Recent progress in computer vision has been driven by high-capacity deep convolutional neural network (CNN) models trained on generic large datasets. However, creating large datasets with dense pixel-level labels is extremely costly. In this paper, we focus on the problem of instance segmentation for robotic manipulation using rich image and depth features. To avoid intensive human labeling, we develop an automated rendering pipeline for rapidly generating labeled datasets. Given 3D object models as input, the rendering pipeline produces photorealistic images with pixel-accurate semantic label maps and depth maps. The synthetic dataset is then used to train an RGB-D segmentation model by extending the Mask R-CNN framework for depth input fusion. Our results open up new possibilities for advancing robotic perception using cheap and large-scale synthetic data.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Accurate Objectness Instance Segmentation from Photorealistic Rendering for Robotic Manipulation


    Weitere Titelangaben:

    Springer Proceedings in Advanced Robotics


    Beteiligte:
    Xiao, Jing (Herausgeber:in) / Kröger, Torsten (Herausgeber:in) / Khatib, Oussama (Herausgeber:in) / Li, Siyi (Autor:in) / Zhou, Jiaji (Autor:in) / Jia, Zhenzhong (Autor:in) / Yeung, Dit-Yan (Autor:in) / Mason, Matthew T. (Autor:in)

    Kongress:

    International Symposium on Experimental Robotics ; 2018 ; Buenos Aires, Argentina November 05, 2018 - November 08, 2018



    Erscheinungsdatum :

    23.01.2020


    Format / Umfang :

    11 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Visual object tracking based on objectness measure with multiple instance learning

    Hua, Weixin / Mu, Dejun / Guo, Dawei et al. | British Library Online Contents | 2017


    BlenderProc2: A Procedural Pipeline for Photorealistic Rendering

    Denninger, Maximilian / Winkelbauer, Dominik / Sundermeyer, Martin et al. | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2023

    Freier Zugriff


    Learning Stixel-based Instance Segmentation

    Santarossa, Monty / Schneider, Lukas / Zelenka, Claudius et al. | IEEE | 2021