Litcius/Paper detail

MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images

Rui Li, Chenxi Duan, Shunyi Zheng, Ce Zhang, Peter M. Atkinson

2021IEEE Geoscience and Remote Sensing Letters129 citationsDOIOpen Access PDF

Abstract

Semantic segmentation of remotely sensed images plays an important role in land resource management, yield estimation, and economic assessment. U-Net, a deep encoder&#x2013;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&#x002B;, among other benchmark approaches. Code is available at <uri>https://github.com/lironui/MACU-Net</uri>.

Topics & Concepts

Computer scienceSegmentationFeature (linguistics)Convolution (computer science)Benchmark (surveying)Artificial intelligenceBlock (permutation group theory)Feature extractionNet (polyhedron)Image segmentationScale (ratio)Pattern recognition (psychology)EncoderRemote sensingComputer visionArtificial neural networkGeographyCartographyMathematicsLinguisticsGeometryOperating systemPhilosophyAdvanced Neural Network ApplicationsRemote-Sensing Image ClassificationAdvanced Image and Video Retrieval Techniques