-based robot visual positioning for intelligent assembly , 2004, J. Intell. Manuf..

[25]  Cordelia Schmid,et al.  Toward Category-Level Object Recognition , 2006, Toward Category-Level Object Recognition.

[26]  Stavros Paschalakis,et al.  Pattern recognition in grey level images using moment based invariant features , 1999 .

[27]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[28]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[29]  M.P. Dale,et al.  Fingerprint matching using transform features , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

[30]  Jianwei Zhang,et al.  Multi sensor fusion of camera and 3D laser range finder for object recognition , 2010, 2010 IEEE Conference on Multisensor Fusion and Integration.