Abstract

This paper proposes a stereo matching method enhanced by instance segmentation results obtained by a deep convolutional neural network. The system configuration and bin picking process flow are newly suggested by using the proposed method and it is applied to the bin picking problem for tiny cubic workpieces. The picking plan is generated by applying Harris corner detector to the point-cloud in the 3-dimensional map. In the experiments, two kinds of piles consisting of cubes with a side of 10 [mm] or 5 [mm] are tested for bin picking. In these bin picking problems, all cubes are successfully picked up and the results show the feasibility of proposed method. As future work, not only cubes but also other arbitrarily shaped workpieces should be recognized.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.