More Web Proxy on the site http://driver.im/

research-article

Fully Residual Convolutional Neural Networks for Aerial Image Segmentation

Authors:

Dinh Viet Sang,

Nguyen Duc MinhAuthors Info & Claims

SoICT '18: Proceedings of the 9th International Symposium on Information and Communication Technology

Pages 289 - 296

https://doi.org/10.1145/3287921.3287970

Published: 06 December 2018 Publication History

Abstract

Semantic segmentation from aerial imagery is one of the most essential tasks in the field of remote sensing with various potential applications ranging from map creation to intelligence service. One of the most challenging factors of these tasks is the very heterogeneous appearance of artificial objects like buildings, cars and natural entities such as trees, low vegetation in very high-resolution digital images. In this paper, we propose an efficient deep learning approach to aerial image segmentation. Our approach utilizes the architecture of fully convolutional network (FCN) based on the backbone ResNet101 with additional upsampling skip connections. Besides typical color channels, we also use DSM and normalized DSM (nDSM) as the input data of our models. We achieve overall accuracy of 91%, which is in top 4 among 140 submissions from all over the world on the well-known Vaihingen dataset from ISPRS 2D Semantic Labeling Contest. Especially, our approach yields better results then all state-of-the-art methods in segmentation of car objects.

References

[1]

M. Gerke. Use of the stair vision library within the isprs 2d semantic labeling benchmark (vaihingen). 2014.

[2]

K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770--778, 2016.

[3]

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger. Densely connected convolutional networks.

[4]

G. Huang, Z. Liu, K. Q. Weinberger, and L. van der Maaten. Densely connected convolutional networks. arXiv preprint arXiv:1608.06993, 2016.

[5]

ISPRS Working group III/4. Isprs 2d semantic labeling contest. URL: http://www2.isprs.org/commissions/comm3/wg4/results.html. Accessed: 2018-09-01.

[6]

D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint ar Xiv:1412.6980, 2014.

[7]

A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097--1105, 2012.

Digital Library

[8]

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.

[9]

G. Lin, C. Shen, A. van den Hengel, and I. Reid. Efficient piecewise training of deep structured models for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3194--3203, 2016.

[10]

J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431--3440, 2015.

[11]

I. Markus Gerke. Use of the stair vision library within the isprs 2d semantic labeling benchmark (vaihingen).

[12]

T. T. Nguyen, S. V. Dinh, N. T. Quang, and H. T. T. Binh. Semantic segmentation of objects from airborne imagery. In Defence Technology-Japan (ACDT), 2017 Fourth Asian Conference on, pages 1--6. IEEE, 2017.

[13]

S. Paisitkriangkrai, J. Sherrah, P. Janney, V.-D. Hengel, et al. Effective semantic pixel labelling with convolutional networks and conditional random fields. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 36--43, 2015.

[14]

N. T. Quang, N. T. Thuy, D. V. Sang, and H. T. T. Binh. An efficient framework for pixel-wise building segmentation from aerial images. In Proceedings of the sixth international symposium on information and communication technology, pages 282--287. ACM, 2015.

Digital Library

[15]

O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234--241. Springer, 2015.

[16]

J. Sherrah. Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery. arXiv preprint arXiv:1606.02585, 2016.

[17]

K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint ar Xiv:1409.1556, 2014.

[18]

T. Speldekamp, C. Fries, C. Gevaert, and M. Gerke. Automatic semantic labelling of urban areas using a rule-based approach and realized with mevislab. 2015.

[19]

W. Sun and R. Wang. Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with dsm. IEEE Geoscience and Remote Sensing Letters, 15(3):474--478, 2018.

[20]

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1--9, 2015.

[21]

S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. arXiv preprint arXiv:1611.05431, 2016.

[22]

J. Yao and Z. M. Zhang. Semi-supervised learning based object detection in aerial imagery. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1011--1016, Washington, DC, USA, 2005. IEEE Computer Society.

Digital Library

[23]

S. Zagoruyko and N. Komodakis. Wide residual networks. arXiv preprint ar Xiv:1605.07146, 2016.

[24]

P. Zhong and R. Wang. Object detection based on combination of conditional random field and markov random field. In Proceedings of the 18th International Conference on Pattern Recognition, pages 160--163, 2006.

Digital Library

Cited By

Meng YYuan ZYang JLiu PYan JZhu HMa ZJiang ZZhang ZMi X(2024)Cross-Domain Land Cover Classification of Remote Sensing Images Based on Full-Level Domain AdaptationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing10.1109/JSTARS.2024.340780817(11434-11450)Online publication date: 2024
https://doi.org/10.1109/JSTARS.2024.3407808
Vostikolaei FJabari S(2024)Multimodal Building Footprint Extraction from Orthophotoa and Lidar Point Clouds Using Deep Learning FrameworkIGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium10.1109/IGARSS53475.2024.10641225(8214-8217)Online publication date: 7-Jul-2024
https://doi.org/10.1109/IGARSS53475.2024.10641225
Li ZChen XJiang JHan ZLi ZFang THuo HLi QLiu M(2022)Cascaded Multiscale Structure With Self-Smoothing Atrous Convolution for Semantic SegmentationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2021.308890260(1-13)Online publication date: 2022
https://doi.org/10.1109/TGRS.2021.3088902
Show More Cited By

Index Terms

Fully Residual Convolutional Neural Networks for Aerial Image Segmentation
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
      1. Neural networks

Recommendations

Brain Lacunae Segmentation from Fair Sequence Based On Fully Convolutional Neural Network
ACAI '18: Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence

Neuroimaging in the context of brain disease is becoming more and more important. Brain detection and segmentation are two fundamental steps in neuroimage analysis. Because the cost of manual segmentation of the brain is too much, more and more ...
Lung Segmentation Using a Fully Convolutional Neural Network with Weekly Supervision
ICBSP '18: Proceedings of the 2018 3rd International Conference on Biomedical Imaging, Signal Processing

Most supervised methods for lung CT image segmentation require all training examples to be labeled with segmentation masks. This requirement makes it expensive to annotate varies categories of lung diseases. The goal of this paper is to propose a new ...
Comparison of convolutional neural network training strategies for cone-beam CT image segmentation
Highlights
- Comprehensive comparison between convolutional neural network training strategies.
Abstract Background and objective
Over the past decade, convolutional neural networks (CNNs) have revolutionized the field of medical image segmentation. Prompted by the developments in computational resources and the availability of ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

SoICT '18: Proceedings of the 9th International Symposium on Information and Communication Technology

December 2018

496 pages

ISBN:9781450365390

DOI:10.1145/3287921

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

SOICT: School of Information and Communication Technology - HUST
NAFOSTED: The National Foundation for Science and Technology Development

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 06 December 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

SoICT 2018

SoICT 2018: The Ninth International Symposium on Information and Communication Technology

December 6 - 7, 2018

Danang City, Viet Nam

Acceptance Rates

Overall Acceptance Rate 147 of 318 submissions, 46%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
175
Total Downloads

Downloads (Last 12 months)15
Downloads (Last 6 weeks)1

Reflects downloads up to 31 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Meng YYuan ZYang JLiu PYan JZhu HMa ZJiang ZZhang ZMi X(2024)Cross-Domain Land Cover Classification of Remote Sensing Images Based on Full-Level Domain AdaptationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing10.1109/JSTARS.2024.340780817(11434-11450)Online publication date: 2024
https://doi.org/10.1109/JSTARS.2024.3407808
Vostikolaei FJabari S(2024)Multimodal Building Footprint Extraction from Orthophotoa and Lidar Point Clouds Using Deep Learning FrameworkIGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium10.1109/IGARSS53475.2024.10641225(8214-8217)Online publication date: 7-Jul-2024
https://doi.org/10.1109/IGARSS53475.2024.10641225
Li ZChen XJiang JHan ZLi ZFang THuo HLi QLiu M(2022)Cascaded Multiscale Structure With Self-Smoothing Atrous Convolution for Semantic SegmentationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2021.308890260(1-13)Online publication date: 2022
https://doi.org/10.1109/TGRS.2021.3088902
Wang ZFan CXian M(2021)Application and Evaluation of a Deep Learning Architecture to Urban Tree Canopy MappingRemote Sensing10.3390/rs1309174913:9(1749)Online publication date: 30-Apr-2021
https://doi.org/10.3390/rs13091749
Chen XLi ZJiang JHan ZDeng SLi ZFang THuo HLi QLiu M(2021)Adaptive Effective Receptive Field Convolution for Semantic Segmentation of VHR Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2020.300914359:4(3532-3546)Online publication date: Apr-2021
https://doi.org/10.1109/TGRS.2020.3009143
Zhang RDu LXiao QLiu J(2020)Comparison of Backbones for Semantic Segmentation NetworkJournal of Physics: Conference Series10.1088/1742-6596/1544/1/0121961544:1(012196)Online publication date: 1-May-2020
https://doi.org/10.1088/1742-6596/1544/1/012196

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents