A Prior-Guided Dual Branch Multi-Feature Fusion Network for Building Segmentation in Remote Sensing Images
-
Published:2024-07-02
Issue:7
Volume:14
Page:2006
-
ISSN:2075-5309
-
Container-title:Buildings
-
language:en
-
Short-container-title:Buildings
Author:
Wu Yingbin12ORCID, Zhao Peng1, Wang Fubo1, Zhou Mingquan13, Geng Shengling13, Zhang Dan13
Affiliation:
1. School of Computer Science, Qinghai Normal University, Xining 810016, China 2. School of Mathematics and Information Technology, Yuncheng University, Yuncheng 044000, China 3. State Key Laboratory of Tibetan Intelligent Information Processing and Application, Xining 810016, China
Abstract
The domain of remote sensing image processing has witnessed remarkable advancements in recent years, with deep convolutional neural networks (CNNs) establishing themselves as a prominent approach for building segmentation. Despite the progress, traditional CNNs, which rely on convolution and pooling for feature extraction during the encoding phase, often fail to precisely delineate global pixel interactions, potentially leading to the loss of vital semantic details. Moreover, conventional CNN-based segmentation models frequently neglect the nuanced semantic differences between shallow and deep features during the decoding phase, which can result in subpar feature integration through rudimentary addition or concatenation techniques. Additionally, the unique boundary characteristics of buildings in remote sensing images, which offer a rich vein of prior information, have not been fully harnessed by traditional CNNs. This paper introduces an innovative approach to building segmentation in remote sensing images through a prior-guided dual branch multi-feature fusion network (PDBMFN). The network is composed of a prior-guided branch network (PBN) in the encoding process, a parallel dilated convolution module (PDCM) designed to incorporate prior information, and a multi-feature aggregation module (MAM) in the decoding process. The PBN leverages prior region and edge information derived from superpixels and edge maps to enhance edge detection accuracy during the encoding phase. The PDCM integrates features from both branches and applies dilated convolution across various scales to expand the receptive field and capture a more comprehensive semantic context. During the decoding phase, the MAM utilizes deep semantic information to direct the fusion of features, thereby optimizing segmentation efficacy. Through a sequence of aggregations, the MAM gradually merges deep and shallow semantic information, culminating in a more enriched and holistic feature representation. Extensive experiments are conducted across diverse datasets, such as WHU, Inria Aerial, and Massachusetts, revealing that PDBMFN outperforms other sophisticated methods in terms of segmentation accuracy. In the key segmentation metrics, including mIoU, precision, recall, and F1 score, PDBMFN shows a marked superiority over contemporary techniques. The ablation studies further substantiate the performance improvements conferred by the PBN’s prior information guidance and the efficacy of the PDCM and MAM modules.
Funder
National Natural Science Foundation of China Qinghai Provincial Natural Science Foundation of China Natural Science Youth Foundation of Qinghai Province 2022 Annual Technological Innovation Project of Higher Education Institutions in Shanxi Province
Reference49 articles.
1. Zhao, W., Persello, C., and Stein, A. (October, January 26). Building Instance Segmentation and Boundary Regularization from High-Resolution Remote Sensing Images. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium(IGARSS), Waikoloa Village, HI, USA. 2. Aslam, R.W., Shu, H., Naz, I., Quddoos, A., Yaseen, A., Gulshad, K., and Alarifi, S.S. (2024). Machine Learning-Based Wetland Vulnerability Assessment in the Sindh Province Ramsar Site Using Remote Sensing Data. Remote Sens., 16. 3. Yu, A., Quan, Y., Yu, R., Guo, W., Wang, X., Hong, D., Zhang, H., Chen, J., Hu, Q., and He, P. (2023). Deep learning methods for semantic segmentation in remote sensing with small data: A survey. Remote Sens., 15. 4. Building Outline Extraction Using a Heuristic Approach Based on Generalization of Line Segments;Partovi;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2017 5. Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images;Ghaffarian;Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.,2014
|
|