Comparative analysis of deep learning based building extraction methods with the new VHR Istanbul dataset

Bakırman, Tolga; Komurcu, Irem; Sertel, Elif

doi:10.1016/j.eswa.2022.117346

Cited by 19 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We implemented the Resnext50-32 × -4d encoder, which was found successful for road extraction by [2], and the se_resnext101_32 × 4d encoder, which was found the best encoder with Unet++ architecture for the building detection task [19].…”

Section: Resultsmentioning

confidence: 99%

“…Precision is the fraction of classified pixels relevant to the class and recall indicates the fraction of the relevant pixels that are successfully classified. F1 score, the harmonic mean of the precision and recall, is also calculated since it works well on imbalanced data [10], [19]. The accuracy value is calculated using true positive, true negative, false positive, and false negative values.…”

Section: Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Road Extraction From Historical Maps

Avci¹,

Sertel

Kabadayı³

2022

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

Automatic road extraction from historical maps is 1 an important task to understand past transportation conditions 2 and conduct spatiotemporal analysis revealing information about 3 historical events and human activities over the years. This 4 research aimed to propose the ideal architecture, encoder, and 5 hyperparameter settings for the historical road extraction task. 6 We used a dataset including 7076 patches with the size of 7 256 × 256 pixels generated from scanned historical Deutsche 8 Heereskarte 1:200 000 Türkei (DHK 200 Turkey) maps and their 9 corresponding digitized ground truth masks for five different 10 roads types. We first tested the widely used Unet++ and 11 Deeplabv3 architectures. We also evaluated the contribution of 12 attention models by implementing Unet++ with the concurrent 13 spatial and channel-squeeze and excitation block and multiscale 14 attention net. We achieved the best results with split-attention 15 network (Timm-resnest200e) encoder and Unet++ architecture, 16 with 98.99% overall accuracy, 41.99% intersection of union, 17 51.41% precision, 69.7% recall, and 57.72% F1 score values. 18 Our output weights could be directly used for the inference of 19 other DHK maps and transfer learning for similar or different 20 historical maps. The proposed architecture could also be imple-21 mented in different road extraction studies.22

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

Deep Learning-Based Road Extraction From Historical Maps

Avci¹,

Sertel

Kabadayı³

2022

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the realm of building footprint segmentation, deep learning approaches employing convolutional neural networks (CNNs) have become pivotal, showcasing remarkable capabilities in pixel-based or object-based semantic segmentation on orthophotos 10 , 28 , 29 . The extensive array of deep learning algorithms, including AlexNet, fully convolutional networks, U-Net, VGG, GoogLeNet, ResNet, DenseNet, LinkNet, pyramid scene parsing network, bottom-up and top-down feature pyramid network, and DeepLabv3 and DeepLabv3+, have demonstrated their efficiency in achieving both accuracy and robustness during the building footprint segmentation process 30 .…”

Section: Related Workmentioning

confidence: 99%

Revolutionizing urban mapping: deep learning and data fusion strategies for accurate building footprint segmentation

Dabove,

Daud,

Olivotto

2024

Sci Rep

View full text Add to dashboard Cite

In the dynamic urban landscape, understanding the distribution of buildings is paramount. Extracting and delineating building footprints from high-resolution images, captured by aerial platforms or satellites, is essential but challenging to accomplish manually, due to the abundance of high-resolution data. Automation becomes imperative, yet it introduces complexities related to handling diverse data sources and the computational demands of advanced algorithms. The innovative solution proposed in this paper addresses some intricate challenges occurring when integrating deep learning and data fusion on Earth Observed imagery. By merging RGB orthophotos with Digital Surface Models, deriving from the same aerial high-resolution surveys, an integrated consistent four-band dataset is generated. This unified approach, focused on the extraction of height information through stereoscopy utilizing a singular source, facilitates enhanced pixel-to-pixel data fusion. Employing DeepLabv3 algorithms, a state-of-the-art semantic segmentation network for multi-scale context, pixel-based segmentation on the integrated dataset was performed, excelling in capturing intricate details, particularly when enhanced by the additional height information deriving from the Digital Surface Models acquired over urban landscapes. Evaluation over a 21 km2 area in Turin, Italy, featuring diverse building frameworks, showcases how the proposed approach leads towards superior accuracy levels and building boundary refinement. Notably, the methodology discussed in the present article, significantly reduces training time compared to conventional approaches like U-Net, overcoming inherent challenges in high-resolution data automation. By establishing the effectiveness of leveraging DeepLabv3 algorithms on an integrated dataset for precise building footprint segmentation, the present contribution holds promise for applications in 3D modelling, Change detection and urban planning. An approach favouring the application of deep learning strategies on integrated high-resolution datasets can then guide decision-making processes facilitating urban management tasks.

show abstract

“…The building register is the fundamental record for storing information and other relevant data necessary for taxation, public planning and emergency services. Up-to-date building footprint maps are essential for many geospatial applications including disaster management, population estimation, monitoring of urban and impervious areas, 3D city modeling, detection of illegal construction cases (Bakirman et al, 2022), updating topographical databases on a country-wide level and assessing the damage after natural disasters (Takhtkeshha et al, 2023). Although machine learning methods have achieved accurate results in the past in building segmentation, current trends have moved towards the utilization of deep learning for building footprint extraction, that require minimal post-processing after segmentation has been performed.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Deep Learning Workflow for Building Segmentation, Boundary Regularization and Vectorization of Building Footprints

Šanca

Jyhne

Gazzea

et al. 2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Automatic building footprint extraction from remote sensing imagery is a widely used method, with deep learning techniques being particularly effective. However, deep learning approaches still require additional post-processing steps due to pixel-wise predictions, that contribute to occluded and geometrically incorrectly segmented buildings. To address this issue, we propose an end-to-end workflow that utilizes binary semantic segmentation, regularization, and vectorization. We implement and assess the performance of four convolutional neural network architectures including U-Net, U-NetFormer, FT-UnetFormer, and DCSwin on the MapAI Precision in Building Segmentation competition. To additionally improve the shape of the predicted buildings we apply regularization on the predictions to assess whether regularization further improves the geometrical shape and improve the prediction accuracy. We aim to produce accurate predictions with regularized boundaries that can prove useful in many cartographic and engineering applications. The regularization and vectorization workflow is further developed into a working QGIS-plugin that can be used to extend the functionality of QGIS. Our aim is to provide an end-to-end workflow for building segmentation, regularization and vectorization.

show abstract

Comparative analysis of deep learning based building extraction methods with the new VHR Istanbul dataset

Cited by 19 publications

References 54 publications

Deep Learning-Based Road Extraction From Historical Maps

Deep Learning-Based Road Extraction From Historical Maps

Revolutionizing urban mapping: deep learning and data fusion strategies for accurate building footprint segmentation

An End-to-End Deep Learning Workflow for Building Segmentation, Boundary Regularization and Vectorization of Building Footprints

Contact Info

Product

Resources

About