Automated Matching of Multi-Scale Building Data Based on Relaxation Labelling and Pattern Combinations

Abstract

With the increasingly urgent demand for map conflation and timely data updating, data matching has become a crucial issue in big data and the GIS community. However, non-rigid deviation, shape homogenization, and uncertain scale differences occur in crowdsourced and official building data, causing challenges in conflating heterogeneous building datasets from different sources and scales. This paper thus proposes an automated building data matching method based on relaxation labelling and pattern combinations. The proposed method first detects all possible matching objects and pattern combinations to create a matching table, and calculates four geo-similarities for each candidate-matching pair to initialize a probabilistic matching matrix. After that, the contextual information of neighboring candidate-matching pairs is explored to heuristically amend the geo-similarity-based matching matrix for achieving a contextual matching consistency. Three case studies are conducted to illustrate that the proposed method obtains high matching accuracies and correctly identifies various 1:1, 1:M, and M:N matching. This indicates the pattern-level relaxation labelling matching method can efficiently overcome the problems of shape homogeneity and non-rigid deviation, and meanwhile has weak sensitivity to uncertain scale differences, providing a functional solution for conflating crowdsourced and official building data.

Reallocation model in land consolidation using multi‐objective particle swarm optimization dealing with landowners' rights

“…The shape of the land is effective in the facilitation of mechanization operations and “planting to harvesting” activities (Asiama, Bennett, Zevenbergen, & Mano, 2019). Numerous indicators have been developed to express the geometric shape of the land parcels (Aslan, Gündoğdu, & Arici, 2007; Demetriou et al., 2013; Oksanen, 2013; Wang, Lv, Chen, & Du, 2015; Zandonadi, Luck, Stombaugh, & Shearer, 2013; Zhang et al., 2017, 2019). In this research, the indicators of compactness, elongation, orientation, rectangularity, and smoothness of the edges have been used to calculate the geometric similarity.…”

A building polygonal object matching method based on minimum bounding rectangle combinatorial optimization and relaxation labeling

“…Furthermore, some relaxation labeling-based matching evaluation methods are favored by researchers (Song et al, 2011;Yang et al, 2013;Zhang et al, 2014Zhang et al, , 2019Zhang, Yin, et al, 2018). Relaxation labeling algorithms come from computer vision and pattern recognition and usually determine the one-to-one correspondence between points.…”

“…It extends the existing relaxation labeling algorithm to handle one‐to‐many and many‐to‐many matching objects. However, this approach has also been criticized because it only calculates the matching confidence of 1:1 matching pairs and ignores the total matching confidence of 1:N and M:N matching pairs (Zhang et al, 2019). Therefore, Zhang et al (2019) proposed a pattern combination method to improve this approach.…”

“…However, this approach has also been criticized because it only calculates the matching confidence of 1:1 matching pairs and ignores the total matching confidence of 1:N and M:N matching pairs (Zhang et al, 2019). Therefore, Zhang et al (2019) proposed a pattern combination method to improve this approach. However, the pattern combination method is exhaustive in nature, incurs high computational costs, and may be impractical for handling large geospatial datasets in practice.…”

“…However, the pattern combination method is exhaustive in nature, incurs high computational costs, and may be impractical for handling large geospatial datasets in practice. To solve this vexing disadvantage, Zhang et al (2019) set a series of thresholds to filter out unlikely potential matching pairs for relaxation labeling‐based evaluation algorithms to work effectively.…”