A review of deep learning methods for semantic segmentation of remote sensing imagery

By Xiaohui Yuan, Jianfang Shi, Lichuan Gu. Expert systems with applications, 2021

696 citations recorded by the source corpus.

Abstract Semantic segmentation of remote sensing imagery has been employed in many applications and is a key research topic for decades. With the success of deep learning methods in the field of computer vision, researchers have made a great effort to transfer their superior performance to the field of remote sensing image analysis. This paper starts with a summary of the fundamental deep neural network architectures and reviews the most recent developments of deep learning methods for semantic segmentation of remote sensing imagery including non-conventional data such as hyperspectral images and point clouds. In our review of the literature, we identified three major challenges faced by researchers and summarize the innovative development to address them. As tremendous efforts have been devoted to advancing pixel-level accuracy, the emerged deep learning methods demonstrated much-improved performance on several public data sets. As to handling the non-conventional, unstructured point cloud and rich spectral imagery, the performance of the state-of-the-art methods is, on average, inferior to that of the satellite imagery. Such a performance gap also exists in learning from small data sets. In particular, the limited non-conventional remote sensing data sets with labels is an obstacle to developing and evaluating new deep learning methods.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/fd23d4edf5fd7f9331f12e84355c5e537b5bc555

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Ocean Engineering

Citations in the corpus

Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks (2023, methodology): “With the emergence and rapid development of DL, there have been recently numerous semantic segmentation methods successfully developed for RS with a focus on a single studied scene [2].”
The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot (2023, background): “CNNs consist of multiple convolutional layers that apply filters to learn increasingly complex features, making them well-suited for segmenting objects in many remote sensing images [58, 4].”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “We refer the interested reader to the numerous surveys on machine learning and deep learning in remote sensing [8, 239, 240, 241, 242, 243, 244] for more details about common downstream tasks and available datasets.”
PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers (2022, background): “With the increasing demand of intelligence, semantic segmentation has become the basic perception component for applications such as autonomous driving [16], medical imaging diagnosis [2] and remote sensing imagery [54].”