Authors:
Junesuk Lee
1
;
Sangseung Kang
2
and
Soon-Yong Park
1
Affiliations:
1
School of Computer Science and Engineering, Kyungpook National University, Daegu and South Korea
;
2
Intelligent Robotics Research Division, Electronics and Telecommunications Research Institute, Daejeon and South Korea
Keyword(s):
Bin Picking, Pose Estimation, Object Detection, Deep Learning, 3D Matching.
Related
Ontology
Subjects/Areas/Topics:
Image Processing
;
Informatics in Control, Automation and Robotics
;
Robotics and Automation
;
Vision, Recognition and Reconstruction
Abstract:
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.