.png){kind=icon}
返回
Semantic Segmentation for Remote Sensing Image Using the Multigranularity Object-Based Markov Random Field With Blinking Coefficient
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2023.3301494.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semantic segmentation is one of the most important tasks in remote sensing. In the semantic segmentation of remote sensing images, some regions are repeatedly transformed between multiclasses, which affects the convergence speed and segmentation accuracy. This is because the increased spatial resolution makes the spectral distribution of geographic targets differ from the overall category distribution. The Markov random field (MRF) model is widely used for semantic segmentation of remote sensing images because of its outstanding spatial description ability. Some scholars have made improvements on MRF models to extract more information or enhance semantic inference. However, these improvements fail to capture the correlation between the multigranularity layers and the historical information. In this article, we propose a new MRF-based model that adopts multigranularity layers to realize the multigranularity correlation representation of targets and the spatial-temporal inference of segmentation labels. First, the algorithm constructs a multigrained layer structure based on remote sensing images to enhance feature extraction for targets of different sizes in images. Second, for the multilayer feature field, a cross-layer Gauss-Markov model is constructed based on intra-inter-layer feature correlation constraints. Then, for the multigranularity layer label field, a self-renewing pairwise spatial-temporal potential function with blinking coefficients is constructed based on the newly defined cross-layer augmented neighborhood system, which can accelerate the convergence of segmentation by using the history information and spatial neighborhood information. The proposed method is tested on texture images, SPOT-5, and Gaofen-2 images. Experiments show that the proposed method has a better performance compared to other state-of-the-art MRF-based methods.
Keyword:
Markov random field (MRF)
multigranularity
remote sensing image
semantic segmentation
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
Nonsubsampled contourlet transform-based conditional random field for SAR images segmentation基于非下采样contourlet变换的条件随机场SAR图像分割.png)
SIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
分享收藏Semantic Segmentation for Remote Sensing Images Using Pyramid Object-Based Markov Random Field With Dual-Track Information Transmission基于金字塔对象的双轨信息传递马尔可夫随机场的遥感图像语义分割
PREAI
分享收藏Object Detection in High Resolution Remote Sensing Imagery Based on Convolutional Neural Networks With Suitable Object Scale Features基于合适目标尺度特征的卷积神经网络高分辨率遥感影像目标检测
PREAI
分享收藏Enhancing Multiscale Representations With Transformer for Remote Sensing Image Semantic Segmentation利用Transformer增强多尺度表示的遥感图像语义分割
PREAI
分享收藏分享收藏Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning基于深度学习的多光谱遥感图像语义分割算法
OAAI
OAAI分享收藏
查看更多内容