3D Pose Estimation of Bin Picking Object using Deep Learning and 3D Matching

In this paper, we propose a method to estimate 3D pose information of an object in a randomly piled-up environment by using image data obtained from an RGB-D camera. The proposed method consists of two modules: object detection by deep learning, and pose estimation by Iterative Closest Point (ICP) algorithm. In the first module, we propose an image encoding method to generate three channel images by integrating depth and infrared images captured by the camera. We use these encoded images as both the input data and training data set in a deep learning-based object detection step. Also, we propose a depth-based filtering method to improve the precision of object detection and to reduce the number of false positives by preprocessing input data. ICP-based 3D pose estimation is done in the second module, where we applied a plane-fitting method to increase the accuracy of the estimated pose.

[1]  Sazali Yaacob,et al.  Stereo vision system for a bin picking adept robot , 2007 .

[2]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[3]  Kai-Tai Song,et al.  CAD-based pose estimation for random bin-picking of multiple objects using a RGB-D camera , 2015, 2015 15th International Conference on Control, Automation and Systems (ICCAS).

[4]  Paul J. Besl,et al.  Method for registration of 3-D shapes , 1992, Other Conferences.

[5]  Masayuki Inaba,et al.  3D object segmentation for shelf bin picking by humanoid with deep learning and occupancy voxel grid map , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[6]  Thomas Butkiewicz.  Low-cost coastal mapping using Kinect v2 time-of-flight cameras , 2014, 2014 Oceans - St. John's.

[7]  Reinhard Klein,et al.  Efficient RANSAC for Point‐Cloud Shape Detection , 2007, Comput. Graph. Forum.

[8]  Morten Lind,et al.  A flexible 3D object localization system for industrial part handling , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[10]  Yisheng Guan,et al.  A 3D object detection and pose estimation pipeline using RGB-D images , 2017, 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[11]  Shang-Hong Lai,et al.  3D object detection and pose estimation from depth image for robotic bin picking , 2014, 2014 IEEE International Conference on Automation Science and Engineering (CASE).