scholarly journals BUILDING OUTLINE EXTRACTION FROM AERIAL IMAGERY AND DIGITAL SURFACE MODEL WITH A FRAME FIELD LEARNING FRAMEWORK

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 487-493
Author(s):  
X. Sun ◽  
W. Zhao ◽  
R. V. Maretto ◽  
C. Persello
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
Aerial Images ◽  
Surface Model ◽  
Digital Surface Model ◽  
Frame Field ◽  
Learning Framework ◽  
Elevation Data ◽  
3D Information ◽  
Direction Information

Abstract. Deep learning-based semantic segmentation models for building delineation face the challenge of producing precise and regular building outlines. Recently, a building delineation method based on frame field learning was proposed by Girard et al. (2020) to extract regular building footprints as vector polygons directly from aerial RGB images. A fully convolution network (FCN) is trained to learn simultaneously the building mask, contours, and frame field followed by a polygonization method. With the direction information of the building contours stored in the frame field, the polygonization algorithm produces regular outlines accurately detecting edges and corners. This paper investigated the contribution of elevation data from the normalized digital surface model (nDSM) to extract accurate and regular building polygons. The 3D information provided by the nDSM overcomes the aerial images’ limitations and contributes to distinguishing the buildings from the background more accurately. Experiments conducted in Enschede, the Netherlands, demonstrate that the nDSM improves building outlines’ accuracy, resulting in better-aligned building polygons and prevents false positives. The investigated deep learning approach (fusing RGB + nDSM) results in a mean intersection over union (IOU) of 0.70 in the urban area. The baseline method (using RGB only) results in an IOU of 0.58 in the same area. A qualitative analysis of the results shows that the investigated model predicts more precise and regular polygons for large and complex structures.

scholarly journals Orchard Mapping with Deep Learning Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3813
Author(s):  
Athanasios Anagnostis ◽  
Aristotelis C. Tagarakis ◽  
Dimitrios Kateris ◽  
Vasileios Moysiadis ◽  
Claus Grøn Sørensen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Automated Detection ◽  
Aerial Images ◽  
Training Dataset ◽  
Field Boundary ◽  
Different Seasons ◽  
Detection And Localization ◽  
Different Levels

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

scholarly journals IMG2nDSM: Height Estimation from Single Airborne RGB Images with Deep Learning

2021 ◽  
Vol 13 (12) ◽  
pp. 2417
Author(s):  
Savvas Karatsiolis ◽  
Andreas Kamilaris ◽  
Ian Cole
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Aerial Imagery ◽  
Aerial Images ◽  
Surface Model ◽  
Large Area ◽  
Digital Terrain ◽  
Terrain Models ◽  
Architectural Features ◽  
Rgb Images

Estimating the height of buildings and vegetation in single aerial images is a challenging problem. A task-focused Deep Learning (DL) model that combines architectural features from successful DL models (U-NET and Residual Networks) and learns the mapping from a single aerial imagery to a normalized Digital Surface Model (nDSM) was proposed. The model was trained on aerial images whose corresponding DSM and Digital Terrain Models (DTM) were available and was then used to infer the nDSM of images with no elevation information. The model was evaluated with a dataset covering a large area of Manchester, UK, as well as the 2018 IEEE GRSS Data Fusion Contest LiDAR dataset. The results suggest that the proposed DL architecture is suitable for the task and surpasses other state-of-the-art DL approaches by a large margin.

scholarly journals Towards Scalable Economic Photovoltaic Potential Analysis Using Aerial Images and Deep Learning

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3800
Author(s):  
Sebastian Krapf ◽  
Nils Kemmerzell ◽  
Syed Khawaja Haseeb Khawaja Haseeb Uddin ◽  
Manuel Hack Hack Vázquez ◽  
Fabian Netzler ◽  
...  
Keyword(s):  
Deep Learning ◽  
System Analysis ◽  
State Of The Art ◽  
Critical Role ◽  
Semantic Segmentation ◽  
Energy System ◽  
Aerial Images ◽  
Potential Analysis ◽  
3D Data ◽  
Challenges And Opportunities

Roof-mounted photovoltaic systems play a critical role in the global transition to renewable energy generation. An analysis of roof photovoltaic potential is an important tool for supporting decision-making and for accelerating new installations. State of the art uses 3D data to conduct potential analyses with high spatial resolution, limiting the study area to places with available 3D data. Recent advances in deep learning allow the required roof information from aerial images to be extracted. Furthermore, most publications consider the technical photovoltaic potential, and only a few publications determine the photovoltaic economic potential. Therefore, this paper extends state of the art by proposing and applying a methodology for scalable economic photovoltaic potential analysis using aerial images and deep learning. Two convolutional neural networks are trained for semantic segmentation of roof segments and superstructures and achieve an Intersection over Union values of 0.84 and 0.64, respectively. We calculated the internal rate of return of each roof segment for 71 buildings in a small study area. A comparison of this paper’s methodology with a 3D-based analysis discusses its benefits and disadvantages. The proposed methodology uses only publicly available data and is potentially scalable to the global level. However, this poses a variety of research challenges and opportunities, which are summarized with a focus on the application of deep learning, economic photovoltaic potential analysis, and energy system analysis.

scholarly journals A Novel Object-Based Deep Learning Framework for Semantic Segmentation of Very High-Resolution Remote Sensing Data: Comparison with Convolutional and Fully Convolutional Networks

2019 ◽  
Vol 11 (6) ◽  
pp. 684 ◽  
Author(s):  
Maria Papadomanolaki ◽  
Maria Vakalopoulou ◽  
Konstantinos Karantzalos
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Novel Object ◽  
Convolutional Networks ◽  
Learning Framework ◽  
Fully Convolutional Networks ◽  
Object Based ◽  
Deep Networks ◽  
Very High

Deep learning architectures have received much attention in recent years demonstrating state-of-the-art performance in several segmentation, classification and other computer vision tasks. Most of these deep networks are based on either convolutional or fully convolutional architectures. In this paper, we propose a novel object-based deep-learning framework for semantic segmentation in very high-resolution satellite data. In particular, we exploit object-based priors integrated into a fully convolutional neural network by incorporating an anisotropic diffusion data preprocessing step and an additional loss term during the training process. Under this constrained framework, the goal is to enforce pixels that belong to the same object to be classified at the same semantic category. We compared thoroughly the novel object-based framework with the currently dominating convolutional and fully convolutional deep networks. In particular, numerous experiments were conducted on the publicly available ISPRS WGII/4 benchmark datasets, namely Vaihingen and Potsdam, for validation and inter-comparison based on a variety of metrics. Quantitatively, experimental results indicate that, overall, the proposed object-based framework slightly outperformed the current state-of-the-art fully convolutional networks by more than 1% in terms of overall accuracy, while intersection over union results are improved for all semantic categories. Qualitatively, man-made classes with more strict geometry such as buildings were the ones that benefit most from our method, especially along object boundaries, highlighting the great potential of the developed approach.

scholarly journals TESTING OF LAND COVER CLASSIFICATION FROM MULTISPECTRAL AIRBORNE LASER SCANNING DATA

2016 ◽  
Vol XLI-B7 ◽  
pp. 161-169 ◽  
Author(s):  
K. Bakuła ◽  
P. Kupidura ◽  
Ł. Jełowicki
Keyword(s):  
Land Cover ◽  
Laser Scanning ◽  
Near Infrared ◽  
Airborne Laser Scanning ◽  
Surface Model ◽  
Digital Surface Model ◽  
Airborne Laser ◽  
Laser Reflectance ◽  
Elevation Data ◽  
Intensity Images

Multispectral Airborne Laser Scanning provides a new opportunity for airborne data collection. It provides high-density topographic surveying and is also a useful tool for land cover mapping. Use of a minimum of three intensity images from a multiwavelength laser scanner and 3D information included in the digital surface model has the potential for land cover/use classification and a discussion about the application of this type of data in land cover/use mapping has recently begun. In the test study, three laser reflectance intensity images (orthogonalized point cloud) acquired in green, near-infrared and short-wave infrared bands, together with a digital surface model, were used in land cover/use classification where six classes were distinguished: water, sand and gravel, concrete and asphalt, low vegetation, trees and buildings. In the tested methods, different approaches for classification were applied: spectral (based only on laser reflectance intensity images), spectral with elevation data as additional input data, and spectro-textural, using morphological granulometry as a method of texture analysis of both types of data: spectral images and the digital surface model. The method of generating the intensity raster was also tested in the experiment. Reference data were created based on visual interpretation of ALS data and traditional optical aerial and satellite images. The results have shown that multispectral ALS data are unlike typical multispectral optical images, and they have a major potential for land cover/use classification. An overall accuracy of classification over 90% was achieved. The fusion of multi-wavelength laser intensity images and elevation data, with the additional use of textural information derived from granulometric analysis of images, helped to improve the accuracy of classification significantly. The method of interpolation for the intensity raster was not very helpful, and using intensity rasters with both first and last return numbers slightly improved the results.

scholarly journals TESTING OF LAND COVER CLASSIFICATION FROM MULTISPECTRAL AIRBORNE LASER SCANNING DATA

2016 ◽  
Vol XLI-B7 ◽  
pp. 161-169 ◽  
Author(s):  
K. Bakuła ◽  
P. Kupidura ◽  
Ł. Jełowicki
Keyword(s):  
Land Cover ◽  
Laser Scanning ◽  
Near Infrared ◽  
Airborne Laser Scanning ◽  
Surface Model ◽  
Digital Surface Model ◽  
Airborne Laser ◽  
Laser Reflectance ◽  
Elevation Data ◽  
Intensity Images

Multispectral Airborne Laser Scanning provides a new opportunity for airborne data collection. It provides high-density topographic surveying and is also a useful tool for land cover mapping. Use of a minimum of three intensity images from a multiwavelength laser scanner and 3D information included in the digital surface model has the potential for land cover/use classification and a discussion about the application of this type of data in land cover/use mapping has recently begun. In the test study, three laser reflectance intensity images (orthogonalized point cloud) acquired in green, near-infrared and short-wave infrared bands, together with a digital surface model, were used in land cover/use classification where six classes were distinguished: water, sand and gravel, concrete and asphalt, low vegetation, trees and buildings. In the tested methods, different approaches for classification were applied: spectral (based only on laser reflectance intensity images), spectral with elevation data as additional input data, and spectro-textural, using morphological granulometry as a method of texture analysis of both types of data: spectral images and the digital surface model. The method of generating the intensity raster was also tested in the experiment. Reference data were created based on visual interpretation of ALS data and traditional optical aerial and satellite images. The results have shown that multispectral ALS data are unlike typical multispectral optical images, and they have a major potential for land cover/use classification. An overall accuracy of classification over 90% was achieved. The fusion of multi-wavelength laser intensity images and elevation data, with the additional use of textural information derived from granulometric analysis of images, helped to improve the accuracy of classification significantly. The method of interpolation for the intensity raster was not very helpful, and using intensity rasters with both first and last return numbers slightly improved the results.

scholarly journals Semantic Segmentation of Urban Buildings Using a High-Resolution Network (HRNet) with Channel and Spatial Attention Gates

2021 ◽  
Vol 13 (16) ◽  
pp. 3087
Author(s):  
Seonkyeong Seong ◽  
Jaewan Choi
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Spatial Attention ◽  
Semantic Segmentation ◽  
Aerial Images ◽  
Building Extraction ◽  
Learning Models ◽  
Urban Buildings

In this study, building extraction in aerial images was performed using csAG-HRNet by applying HRNet-v2 in combination with channel and spatial attention gates. HRNet-v2 consists of transition and fusion processes based on subnetworks according to various resolutions. The channel and spatial attention gates were applied in the network to efficiently learn important features. A channel attention gate assigns weights in accordance with the importance of each channel, and a spatial attention gate assigns weights in accordance with the importance of each pixel position for the entire channel. In csAG-HRNet, csAG modules consisting of a channel attention gate and a spatial attention gate were applied to each subnetwork of stage and fusion modules in the HRNet-v2 network. In experiments using two datasets, it was confirmed that csAG-HRNet could minimize false detections based on the shapes of large buildings and small nonbuilding objects compared to existing deep learning models.

Sign in / Sign up

Export Citation Format

Share Document