A hybrid approach to building simplification with an evaluator from a backpropagation neural network

Yang, Min; Yuan, Tuo; Yan, Xiongfeng; Ai, Tinghua; Jiang, Chenjun

doi:10.1080/13658816.2021.1873998

Cited by 29 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They compared the performance of three network architectures (i.e., U-net, residual U-net, and generative adversarial network [GAN]) at different target map scales, and concluded that all the three networks have abilities to generate building maps at different scales. Yang et al (2021) proposed a supervised neural network model to identify the best simplified representation of buildings from the simplification candidates generated by exiting algorithms. In addition, there are some studies that use neural network models for line simplification.…”

Section: Rel Ated Workmentioning

confidence: 99%

See 1 more Smart Citation

Data‐driven polyline simplification using a stacked autoencoder‐based deep neural network

Chen

2022

Transactions in GIS

View full text Add to dashboard Cite

Automatic simplification of polylines is an important issue in spatial database and mapping. Traditional rule‐based methods are usually limited in performance, especially when the man‐made rules have to be adapted to different polylines with different shapes and structures. Compared to the existing neural network methods focusing only on the output layer or the code layers for classification or regression, our proposed method generates multi‐level abstractions of polylines by extracting features from multiple hidden layers. Specifically, we first organize the cartographic polylines into the form of feature vectors acceptable to the neural network model. Then, a stacked autoencoder‐based deep neural network model is trained to learn the pattern features of polyline bends and omit unimportant details layer by layer. Finally, the multi‐level abstractions of input polylines are generated from different hidden layers of a single model. The experimental results demonstrate that, compared with the classic Douglas–Peucker and Wang and Muller algorithms, the proposed method is able to properly simplify the polylines while representing their essential shapes smoothly and reducing areal displacement.

show abstract

Section: Rel Ated Workmentioning

confidence: 99%

“…In the map generalization domain, existing neural network‐based studies focus mainly on building generalization (Cheng et al, 2013; Feng et al, 2019; Sester et al, 2018; Touya et al, 2019; Yang et al, 2021). For example, Feng et al (2019) employed deep convolutional neural networks (DCNNs) for building generalization with raster images.…”

Section: Related Workmentioning

confidence: 99%

Data‐driven polyline simplification using a stacked autoencoder‐based deep neural network

Chen

2022

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…For a building, as Figure 12a shows, the tangent angle of an arbitrary point 𝑂 on its outline along a reference orientation (e.g., X-axis) is 𝜓, and the turning function 𝑓 𝑠 is defined as the change relationship of the tangent angle 𝜓 along its outline in a counterclockwise direction with respect to the arc length 𝑠 (as Figure 12b shows). The total arc length 𝑠 is 1 [42]. The 𝑆𝐷𝐶 between the original and simplified buildings is measured as follows [40]:…”

Section: Determination Of the Simplification Evaluation Indicatorsmentioning

confidence: 99%

“…In combined-based methods, different algorithms are combined to achieve the building simplification task. Considering numerous algorithms to simplify buildings, Yang et al (2021) [42] presented a hybrid approach that identifies the best simplified representation of a building among four existing algorithms to generate simplification candidates with a backpropagation neural network. Wei et al (2021) [8] proposed a combined building simplification approach based on local structure classification.…”

mentioning

confidence: 99%

A Progressive Simplification Method for Buildings Based on Structural Subdivision

Zhai

Yin

et al. 2022

IJGI

View full text Add to dashboard Cite

Building simplification is an important research area in automatic map generalization. Up to now, many approaches have been proposed by scholars. However, in the continuous transformation of scales for buildings, keeping the main shape characteristics, area, and orthogonality of buildings are always the key and difficult points. Therefore, this paper proposes a method of progressive simplification for buildings based on structural subdivision. In this paper, iterative simplification is adopted, which transforms the problem of building simplification into the simplification of the minimum details of building outlines. Firstly, a top priority structure (TPS) is determined, which represents the smallest detail in the outline of the building. Then, according to the orthogonality and concave–convex characteristics, the TPS are classified as 62 subdivisions, which cover the local structure of the building polygon. Then, the subdivisions are divided into four simplification types. The building is simplified to eliminate the TPS continuously, retaining the right-angle characteristics and area as much as possible, until the results satisfy the constraints and rules of simplification. A topographic dataset (1:1K) collected from Kadaster was used for our experiments. In order to evaluate the algorithm, many tests were undertaken, including tests of multi-scale simplification and simplification of typical buildings, which indicate that this method can realize multi-scale presentation of buildings. Compared with the existing simplification methods, the comparison results show that the proposed method can simplify buildings effectively, which has certain advantages in keeping shape characteristics, area, and rectangularity.

show abstract

“…Some studies have approached some pre-processing operations of generalization, e.g., structure recognition (Yan et al, 2019), building grouping (Yan et al, 2020), and shape coding (Yan et al, 2021), most of which are based on graph neural networks (GCNs). Recently, a classifier was trained using a backpropagation neural network to select the most appropriate conventional simplification algorithms for different shapes of buildings (Yang et al, 2022), but it still falls short of explicitly modeling the associated generalization operators, such as simplification, most importantly. Although in principle it has been shown that GCNs are capable of encoding vector map objects, it is still unclear how GCNs could work for end-to-end map generalization, that is, vector maps in and vector maps out.…”

mentioning

confidence: 99%

Building simplification of vector maps using graph convolutional neural networks

Zhou

Fang²,

Weibel³

2022

Abstr. Int. Cartogr. Assoc.

View full text Add to dashboard Cite

A hybrid approach to building simplification with an evaluator from a backpropagation neural network

Cited by 29 publications

References 31 publications

Data‐driven polyline simplification using a stacked autoencoder‐based deep neural network

Data‐driven polyline simplification using a stacked autoencoder‐based deep neural network

A Progressive Simplification Method for Buildings Based on Structural Subdivision

Building simplification of vector maps using graph convolutional neural networks

Contact Info

Product

Resources

About