MAP-Net: Multiple Attending Path Neural Network for Building Footprint Extraction From Remote Sensed Imagery

Zhu, Qing; Liao, Cheng; Han, Hu; Mei, Xiaohong; Li, Haifeng

doi:10.1109/tgrs.2020.3026051

Cited by 190 publications

(104 citation statements)

References 46 publications

Supporting

Mentioning

103

Contrasting

Order By: Relevance

“…EU-Net [37] uses the DSPP module to extract dense and multi-scale features and a focal loss function to make the training stage more stable. MAP-Net [40] has an HRNet-like architecture with a multiparallel path to capture spatial multi-scale features. We do not reproduce the results of these building extraction networks since most of their source codes are not available.…”

Section: Selected Models For Comparisonmentioning

confidence: 99%

“…We further compared the computational cost of different models in terms of floating point of operations (FLOPs) and the number of trainable parameters. These two metrics have been frequently used to measure models' computational complexity in the deep learning area [40,46,57]. Higher FLOPs and more trainable parameters correspond to greater complexity of a model.…”

Section: H Complexity Of Mha-netmentioning

confidence: 99%

“…With the advances made in FCNs and semantic segmentation, many FCN-based models have been designed to automatically extract building footprints [8,13,[31][32][33][34][35][36][37][38][39][40][41][42]. For example, Bischke et al [34] developed a multi-task building segmentation network to address the problem of preserving building footprint boundaries.…”

Section: Introductionmentioning

confidence: 99%

“…Guo et al [39] proposed a scene-driven multi-task parallel attention convolution network (MTPA-Net) to extract buildings for various scenes. Zhu et al developed the MAP-Net model [40] that can learn multi-scale features via a multiparallel path and aggregate them with an attention module. Ding et al [41] argued that traditional CNNs could not capture the shape patterns of buildings and proposed an adversarial shape learning network (ASLNet) to strengthen the performance of building extraction by augmenting building shape features.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MHA-Net: Multipath Hybrid Attention Network for Building Footprint Extraction From High-Resolution Remote Sensing Imagery

Cai

Chen

2021

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

View full text Add to dashboard Cite

Deep learning approaches have been widely applied to building footprint extraction using high-resolution imagery. However, the traditional fully convolution network (FCN) still has problems in recovering spatial details and discriminating buildings with varying sizes and styles. We propose a novel multipath hybrid attention network (MHA-Net) to address these challenges. We design a separable convolution block attention module and an attention downsampling module as the basic modules with separable convolutions and channel attention. The MHA-Net architecture consists of three components: the encoding network, multipath hybrid dilated convolution (HDC), and dense upsampling convolution (DUC). The encoding network is used to encode the high-level semantic contexts of images. The multipath HDC aggregates multi-scale features by combining rich semantic representations extracted by HDCs, which can achieve promising results in extracting tiny buildings. The DUC is capable of recovering precise spatial information of buildings. We evaluate our network on two public datasets, the WHU aerial building dataset and the Massachusetts building dataset. According to the experimental results, MHA-Net outperforms other classical semantic segmentation models and several recent building extraction models. In particular, MHA-Net can improve the extraction accuracy of small buildings and is robust to complicated building roofs.

show abstract

Section: Selected Models For Comparisonmentioning

confidence: 99%

Section: H Complexity Of Mha-netmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MHA-Net: Multipath Hybrid Attention Network for Building Footprint Extraction From High-Resolution Remote Sensing Imagery

Cai

Chen

2021

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

View full text Add to dashboard Cite

show abstract

“…As a consequence, the extracted buildings are generally not regularized and adhesive in a complex urban environment. As Figure 1 shows, indicated by the yellow circle, column (b) extracted by MAP-Net [8], which proposed an independently parallel network that preserves multiscale spatial details and rich high-level semantics features, is inaccurate at the building boundary, specifically in adjacent areas. Even if the pixel-wise metrics such as the intersection over union (IoU) scores (as explicitly optimized in the end-to-end objective function) are relatively high, the above flaw still renders the results less useful.…”

mentioning

confidence: 99%

Joint Learning of Contour and Structure for Boundary-Preserved Building Extraction

Liao

Han

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Most of the existing approaches to the extraction of buildings from high-resolution orthoimages consider the problem as semantic segmentation, which extracts a pixel-wise mask for buildings and trains end-to-end with manually labeled building maps. However, as buildings are highly structured, such a strategy suffers several problems, such as blurred boundaries and the adhesion to close objects. To alleviate the above problems, we proposed a new strategy that also considers the contours of the buildings. Both the contours and structures of the buildings are jointly learned in the same network. The contours are learnable because the boundary of the mask labels of buildings implicitly represents the contours of buildings. We utilized the building contour information embedded in the labels to optimize the representation of building boundaries, then combined the contour information with multi-scale semantic features to enhance the robustness to image spatial resolution. The experimental results showed that the proposed method achieved 91.64%, 81.34%, and 74.51% intersection over union (IoU) on the WHU, Aerial, and Massachusetts building datasets, and outperformed the state-of-the-art (SOTA) methods. It significantly improved the accuracy of building boundaries, especially for the edges of adjacent buildings. The code is made publicly available.

show abstract

Lake water body extraction of optical remote sensing images based on semantic segmentation

et al. 2022

View full text Add to dashboard Cite

MAP-Net: Multiple Attending Path Neural Network for Building Footprint Extraction From Remote Sensed Imagery

Cited by 190 publications

References 46 publications

MHA-Net: Multipath Hybrid Attention Network for Building Footprint Extraction From High-Resolution Remote Sensing Imagery

MHA-Net: Multipath Hybrid Attention Network for Building Footprint Extraction From High-Resolution Remote Sensing Imagery

Joint Learning of Contour and Structure for Boundary-Preserved Building Extraction

Lake water body extraction of optical remote sensing images based on semantic segmentation

Contact Info

Product

Resources

About