Paper
12 October 2022 Super-resolution for semantic segmentation
Xuan Zhang, Guoping Xu, Wentao Liao, Xinglong Wu
Author Affiliations +
Proceedings Volume 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022); 123421G (2022) https://doi.org/10.1117/12.2643026
Event: Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 2022, Wuhan, China
Abstract
Image segmentation is a classical problem in the field of computer vision. With the extensive development of deep learning, it has achieved much progress in semantic segmentation. However, the mainstream networks used in deep learning such as Fast-SCNN, U-Net, which still face challenges in image segmentation. A common problem is that linear interpolation is used in the up-sampling stage of these networks to obtain high-resolution images. Due to the lack of sufficient feature information, the contours of the objects in the image are blurred and grided. For this reason, we propose a new super-resolution (SR) method to replace the up-sampling with linear interpolation in the network model. Five representative networks integrated with our proposed SR module are used for verification on the CamVid data set. The experimental results show that our method has a 2%~4% improvement in mIoU (the mean value of Intersection over Union) and a 2%~3% improvement in pixel accuracy, which demonstrates its generalization and effectiveness of our method.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xuan Zhang, Guoping Xu, Wentao Liao, and Xinglong Wu "Super-resolution for semantic segmentation", Proc. SPIE 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 123421G (12 October 2022); https://doi.org/10.1117/12.2643026
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Super resolution

Image processing

Convolution

Data modeling

Buildings

Image resolution

Back to Top