About: ModuleNet: A Convolutional Neural Network for Stereo Vision

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: ModuleNet: A Convolutional Neural Network for Stereo Vision Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	ModuleNet: A Convolutional Neural Network for Stereo Vision
Creator	Cuevas-Tello, J Renteria-Vidales, O Reyes-Figueroa, A Rivera, M
Source	PMC
abstract	Convolutional Neural Networks (CNN) has gained much attention for the solution of numerous vision problems including disparities calculation in stereo vision systems. In this paper, we present a CNN based solution for disparities estimation that builds upon a basic module (BM) with limited range of disparities that can be extended using various BM in parallel. Our BM can be understood as a segmentation by disparity and produces an output channel with the memberships for each disparity candidate, additionally the BM computes a channel with the out–of–range disparity regions. This extra channel allows us to parallelize several BM and dealing with their respective responsibilities. We train our model with the MPI Sintel dataset. The results show that ModuleNet, our modular CNN model, outperforms the baseline algorithm Efficient Large-scale Stereo Matching (ELAS) and FlowNetC achieving about a 80% of improvement.
has issue date	2020-04-29(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49076-8_21
has license	no-cc
sha1sum (hex)	542fd31741c98acb3ebf1b02739b58aa75db209e
schema:url	https://doi.org/10.1007/978-3-030-49076-8_21
resource representing a document's title	ModuleNet: A Convolutional Neural Network for Stereo Vision
has PubMed Central identifier	PMC7297576
schema:publication	Pattern Recognition
resource representing a document's body	covid:542fd31741c98acb3ebf1b02739b58aa75db209e#body_text
is schema:about of	named entity 'limited' named entity 'disparity' named entity 'extra channel' named entity 'model' named entity 'basic' named entity 'REGIONS' named entity 'CHANNEL' named entity 'EFFICIENT' named entity 'LARGE' named entity 'PARALLEL' named entity 'CNN' named entity 'CALCULATION' named entity 'ALLOWS' named entity 'ATTENTION' named entity 'NUMEROUS' named entity 'The' named entity 'paper' named entity 'CNN' named entity 'disparities' named entity 'solution' named entity 'parallelize' named entity 'extra channel' named entity 'vision problems' named entity 'MAE' named entity 'probability' named entity 'pixels' named entity 'training set' named entity 'disparity maps' named entity 'U-Net' named entity 'Intel' named entity 'pixel' named entity 'cross correlation' named entity 'U-Net' named entity 'Hamming distance' named entity 'integer' named entity 'tensor' named entity 'ELAS' named entity 'parallelize' named entity 'regularizer' named entity 'census transform' named entity 'ELAS' named entity 'U-Net' named entity 'inference' named entity 'data set' named entity 'probability' named entity 'Movidius' named entity 'ground truth' named entity 'pixels' named entity 'FlowNet' named entity 'CNN' named entity 'ELAS' named entity '1, 2' named entity 'FlowNet' named entity 'CNN' named entity 'normalized cross-correlation' named entity 'probability' named entity 'short film' named entity 'dynamic range' named entity 'optimization algorithm' named entity 'Sum of Absolute Differences' named entity 'tensor' named entity 'U-Net' named entity 'FlowNet' named entity 'ground truth' named entity 'FlowNet' named entity 'stereo pairs' named entity 'NVIDIA' named entity 'tensor' named entity 'CNN' named entity 'pixels' named entity 'FlowNet' named entity 'FlowNet' named entity 'FlowNet' named entity 'pixels' named entity 'pixel' named entity 'training set' named entity 'ELAS' named entity 'Convolutional Network' named entity 'GPU' named entity 'U-Net'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software