loading
Documents

Research.Publish.Connect.

Paper

Authors: Ganesh Sistu 1 ; Sumanth Chennupati 2 and Senthil Yogamani 1

Affiliations: 1 Valeo Vision Systems and Ireland ; 2 Valeo Troy and U.S.A.

ISBN: 978-989-758-354-4

ISSN: 2184-4321

Keyword(s): Semantic Segmentation, Visual Perception, Automated Driving.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Image and Video Analysis ; Segmentation and Grouping

Abstract: Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Multi-Stream FCN (MSFCN) networks. In case of RFCN, a recurrent network namely LSTM is inserted between the encoder and decoder. MSFCN combines the encoders of different frames into a fused encoder via 1x1 channel-wise convolution. We use a ResNet50 network as the baseline encoder and construct three networks namely MSFCN of order 2 & 3 and RFCN of order 2. MSFCN-3 produces the best results with an accuracy improvement of 9% and 15% for Highway and New York-like city scenarios in the SYNTHIACVPR’ 16 dataset using mean IoU metric. MSFCN-3 also produced 11% and 6% for SegTrack V2 and DAVIS datasets over the baseline FCN network. We also designed an efficient version of MSFCN -2 and RFCN-2 using weight sharing among the two encoders. The efficient MSFCN-2 provided an improvement of 11% and 5% for KITTI and SYNTHIA with negligible increase in computational complexity compared to the baseline version. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.233.111.242

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Sistu, G.; Chennupati, S. and Yogamani, S. (2019). Multi-stream CNN based Video Semantic Segmentation for Automated Driving.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP, ISBN 978-989-758-354-4, ISSN 2184-4321, pages 173-180. DOI: 10.5220/0007248401730180

@conference{visapp19,
author={Ganesh Sistu. and Chennupati, S. and Senthil Yogamani.},
title={Multi-stream CNN based Video Semantic Segmentation for Automated Driving},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP,},
year={2019},
pages={173-180},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007248401730180},
isbn={978-989-758-354-4},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP,
TI - Multi-stream CNN based Video Semantic Segmentation for Automated Driving
SN - 978-989-758-354-4
AU - Sistu, G.
AU - Chennupati, S.
AU - Yogamani, S.
PY - 2019
SP - 173
EP - 180
DO - 10.5220/0007248401730180

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.