Automatic Extraction of Built-Up Areas From Panchromatic and Multispectral Remote Sensing Images Using Double-Stream Deep Convolutional Neural Networks

Tan, Yihua; Xiong, Shengzhou; Li, Yansheng

doi:10.1109/jstars.2018.2871046

Cited by 45 publications

(25 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the number of pooling layers increases, the spatial resolution of the image decreases. The shape characteristics of buildings also change with a change in the image resolution [54]. To adapt to the appearance of morphological building features at different resolutions, a group of adaptive dilated convolutions is constructed to better map these features.…”

Section: ) Residual Connected Unitmentioning

confidence: 99%

Refined Extraction Of Building Outlines From High-Resolution Remote Sensing Imagery Based on a Multifeature Convolutional Neural Network and Morphological Filtering

Xie

Zhu

Cao

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The automatic extraction of building outlines from high-resolution images is an important and challenging task. Convolutional neural networks have shown excellent results compared with traditional building extraction methods because of their ability to extract high-level abstract features from images. However, it is difficult to fully utilize the multiple features of current building extraction methods; consequently, the resulting building boundaries are irregular. To overcome these limitations, we propose a method for extracting buildings from high-resolution images using a multifeature convolutional neural network (MFCNN) and morphological filtering. Our method consists of two steps. First, the MFCNN, which consists of residual connected unit, dilated perception unit, and pyramid aggregation unit, is used to achieve pixel-level segmentation of the buildings. Second, morphological filtering is used to optimize the building boundaries, improve the boundary regularity, and obtain refined building boundaries. The Massachusetts and Inria datasets are selected for experimental analysis. Under the same experimental conditions, the extraction results achieved with the proposed MFCNN are compared with the results of other deep learning models that have been commonly used in recent years: FCN-8s, SegNet, and U-Net. The results on both datasets reveal that the proposed model improves the F1-score by 3.31%-5.99%, increases the overall accuracy (OA) by 1.85%-3.07%, and increases the intersection over union (IOU) by 3.47%-8.82%. These findings illustrate that the proposed method is effective at extracting buildings from complex scenes. Index Terms-Building outline extraction, high-resolution images, morphological filtering, multifeature convolutional neural network (MFCNN). I. INTRODUCTION A S A critical component of basic urban geographic information, buildings play an important role in population estimation, change monitoring, urban planning, and smart city construction [1]-[3]. Consequently, the automatic extraction of Manuscript

show abstract

Section: ) Residual Connected Unitmentioning

confidence: 99%

Refined Extraction Of Building Outlines From High-Resolution Remote Sensing Imagery Based on a Multifeature Convolutional Neural Network and Morphological Filtering

Xie

Zhu

Cao

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In our previous work [90], a double-stream convolutional neural network (DSCNN) model based on Inception V3 was proposed to extract the built-up area automatically. The network consists of two branches: the upper branches manipulate the panchromatic image providing primary information for object classification, and the lower branch attaches more importance to the multispectral image, providing auxiliary information for improvement in accuracy (with the overall accuracy reaching 98.39%).…”

Section: Taking the Scene As The Primary Unit To Interpret Objects Frmentioning

confidence: 99%

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Wang

2019

Applied Sciences

Self Cite

124

View full text Add to dashboard Cite

As a fundamental and important task in remote sensing, remote sensing image scene understanding (RSISU) has attracted tremendous research interest in recent years. RSISU includes the following sub-tasks: remote sensing image scene classification, remote sensing image scene retrieval, and scene-driven remote sensing image object detection. Although these sub-tasks have different goals, they share some communal hints. Hence, this paper tries to discuss them as a whole. Similar to other domains (e.g., speech recognition and natural image recognition), deep learning has also become the state-of-the-art technique in RSISU. To facilitate the sustainable progress of RSISU, this paper presents a comprehensive review of deep-learning-based RSISU methods, and points out some future research directions and potential applications of RSISU.

show abstract

“…Compared with the popular region proposal in computer vision fields, OBIA could handle various shapes and sizes of the real land covers. The multibranch parallel network models based on GoogLeNet [34] and skip-layer architectures based on ResNet [35] are investigated [52], [53].…”

Section: Introductionmentioning

confidence: 99%

Very High Resolution Remote Sensing Imagery Classification Using a Fusion of Random Forest and Deep Learning Technique—Subtropical Area for Example

Dong

Xing

Liu

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recently, convolutional neural networks (CNNs) showed excellent performance in many tasks, such as computer vision and remote sensing semantic segmentation. Especially, the ability to learn high-representation features of CNN draws much attention. And random forest (RF) algorithm, on the other hand, is widely applied for variables selection, classification, and regression. Based on the previous fusion models that fused CNN with the other models, such as conditional random fields (CRFs), support vector machine (SVM), and RF, this article tested a method based on the fusion of an RF classifier and the CNN for a very high resolution remote sensing (VHRRS) based forests mapping. The study area is located in the south of China and the main purpose was to precisely distinguish Lei bamboo forests from the other subtropical forests. The main novelties of this article are as follows. First, a test was conducted to confirm if a fusion of CNN and RF make an improvement in the VHRRS information extraction. Second, based on RF, variables with high importance were selected. Then, a test was again conducted to confirm if the learning from the selected variables will further give better results.

show abstract

Automatic Extraction of Built-Up Areas From Panchromatic and Multispectral Remote Sensing Images Using Double-Stream Deep Convolutional Neural Networks

Cited by 45 publications

References 38 publications

Refined Extraction Of Building Outlines From High-Resolution Remote Sensing Imagery Based on a Multifeature Convolutional Neural Network and Morphological Filtering

Refined Extraction Of Building Outlines From High-Resolution Remote Sensing Imagery Based on a Multifeature Convolutional Neural Network and Morphological Filtering

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Very High Resolution Remote Sensing Imagery Classification Using a Fusion of Random Forest and Deep Learning Technique—Subtropical Area for Example

Contact Info

Product

Resources

About