Road Extraction from Remote Sensing Image by Integrating DCNN with Short Range Conditional Random Field

被引：0
|
作者：
He X. [1 ,3 ]
Chen M. [2 ]
Li P. [2 ]
Tian Z. [1 ,3 ]
Zhou G. [1 ,3 ]
机构：
[1] School of Earth Science and Technology, Zhengzhou University, Zhengzhou
[2] School of Information Engineering, Zhengzhou University, Zhengzhou
[3] Joint Laboratory of Eco-Meteorology, Chinese Academy of Meteorological Sciences, Zhengzhou University, Zhengzhou
来源：
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | 2024年 / 49卷 / 03期
关键词：
conditional random field; deep learning; remote sensing image; road extraction; semantic segmentation;
D O I：
10.13203/j.whugis20210464
中图分类号：
学科分类号：
摘要：
Objective: Deep convolutional neural network (DCNN) is widely used in automatic road extraction from high-resolution remote sensing images (HRSIs). However, the existing methods make it difficult to model the context relationship of pixels in the predicted results. To solve this problem, some studies have used fully connected conditional random field (FullCRF) to perform secondary optimization of semantic segmentation results combined with context information, but the discontinuity problem of road structure cannot be effectively improved. Methods: In order to improve the integrity of road structure, this paper proposes a short range conditional random filed (SRCRF) model combined with DCNN. SRCRF mainly includes a unary potential function based on road pre-segmentation, a binary potential function based on spectral spatial features, and a K-neighborhood mean field inference algorithm. First, the prior knowledge of road pre-segmentation results is obtained by using the powerful feature extraction capability of DCNN as the unary potential function of SRCRF. Then, the dependence of the binary potential function defined by the linear combination of Gaussian kernel functions on the surrounding nodes is modeled. The binary potential function enables the classification results to have local consistency, that is, adjacent pixels with similar spectral features have the same label. Finally, the K-neighborhood mean field inference algorithm based on the mean-field approximation inference algorithm optimizes the inference range to make full use of the spatial context information and spectral feature context information of the road, and then calculates the optimal label corresponding to each pixel based on the space and spectral feature to optimize the road accurately. The convolution method is adopted to control the inference range of SRCRF within the radius of K in order to improve the proportion of feature vectors. Results: The experimental results show that SRCRF not only alleviates the transition smoothness of FullCRF, but also alleviates the structural discontinuity and incompleteness in the road acquisition results of HRSIs. In Zimbawe-Roads dataset and Cheng-Roads dataset, F1-scores of SRCRF are increased by about 4.01% and 3.73% respectively compared with DCNN, and about 3.25% and 2.28% respectively compared with FullCRF. Conclusions: The proposed SRCRF combines the advantages of DCNN, optimizes the fully connected structure of traditional conditional random fields into the K-neighborhood structure, reduces the inference scope, and improves the proportion of feature vectors. Compared with FullCRF, SRCRF can make better use of image color features and spatial features to accurately optimize the road extraction results of deep learning output. The performance of SRCRF is improved compared with DCNN and FullCRF, and the time is shortened by one order of magnitude compared with FullCRF. In the future, we will further investigate the potential for learning Gaussian features and investigate more complex architecture of conditional random field to better capture global context information. Additionally, we are particularly interested in exploring the application potential of SRCRF in other fields, such as building extraction, vehicle extraction, lake extraction, etc. © 2024 Editorial Department of Geomatics and Information Science of Wuhan University. All rights reserved.
引用
收藏
页码：333 / 342
页数：9
相关论文
共 27 条
  • [1] Abdollahi A, Pradhan B, Shukla N, Et al., Deep Learning Approaches Applied to Remote Sensing Datasets for Road Extraction:A State-of-the-Art Review[J], Remote Sensing, 12, 9, (2020)
  • [2] Soulard C E, Acevedo W, Stehman S V., Removing Rural Roads from the National Land Cover Database to Create Improved Urban Maps for the United States, 1992 to 2011, Photogrammetric Engineering & Remote Sensing, 84, 2, pp. 101-109, (2018)
  • [3] Li D M, Deng L B, Cai Z M, Et al., Notice of Retraction:Intelligent Transportation System in Macao Based on Deep Self-Coding Learning[J], IEEE Transactions on Industrial Informatics, 14, 7, pp. 3253-3260, (2018)
  • [4] Vargas-Munoz J E, Lobry S, Falcao A X, Et al., Correcting Rural Building Annotations in OpenStreetMap Using Convolutional Neural Networks [J], ISPRS Journal of Photogrammetry and Remote Sensing, 147, pp. 283-293, (2019)
  • [5] Xu Y Y, Xie Z, Wu L, Et al., Multilane Roads Extracted from the OpenStreetMap Urban Road Network Using Random Forests[J], Transactions in GIS, 23, 2, pp. 224-240, (2019)
  • [6] Bruzzone L, Persello C., A Novel Context-Sensitive Semisupervised SVM Classifier Robust to Mislabeled Training Samples, IEEE Transactions on Geoscience and Remote Sensing, 47, 7, pp. 2142-2154, (2009)
  • [7] Shelhamer E, Long J, Darrell T., Fully Convolutional Networks for Semantic Segmentation[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 4, pp. 640-651, (2017)
  • [8] Badrinarayanan V, Kendall A, Cipolla R., SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 12, pp. 2481-2495, (2017)
  • [9] Zhang Xinchang, Huang Jianfeng, Ning Ting, Progress and Prospect of Cultivated Land Extraction from High-Resolution Remote Sensing Images, Geomatics and Information Science of Wuhan University, 48, 10, pp. 1582-1590, (2023)
  • [10] Du Peijun, Zhang Peng, Guo Shanchuan, Et al., A Semantic Segmentation Model for Mapping Plastic Greenhouse Based on Spectral Index and High-Resolution Imagery, Geomatics and Information Science of Wuhan University, 48, 10, pp. 1670-1683, (2023)
123