scholarly journals A BOUNDARY AWARE NEURAL NETWORK FOR ROAD EXTRACTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGERY

2020 ◽  
Vol V-3-2020 ◽  
pp. 67-73
Author(s):  
H. Sui ◽  
M. Zhou ◽  
M. Peng ◽  
N. Xiong
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Ground Truth ◽  
Road Extraction ◽  
Remote Sensing Imagery ◽  
Automatic Navigation ◽  
Road Maps ◽  
The Difference ◽  
Road Segmentation ◽  
Coarse To Fine

Abstract. Automatic road extraction from high-resolution remote sensing imagery has various applications like urban planning and automatic navigation. Existing methods for automatic road extraction however, focus on regional accuracy but not on the boundary quality. To address this problem, a Boundary-aware Road extraction Network (BARoadNet) is proposed. BARoadNet is a coarse-to-fine architecture composed of two encoder-to-decoder networks, a Coarse Map Predicting Module (CMPM) and Fine Map Predicting Module (FMPM). The CMPM learns to predict coarse road segmentation maps. The FMPM is used to refine the coarse road maps by learning the difference between the coarse road extraction result and the ground truth. Experiments are conducted on the open Massachusetts Road Dataset. Quantitative and qualitative analysis demonstrate that the proposed BARoadNet can improve the quality and accuracy of road extraction results compared with the state-of-the-art methods.

scholarly journals Road Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning

2018 ◽  
Vol 10 (9) ◽  
pp. 1461 ◽  
Author(s):  
Yongyang Xu ◽  
Zhong Xie ◽  
Yaxing Feng ◽  
Zhanlong Chen
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Road Network ◽  
Deep Convolutional Neural Network ◽  
Road Extraction ◽  
Remote Sensing Imagery ◽  
The Road

The road network plays an important role in the modern traffic system; as development occurs, the road structure changes frequently. Owing to the advancements in the field of high-resolution remote sensing, and the success of semantic segmentation success using deep learning in computer version, extracting the road network from high-resolution remote sensing imagery is becoming increasingly popular, and has become a new tool to update the geospatial database. Considering that the training dataset of the deep convolutional neural network will be clipped to a fixed size, which lead to the roads run through each sample, and that different kinds of road types have different widths, this work provides a segmentation model that was designed based on densely connected convolutional networks (DenseNet) and introduces the local and global attention units. The aim of this work is to propose a novel road extraction method that can efficiently extract the road network from remote sensing imagery with local and global information. A dataset from Google Earth was used to validate the method, and experiments showed that the proposed deep convolutional neural network can extract the road network accurately and effectively. This method also achieves a harmonic mean of precision and recall higher than other machine learning and deep learning methods.

scholarly journals A Coarse-to-Fine Contour Optimization Network for Extracting Building Instances from High-Resolution Remote Sensing Imagery

2021 ◽  
Vol 13 (19) ◽  
pp. 3814
Author(s):  
Fang Fang ◽  
Kaishun Wu ◽  
Yuanyuan Liu ◽  
Shengwen Li ◽  
Bo Wan ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
State Of The Art ◽  
Complex Structures ◽  
Building Extraction ◽  
Remote Sensing Imagery ◽  
Feature Pyramid ◽  
Coarse To Fine ◽  
Original Feature

Building instances extraction is an essential task for surveying and mapping. Challenges still exist in extracting building instances from high-resolution remote sensing imagery mainly because of complex structures, variety of scales, and interconnected buildings. This study proposes a coarse-to-fine contour optimization network to improve the performance of building instance extraction. Specifically, the network contains two special sub-networks: attention-based feature pyramid sub-network (AFPN) and coarse-to-fine contour sub-network. The former sub-network introduces channel attention into each layer of the original feature pyramid network (FPN) to improve the identification of small buildings, and the latter is designed to accurately extract building contours via two cascaded contour optimization learning. Furthermore, the whole network is jointly optimized by multiple losses, that is, a contour loss, a classification loss, a box regression loss and a general mask loss. Experimental results on three challenging building extraction datasets demonstrated that the proposed method outperformed the state-of-the-art methods’ accuracy and quality of building contours.

Research Status on Road Information Extraction from High Resolution Imagery

2013 ◽  
Vol 694-697 ◽  
pp. 1970-1973
Author(s):  
Hao Chen ◽  
Li Ma ◽  
Tian Liang
Keyword(s):  
Remote Sensing ◽  
Computer Vision ◽  
High Resolution ◽  
Information Extraction ◽  
Road Extraction ◽  
Remote Sensing Imagery ◽  
Research Status ◽  
High Resolution Imagery ◽  
Surveying And Mapping

Automatic road extraction from remote sensing imagery is one of the hot topics in the field of remote sensing. surveying and mapping. computer vision. etc. In this paper. we summarize the research status of road extraction from high resolution remote sensing imagery. The difficulties and trends of the research are analyzed in the paper.

scholarly journals Novel Framework for 3D Road Extraction Based on Airborne LiDAR and High-Resolution Remote Sensing Imagery

2021 ◽  
Vol 13 (23) ◽  
pp. 4766
Author(s):  
Lipeng Gao ◽  
Wenzhong Shi ◽  
Jun Zhu ◽  
Pan Shao ◽  
Sitong Sun ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Spatial Data ◽  
Estimation Method ◽  
Point Clouds ◽  
Airborne Lidar ◽  
Least Square ◽  
Collaborative Representation ◽  
Road Extraction ◽  
Remote Sensing Imagery

3D GIS has attracted increasing attention from academics, industries, and governments with the increase in the requirements for the interoperability and integration of different sources of spatial data. Three-dimensional road extraction based on multisource remote sensing data is still a challenging task due to road occlusion and topological complexity. This paper presents a novel framework for 3D road extraction by integrating LiDAR point clouds and high-resolution remote sensing imagery. First, a multiscale collaborative representation-based road probability estimation method was proposed to segment road surfaces from high-resolution remote sensing imagery. Then, an automatic stratification process was conducted to specify the layer values of each road segment. Additionally, a multifactor filtering strategy was proposed in consideration of the complexity of ground features and the existence of noise in LiDAR points. Lastly, a least-square-based elevation interpolation method is used for restoring the elevation information of road sections blocked by overpasses. The experimental results based on two datasets in Hong Kong Island show that the proposed method obtains competitively satisfactory results.

Estimations for Percentage of Impervious Area by the Use of Satellite Remote Sensing Imagery

1994 ◽  
Vol 29 (1-2) ◽  
pp. 135-144 ◽  
Author(s):  
C. Deguchi ◽  
S. Sugio
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Satellite Imagery ◽  
Satellite Remote Sensing ◽  
Aerial Photographs ◽  
Estimation Errors ◽  
Remote Sensing Imagery ◽  
Impervious Area ◽  
Urbanized Areas

This study aims to evaluate the applicability of satellite imagery in estimating the percentage of impervious area in urbanized areas. Two methods of estimation are proposed and applied to a small urbanized watershed in Japan. The area is considered under two different cases of subdivision; i.e., 14 zones and 17 zones. The satellite imageries of LANDSAT-MSS (Multi-Spectral Scanner) in 1984, MOS-MESSR(Multi-spectral Electronic Self-Scanning Radiometer) in 1988 and SPOT-HRV(High Resolution Visible) in 1988 are classified. The percentage of imperviousness in 17 zones is estimated by using these classification results. These values are compared with the ones obtained from the aerial photographs. The percent imperviousness derived from the imagery agrees well with those derived from aerial photographs. The estimation errors evaluated are less than 10%, the same as those obtained from aerial photographs.

scholarly journals Multi-Scene Building Height Estimation Method Based on Shadow in High Resolution Imagery

2021 ◽  
Vol 13 (15) ◽  
pp. 2862
Author(s):  
Yakun Xie ◽  
Dejun Feng ◽  
Sifan Xiong ◽  
Jun Zhu ◽  
Yangge Liu
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Estimation Method ◽  
Absolute Error ◽  
Large Error ◽  
Estimation Methods ◽  
Height Estimation ◽  
Building Height ◽  
Remote Sensing Imagery ◽  
High Resolution Imagery

Accurately building height estimation from remote sensing imagery is an important and challenging task. However, the existing shadow-based building height estimation methods have large errors due to the complex environment in remote sensing imagery. In this paper, we propose a multi-scene building height estimation method based on shadow in high resolution imagery. First, the shadow of building is classified and described by analyzing the features of building shadow in remote sensing imagery. Second, a variety of shadow-based building height estimation models is established in different scenes. In addition, a method of shadow regularization extraction is proposed, which can solve the problem of mutual adhesion shadows in dense building areas effectively. Finally, we propose a method for shadow length calculation combines with the fish net and the pauta criterion, which means that the large error caused by the complex shape of building shadow can be avoided. Multi-scene areas are selected for experimental analysis to prove the validity of our method. The experiment results show that the accuracy rate is as high as 96% within 2 m of absolute error of our method. In addition, we compared our proposed approach with the existing methods, and the results show that the absolute error of our method are reduced by 1.24 m-3.76 m, which can achieve high-precision estimation of building height.

Sign in / Sign up

Export Citation Format

Share Document