Skip to Main content Skip to Navigation
Conference papers

Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network

Matthieu Grard 1, 2 Romain Brégier 1, 3 Florian Sella 1 Emmanuel Dellandréa 2 Liming Chen 2 
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 IMAGINE - Intuitive Modeling and Animation for Interactive Graphics & Narrative Environments
Inria Grenoble - Rhône-Alpes, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann
Abstract : With more and more household objects built on planned obsolescence and consumed by a fast-growing population, hazardous waste recycling has become a critical challenge. Given the large variability of household waste, current recycling platforms mostly rely on human operators to analyze the scene, typically composed of many object instances piled up in bulk. Helping them by robotizing the unitary extraction is a key challenge to speed up this tedious process. Whereas supervised deep learning has proven very efficient for such object-level scene understanding, e.g., generic object detection and segmentation in everyday scenes, it however requires large sets of per-pixel labeled images, that are hardly available for numerous application contexts, including industrial robotics. We thus propose a step towards a practical interactive application for generating an object-oriented robotic grasp, requiring as inputs only one depth map of the scene and one user click on the next object to extract. More precisely, we address in this paper the middle issue of object seg-mentation in top views of piles of bulk objects given a pixel location, namely seed, provided interactively by a human operator. We propose a twofold framework for generating edge-driven instance segments. First, we repurpose a state-of-the-art fully convolutional object contour detector for seed-based instance segmentation by introducing the notion of edge-mask duality with a novel patch-free and contour-oriented loss function. Second, we train one model using only synthetic scenes, instead of manually labeled training data. Our experimental results show that considering edge-mask duality for training an encoder-decoder network, as we suggest, outperforms a state-of-the-art patch-based network in the present application context.
Complete list of metadata
Contributor : Matthieu Grard Connect in order to contact the contributor
Submitted on : Monday, September 24, 2018 - 10:57:32 AM
Last modification on : Friday, February 4, 2022 - 3:29:41 AM
Long-term archiving on: : Tuesday, December 25, 2018 - 1:03:05 PM


Files produced by the author(s)



Matthieu Grard, Romain Brégier, Florian Sella, Emmanuel Dellandréa, Liming Chen. Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network. HFR - 10th International Workshop on Human-Friendy Robotics, Nov 2017, Napoli, Italy. pp.207-221, ⟨10.1007/978-3-319-89327-3_16⟩. ⟨hal-01674511v2⟩



Record views


Files downloads