Street-view Change Detection via Siamese Encoder-decoder Structured Convolutional Neural Networks

Xinwei Zhao, Haichang Li, Rui Wang, Changwen Zheng, Song Shi

2019

Abstract

In this paper, we propose a siamese encoder-decoder structured network for street scene change detection. The encoder-decoder structures have been successfully applied for semantic segmentation. Our work is inspired by the similarity between change detection and semantic segmentation, and the success of siamese network in comparing image patches. Our method is able to precisely detect changes of street scene at the presence of irrelevant visual differences caused by different shooting conditions and weather. Moreover, the encoder and decoder parts are decoupled. Various combinations of different encoders and decoders are evaluated in this paper. Experiments on two street scene datasets, TSUNAMI and GSV, demonstrate that our method outperforms previous ones by a large margin.

Paper Citation

in Harvard Style

Zhao X., Li H., Wang R., Zheng C. and Shi S. (2019). Street-view Change Detection via Siamese Encoder-decoder Structured Convolutional Neural Networks. 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 525-532. DOI: 10.5220/0007407905250532

in Bibtex Style

@conference{visapp19,
author={Xinwei Zhao and Haichang Li and Rui Wang and Changwen Zheng and Song Shi},
title={Street-view Change Detection via Siamese Encoder-decoder Structured Convolutional Neural Networks},
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={525-532},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007407905250532},
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 - Street-view Change Detection via Siamese Encoder-decoder Structured Convolutional Neural Networks
SN - 978-989-758-354-4
AU - Zhao X.
AU - Li H.
AU - Wang R.
AU - Zheng C.
AU - Shi S.
PY - 2019
SP - 525
EP - 532
DO - 10.5220/0007407905250532
PB - SciTePress