Towards 3D object recognition for universal goods in logistic

  • Authors:

  • Bernd Scholz-Reiter;Hendrik Thamer;Claudio Uriarte

  • Affiliations:

  • Bremer Institut für Produktion und Logistik GmbH, University of Bremen, Germany;Bremer Institut für Produktion und Logistik GmbH, University of Bremen, Germany;Bremer Institut für Produktion und Logistik GmbH, University of Bremen, Germany

  • Venue:
  • ECS'10/ECCTD'10/ECCOM'10/ECCS'10 Proceedings of the European conference of systems, and European conference of circuits technology and devices, and European conference of communications, and European conference on Computer science
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The increasing globalization of trade flows causes a continuous growth of packaged goods which are transported in standard container units. The automatic unloading of packaged goods and the following transfer in further processing logistic systems is a major technical challenge. Therefore, an efficient object recognition system is required. Since the development and the successful market launch of the Paketroboter©, an automatic unloading of cubic goods is already possible. However, there is actually no established system which is able to unload universal bulk goods automatically, because a suitable object recognition system for goods with undefined shapes is necessary. In this paper, the EMOSES project is presented that is aimed to develop an object recognition system that is suitable for classification and pose detection of universal packaged goods inside a standard container unit. In order to classify different packaged goods inside a poorly lit container unit the paper presents a concept for object recognition of universal goods. Therefore, applicable sensor data is required that include, in addition to 2D information, information about depth. Hence, range images from Time-of-Flight cameras and simulated images are used for image analysis.