Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF

Li, Er; Femiani, John; Xu, Shibiao; Zhang, Xiao-Peng; Wonka, Peter

doi:10.1109/tgrs.2015.2400462

Cited by 102 publications

(67 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There has been a quick uptake of the approach in the remote sensing community and various solutions based on deep learning have been presented recently (e.g. Audebert et al, 2016Audebert et al, , 2017Audebert et al, , 2018Längkvist et al, 2016;Li et al, 2015;Li and Shao, 2014;Volpi and Tuia, 2017;Liu et al, 2018Liu et al, , 2017aPan et al, 2018a,b;Marmanis et al, 2016Marmanis et al, , 2018Wen et al, 2017;Zhao et al, 2017b). A comprehensive review of deep learning applications in the field of remote sensing can be found in ; Ma et al (2019); Gu et al (2019).…”

Section: Related Workmentioning

confidence: 99%

ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data

Diakogiannis

Waldner

Caccetta

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

990

428

View full text Add to dashboard Cite

Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications. Due to the large within-class and small between-class variance in pixel values of objects of interest, this remains a challenging task. In recent years, deep convolutional neural networks have started being used in remote sensing applications and demonstrate state of the art performance for pixel level classification of objects. Here we propose a reliable framework for performant results for the task of semantic segmentation of monotemporal very high resolution aerial images. Our framework consists of a novel deep learning architecture, ResUNet-a, and a novel loss function based on the Dice loss. ResUNet-a uses a UNet encoder/decoder backbone, in combination with residual connections, atrous convolutions, pyramid scene parsing pooling and multi-tasking inference. ResUNet-a infers sequentially the boundary of the objects, the distance transform of the segmentation mask, the segmentation mask and a colored reconstruction of the input. Each of the tasks is conditioned on the inference of the previous ones, thus establishing a conditioned relationship between the various tasks, as this is described through the architecture's computation graph. We analyse the performance of several flavours of the Generalized Dice loss for semantic segmentation, and we introduce a novel variant loss function for semantic segmentation of objects that has excellent convergence properties and behaves well even under the presence of highly imbalanced classes. The performance of our modeling framework is evaluated on the ISPRS 2D Potsdam dataset. Results show state-of-the-art performance with an average F1 score of 92.9% over all classes for our best model.

show abstract

Section: Related Workmentioning

confidence: 99%

ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data

Diakogiannis

Waldner

Caccetta

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

990

428

View full text Add to dashboard Cite

show abstract

“…The target of this problem is to assign each pixel to a given object category. Note that it is not just limited to building extraction (Li et al, 2015a), road extraction (Cheng et al, 2017b) and vegetation extraction (Wen et al, 2017) which only consider labeling one single category, semantic labeling usually considers several categories simultaneously (Li et al, 2015b;Xu et al, 2016;Xue et al, 2015). As a result, this task is very challenging, especially for the urban areas, which exhibit high diversity of manmade objects.…”

Section: Introductionmentioning

confidence: 99%

Semantic labeling in very high resolution images via a self-cascaded convolutional neural network

Liu

Fan

Wang

et al. 2018

ISPRS Journal of Photogrammetry and Remote Sensing

242

131

View full text Add to dashboard Cite

Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-toend self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Technically, multi-scale contexts are captured on the output of a CNN encoder, and then they are successively aggregated in a self-cascaded manner. Meanwhile, for fine-structured objects, ScasNet boosts the labeling accuracy with a coarse-to-fine refinement strategy. It progressively refines the target objects using the low-level features learned by CNN's shallow layers. In addition, to correct the latent fitting residual caused by multi-feature fusion inside Scas-Net, a dedicated residual correction scheme is proposed. It greatly improves the effectiveness of ScasNet. Extensive experimental results on three public datasets, including two challenging benchmarks, show that ScasNet achieves the state-of-the-art performance.

show abstract

“…A framework is presented on [21] for building extraction from visible band images. Combining supervised and unsupervised classification, accurate rooftop extraction is achieved using a Higher order Conditional Random Field.…”

Section: Data Characteristics and Primitive Featuresmentioning

confidence: 99%

Web-Based Supervised Thematic Mapping

Silva

Bengoa

Quartulli

et al. 2015

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

View full text Add to dashboard Cite

We introduce a methodology for semiautomatic thematic map generation from remotely sensed Earth Observation raster image data based on user-selected examples. The methodology is based on a probabilistic k-nearest neighbor supervised classification algorithm. Efficient operation is attained by exploiting data structures for high-dimensional indexing. The methodology is integrated in a Web-mapping server that is coupled to an HTML supervision interface that supports interactive navigation as well as model training and tuning. Quantitative classification quality and performance measurements are extracted for real optical data with 0.25 m resolution on a highly diverse training area.Index Terms-Remote sensing, thematic mapping, Web-based mapping systems.

show abstract

Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF

Cited by 102 publications

References 29 publications

ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data

ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data

Semantic labeling in very high resolution images via a self-cascaded convolutional neural network

Web-Based Supervised Thematic Mapping

Contact Info

Product

Resources

About