Conflating linear features using turning function distance: A new orientation‐sensitive similarity measure

Abstract

Measuring the similarity between counterpart geospatial features is crucial in the effective conflation of spatial datasets from difference sources. This article proposes a new similarity metric called the “map turning function distance” (MTFD) for matching linear features such as roads based on the well‐known turning function (TF) distance in computer vision. The MTFD overcomes the limitations of the traditional TF distance, such as the inability to handle partial matches and insensitivity to differences in scale and rotation. In particular, the MTFD allows one to: (a) partially match a linear feature to a portion of a larger feature from a certain position of match; and (b) consider both the shape and orientation differences of polylines based on comparing their turning angles. In finding the best match position, we prove that the optimal position can be found among a finite set of positions on the target feature. We then combine the MTFD with widely used point‐offset distances such as the Hausdorff distance to form a composite similarity metric. Our experiments with real road datasets demonstrate that the new metric has greater discriminative power than traditional point‐offset‐based similarity measures, and significantly improves the precision of two tested conflation models.

Towards Topological Geospatial Conflation: An Optimized Node-Arc Conflation Model for Road Networks

“…Such normalization removes the difference in the overall orientation between the two curves and measures only the shape distortion between them. Alternatively, when scale and orientation are important (e.g., in map conflation), a map turning function distance (MTFD) [17] is defined, which can capture both the overall orientation difference and shape distortion.…”

Linear feature conflation: An optimization‐based matching model with connectivity constraints

“…Several studies (Lei, 2020; Lei & Lei, 2019; Lei & Wang, 2021) used the minimum network flow problem (a.k.a. network flow problem) and developed the fixed‐charge matching ( fc‐matching ) problems.…”

“…Despite the advantages of optimization‐based conflation, current conflation models are limited. They are primarily based on the classic “map assignment problem” (Li & Goodchild, 2010, 2011; Rosen & Saalfeld, 1985) and more recently the network flow model (Lei, 2020; Lei & Lei, 2019; Lei & Wang, 2021) in operations research. A main limitation of current optimized conflation models is that they match geospatial objects between datasets at an individual object level.…”