DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Depth-aware object segmentation and grasp detection for robotic picking tasks

Ainetter, Stefan and Böhm, Christoph and Dhakate, Rohit Sudhakar and Weiss, Stephan and Fraundorfer, Friedrich (2021) Depth-aware object segmentation and grasp detection for robotic picking tasks. 32th British Machine Vision Conference (BMVC), 22.-25. Nov. 2021, UK, Online.

[img] PDF

Official URL: https://www.bmvc2021-virtualconference.com/


In this paper, we present a novel deep neural network architecture for joint classagnostic object segmentation and grasp detection for robotic picking tasks using a parallelplate gripper. We introduce depth-aware Coordinate Convolution (CoordConv), a method to increase accuracy for point proposal based object instance segmentation in complex scenes without adding any additional network parameters or computation complexity. Depth-aware CoordConv uses depth data to extract prior information about the location of an object to achieve highly accurate object instance segmentation. These resulting segmentation masks, combined with predicted grasp candidates, lead to a complete scene description for grasping using a parallel-plate gripper. We evaluate the accuracy of grasp detection and instance segmentation on challenging robotic picking datasets, namely Siléane and OCID_grasp, and show the benefit of joint grasp detection and segmentation on a real-world robotic picking task.

Item URL in elib:https://elib.dlr.de/146050/
Document Type:Conference or Workshop Item (Speech)
Title:Depth-aware object segmentation and grasp detection for robotic picking tasks
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Ainetter, Stefanicg.tugraz.atUNSPECIFIED
Böhm, ChristophInstitute of Smart System Technologies, Uni KlagenfurtUNSPECIFIED
Dhakate, Rohit Sudhakarrohit.dhakate (at) tu-dortmund.deUNSPECIFIED
Weiss, StephanInstitute of Smart System Technologies, Uni KlagenfurtUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.deUNSPECIFIED
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 1-13
Keywords:novel deep neural network architecture, joint classagnostic object segmentation
Event Title:32th British Machine Vision Conference (BMVC)
Event Location:UK, Online
Event Type:international Conference
Event Dates:22.-25. Nov. 2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Road Transport
DLR - Research area:Transport
DLR - Program:V ST Straßenverkehr
DLR - Research theme (Project):V - NGC KoFiF, R - Optical remote sensing
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Knickl, Sabine
Deposited On:25 Nov 2021 10:59
Last Modified:25 Nov 2021 10:59

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.