Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints

Soni, Ashish; Koner, Radhakanta; Villuri, Vasanta Govind Kumar

doi:10.1016/j.asej.2021.10.017

Cited by 11 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The additional factor reduces the label inconsistencies by defining the conditional relationship between two classification maps. For a detailed theoretical and mathematical explanation of DuCNN-MMRF, the reader could follow Soni et al [19].…”

Section: Iintermediate Classification: Cnn-based Dual-scale Fusionmentioning

confidence: 99%

“…For instance, The optimal value of 𝜆 1 is 0.4, while calculating some examples from the testing dataset (from [19]). The rest of the values i.e (𝜆 1 ,1], is defined as a negative region, where pixel in this region is either incorrectly classified or uncertain.…”

Section: C-dst: Integrating Dsm With Optical Data Using Dst Based On ...mentioning

confidence: 99%

“…Therefore, instead of defining the mass function, a generalized measure can be used to limit the use of DST for regional-level fusion. This experimentation is the extension of the paper [19], where intermediate classification based on Dual-scale CNN and Modified Markov Random Field (MMRF) has been discussed. Herein, we have used a similar strategy to test in UHR imagery for intermediate classification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Uncertainty based Regional-Decision Fusion of Multispectral and nDSM for Ultra-High Resolution UAV Imagery

Soni

Koner

Villuri

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The recent advancement in the pattern recognition technique has demonstrated the superiority in remote sensing technology, where Deep neural network uses the spatial feature representation such as convolution neural network (CNN), to provide better generalization capability. Regardless of any CNN structure, the prediction always involves uncertainty and imprecision while classifying the ultra-high resolution (UHR) image. Our aim is two-fold: firstly, increase the reliability feature by performing the Dual-scale fusion via a modified Markov random field known as DuCNN-MMRF. Secondly, an integration framework was introduced to combine the multispectral image classification produced by DuCNN-MMRF and normalized-Digital Surface Model (nDSM) information, using a novel approach known as constraint-based Dempster Shafer theory (C-DST). C-DST targeted DuCNN-MMRF’s uncertain information (ambiguous information) and rectified it with complementary information. The complementary information (i.e., nDSM) was processed using conventional machine learning (ML) techniques such as Multilayer perceptron (MLP), Support vector machine (SVM) and Random Forest (RF). The integration approach also uses the Shannon entropy function to exploit the uncertain information of model prediction (i.e. DuCNN-MMRF) at the regional level and subdivide into the positive and negative regions. The positive region is trusted by DuCNN-MMRF, and the negative region was combined with DuCNN-MMRF and MLP (and others ML) in a restricted manner. An ultra-high resolution (UHR) images was collected with an unmanned aerial vehicle (UAV) in the semi-urban region of IIT, Dhanbad, India, and labeled with building features. In addition, ISPRS Potsdam dataset with five land cover classes (Tree, building, grassland, impervious surface, and car) was used. The proposed framework was tested with several combinations i.e. MMRF-SVM, MMRF-RF, MMRF-MLP, along with max-voting fusion. The MMRF-MLP yielded highest accuracy with 85.24% (Fmeasure) and 97.79%(OA), and 76.12%(Fmeasure) and 91.09%(OA), for study area and Potsdam dataset, respectively.

show abstract

Section: Iintermediate Classification: Cnn-based Dual-scale Fusionmentioning

confidence: 99%

Section: C-dst: Integrating Dsm With Optical Data Using Dst Based On ...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Uncertainty based Regional-Decision Fusion of Multispectral and nDSM for Ultra-High Resolution UAV Imagery

Soni

Koner

Villuri

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The past decade has witnessed the continuous development of neural network, which is also used in cloud segmentation [8-[13], power transmission system [14], and building segmentation [15][16][17][18][19][20], etc. In 2015, Long et al [21] proposed the Fully Convolutional Network (FCN), which was the first network successfully used for image segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…Although the existing convolutional neural networks can achieve good results in the field of architectural image segmentation, most of them ignore the correlation of feature information between different channels. Soni et al [19] proposed two-scale input-based architecture: Dual-scale CNN (Du-CNN). A Difference of Normals (DoN) approach is used to isolate 3D buildings from other objects in densely built-up areas.…”

Section: Introductionmentioning

confidence: 99%

ResAt-UNet: A U-Shaped Network Using ResNet and Attention Module for Image Segmentation of Urban Buildings

Fan

Liu

Xia

et al. 2023

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

View full text Add to dashboard Cite

Architectural image segmentation refers to the extraction of architectural objects from remote sensing images. At present, most neural networks ignore the relationship between feature information, and there are problems such as model overfitting and gradient explosion. Thus, this paper proposes an improved UNet based on ResNet34 and Attention Module (ResAt-UNet) to solve the related problems. The algorithm adds a twolayer residual structure (BasicBlock) and a regional enhancement attention mechanism (Space Enhancement Area Enhancement, SEAE) to the original framework of UNet, which enhances the network depth, improves the fitting performance, and extracts small objects more accurately. The experimental results show that the network has achieved MIOU of 78.81% in the Massachusetts dataset, and the newly developed model outperforms UNet in both quantitative and qualitative aspects.

show abstract

The effects of buildings' physical characteristics on urban network centrality

Amen¹

2022

Ain Shams Engineering Journal

View full text Add to dashboard Cite

Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints

Cited by 11 publications

References 33 publications

Uncertainty based Regional-Decision Fusion of Multispectral and nDSM for Ultra-High Resolution UAV Imagery

Uncertainty based Regional-Decision Fusion of Multispectral and nDSM for Ultra-High Resolution UAV Imagery

ResAt-UNet: A U-Shaped Network Using ResNet and Attention Module for Image Segmentation of Urban Buildings

The effects of buildings' physical characteristics on urban network centrality

Contact Info

Product

Resources

About