Object Segmentation Using ESRGAN and Semantic Soft Segmentation (ESRGAN과 Semantic Soft Segmentation을 이용한 객체 분할)

DongSikYoon (윤동식); Noyoon Kwak (곽노윤)

doi:10.20465/KIOTS.2023.9.1.097

Object Segmentation Using ESRGAN and Semantic Soft Segmentation

Journal of Internet of Things and Convergence
Abbr : JKIOTS
2023, 9(1), pp.97-104
DOI : 10.20465/KIOTS.2023.9.1.097
Publisher : The Korea Internet of Things Society
Research Area : Engineering > Computer Science > Internet Information Processing
Received : December 4, 2022
Accepted : January 8, 2023
Published : February 28, 2023

DongSikYoon ¹, Noyoon Kwak ²

¹고려대학교
²백석대학교

Accredited

ABSTRACT

This paper is related to object segmentation using ESRGAN(Enhanced Super Resolution GAN) and SSS(Semantic Soft Segmentation). The segmentation performance of the object segmentation method using Mask R-CNN and SSS proposed by the research team in this paper is generally good, but the segmentation performance is poor when the size of the objects is relatively small. This paper is to solve these problems. The proposed method aims to improve segmentation performance of small objects by performing super-resolution through ESRGAN and then performing SSS when the size of an object detected through Mask R-CNN is below a certain threshold. According to the proposed method, it was confirmed that the segmentation characteristics of small-sized objects can be improved more effectively than the previous method.

KEYWORDS

ESRGAN, Mask R-CNN, Semantic Soft Segmentation, Super-resolution, Image Segmentation

Citation status

* References for papers published after 2023 are currently being built.

[confproc] K. He / 2017 / Mask R-CNN / Proceedings of IEEE International Conference on Computer Vision : 2980~2988

[journal] Y. Aksoy / 2018 / Semantic Soft Segmentation / ACM Trans. Graph

[confproc] D. Yoon / 2020 / Object Segmentation Using MaskR-CNN and Semantic Soft Segmentation / Proceedings of 2020 Winter Conference of Korean Society of Communications and Communications : 872~873

[confproc] K. He / 2016 / Deep Residual Learning for Image Recognition / Proceedings of Conference on Computer Vision and Pattern Recognition : 770~778

[journal] A. Levin / 2008 / Spectral Matting / IEEE Trans. Pattern Anal. Mach. Intell 30(10) : 1699~1712

[confproc] X. Wang / 2018 / ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks / Proceedings of European Conference on Computer Vision

[other] Z. Li / 2017 / Light-head R-CNN : In Defense of Two-stage Object Detector / arXiv preprint arXiv : 1711. 07264

[confproc] Z. Cai / 2018 / Cascade R-CNN : Delving into High Quality Object Detection / Proceedings of Conference on Computer Vision and Pattern Recognition

[other] P. Purkait / 2017 / SPP-Net : Deep Absolute Pose Regression with Synthetic Views / arXiv preprint arXiv : 1712. 03452

[other] Z. Li / 2017 / FSSD : Feature Fusion Single Shot Multibox Detector / arXiv preprint arXiv : 1712. 00960

[confproc] H. Law / 2018 / CornerNet : Detecting Objects as Paired Keypoints / Proceedings of European Conference on Computer Vision

[confproc] J. Redmon / 2016 / You Only Look Once : Unified, Real-time Object Detection / Proceedings of Conference on Computer Vision and Pattern Recognition

[confproc] S. Ren / 2015 / Faster R-CNN : Towards Real-time Object Detection with Region Proposal Networks / Proceedings of Conference on Neural Information Processing Systems

[confproc] J. Long / 2015 / Fully Convolutional Networks for Semantic Segmentation / Proceedings of Conference on Computer Vision and Pattern Recognition

[other] A. Paszke / 2016 / ENet : A Deep Neural Network Architecture for Real-time Semantic Segmentation / arXiv preprint arXiv : 1606. 02147

[confproc] A. Chaurasia / 2017 / LinkNet : Exploiting Encoder Representations for Efficient Semantic Segmentation / 2017 IEEE Visual Communications and Image Processing

[journal] E. Romera / 2017 / ERFNet : Efficient Residual Factorized Convnet for Real-time Semantic Segmentation / IEEE Transactions on Intelligent Transportation Systems 19 : 263~272

[journal] L. -C. Chen / 2017 / DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs / IEEE Trans. Pattern Anal. Mach. Intell 40

[journal] R. Achanta / 2012 / SLIC Superpixels Compared to State-of-the-Art Superpixel Methods / IEEE Trans. Pattern Anal. Mach. Intell 34(11) : 2274~2281

[confproc] H. Zhao / 2017 / Pyramid Scene Parsing Network / Proceedings of Conference on Computer Vision and Pattern Recognition

[confproc] C. Ledig / 2017 / Photo-realistic Single Image Super-resolution Using a Generative Adversarial Network / Proceedings of Conference on Computer Vision and Pattern Recognition : 4681~4690

[confproc] B. Lim / 2017 / Enhanced Deep Residual Networks for Single Image Super-resolution / Proceedings of Conference on Computer Vision and Pattern Recognition

[other] A. Jolicoeur-Martineau / 2018 / The Relativistic Discriminator : a Key Element Missing from Standard GAN / arXiv preprint arXiv : 1807. 00734

This paper was written with support from the National Research Foundation of Korea.

KJCKorea
Journal Central

Journal of Internet of Things and Convergence 2023 KCI Impact Factor : 0.89

Object Segmentation Using ESRGAN and Semantic Soft Segmentation

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of Internet of Things and Convergence 2023 KCI Impact Factor : 0.89

Object Segmentation Using ESRGAN and Semantic Soft Segmentation

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (23) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.