Journal
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
Volume 19, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2021.3052886
Keywords
Convolution; Semantics; Remote sensing; Image segmentation; Kernel; Feature extraction; Decoding; Asymmetric convolution block (ACB); fine-resolution remotely sensed images; semantic segmentation
Categories
Funding
- National Natural Science Foundation of China [41671452]
Ask authors/readers for more resources
This paper proposes a multiscale skip connected and asymmetric-convolution-based U-Net (MACU-Net) architecture for semantic segmentation of remote sensed images, with the goal of enhancing feature representation and extraction. Experimental results demonstrate that MACU-Net outperforms other benchmark approaches.
Semantic segmentation of remotely sensed images plays an important role in land resource management, yield estimation, and economic assessment. U-Net, a deep encoder-decoder architecture, has been used frequently for image segmentation with high accuracy. In this letter, we incorporate multiscale features generated by different layers of U-Net and design a multiscale skip connected and asymmetric-convolution-based U-Net (MACU-Net), for segmentation using fine-resolution remotely sensed images. Our design has the following advantages: (1) the multiscale skip connections combine and realign semantic features contained in both low-level and high-level feature maps; (2) the asymmetric convolution block strengthens the feature representation and feature extraction capability of a standard convolution layer. Experiments conducted on two remotely sensed data sets captured by different satellite sensors demonstrate that the proposed MACU-Net transcends the U-Net, U-Netpyramid pooling layers (PPL), U-Net 3+, among other benchmark approaches. Code is available at https://github.com/lironui/MACU-Net.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available