Pose Estimation of Stacked Rectangular Objects from Depth Images

Daiki Matsuno, Ryo Hachiuma, Hideo Saito, Junichi Sugano, Hideyuki Adachi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper addresses the task of six degrees of freedom (6-DoF) pose estimation of stacked rectangular objects from depth images. Object pose estimation is one of the key challenges for visual processing systems since it plays a vital role in many situations such as warehouse/factory automation, robotic manipulation, and augmented reality. Many recent approaches to object pose estimation use RGB information for detecting and estimating the pose of objects. However, in warehouse/factory automation, objects are often small, occluded, cluttered, and texture-less which makes it difficult to utilize RGB features for detection and pose estimation. In order to overcome this restriction, we use only the depth information (without RGB information) and its geometric features to segment each object and to estimate the 6-DoF (position and orientation) in a stacked scene. We segment the rectangular objects in each scene from the depth and surface normal discontinuities (geometric segmentation). From the geometrically segmented image, four object corner points can be estimated using the convex hull detection and the eight corner points, which are required for the 6-DoF pose estimation, can be calculated. To improve the accuracy of orientation estimation, we estimate four orientation candidates and select the best among them. Experimental results using two evaluation methods show that our method outperformed the baseline method.

Original languageEnglish
Title of host publication2020 IEEE 29th International Symposium on Industrial Electronics, ISIE 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1409-1414
Number of pages6
ISBN (Electronic)9781728156354
DOIs
Publication statusPublished - 2020 Jun
Event29th IEEE International Symposium on Industrial Electronics, ISIE 2020 - Delft, Netherlands
Duration: 2020 Jun 172020 Jun 19

Publication series

NameIEEE International Symposium on Industrial Electronics
Volume2020-June

Conference

Conference29th IEEE International Symposium on Industrial Electronics, ISIE 2020
CountryNetherlands
CityDelft
Period20/6/1720/6/19

Keywords

  • 6-DoF pose estimation
  • depth image
  • geometric segmentation
  • rectangular objects

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Pose Estimation of Stacked Rectangular Objects from Depth Images'. Together they form a unique fingerprint.

  • Cite this

    Matsuno, D., Hachiuma, R., Saito, H., Sugano, J., & Adachi, H. (2020). Pose Estimation of Stacked Rectangular Objects from Depth Images. In 2020 IEEE 29th International Symposium on Industrial Electronics, ISIE 2020 - Proceedings (pp. 1409-1414). [9152510] (IEEE International Symposium on Industrial Electronics; Vol. 2020-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIE45063.2020.9152510