Design of Real-time Semantic Segmentation Decoder for Automated Driving

Arindam Das, Saranya Kandan, Senthil Yogamani, Pavel Křížek

2019

Abstract

Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated driving which requires real-time performance. Recently, there has been a lot of research on designing efficient encoders that are mostly task agnostic. Unlike image classification and bounding box object detection tasks, decoders are computationally expensive as well for semantic segmentation task. In this work, we focus on efficient design of the segmentation decoder and assume that an efficient encoder is already designed to provide shared features for a multi-task learning system. We design a novel efficient non-bottleneck layer and a family of decoders which fit into a small run-time budget using VGG10 as efficient encoder. We demonstrate in our dataset that experimentation with various design choices led to an improvement of 10% from a baseline performance.

Paper Citation

in Harvard Style

Das A., Kandan S., Yogamani S. and Křížek P. (2019). Design of Real-time Semantic Segmentation Decoder for Automated Driving. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 393-400. DOI: 10.5220/0007366003930400

in Bibtex Style

@conference{visapp19,
author={Arindam Das and Saranya Kandan and Senthil Yogamani and Pavel Křížek},
title={Design of Real-time Semantic Segmentation Decoder for Automated Driving},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={393-400},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007366003930400},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Design of Real-time Semantic Segmentation Decoder for Automated Driving
SN - 978-989-758-354-4
AU - Das A.
AU - Kandan S.
AU - Yogamani S.
AU - Křížek P.
PY - 2019
SP - 393
EP - 400
DO - 10.5220/0007366003930400
PB - SciTePress