From Raster Predictions to Vector Layers of Buildings: A Computational Geometry Approach

Bauchet, Jean-Philippe; Gobbin, Arno; Tarabalka, Yuliya

doi:10.1109/igarss46834.2022.9883810

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each acquisition, a manual vectorization of building rooftops is performed, creating an accurate and detailed representation of the urban environment. In addition, an automatic extraction method described in (Bauchet et al, 2022) is applied to generate an alternative set of rooftop vectors.…”

Section: Dataset Overviewmentioning

confidence: 99%

Novel Approaches for Aligning Geospatial Vector Maps

Cherif,

Tripodi,

Tarabalka

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The surge in data across diverse fields presents an essential need for advanced techniques to merge and interpret this information. With a special emphasis on compiling geospatial data, this integration is crucial for unlocking new insights from geographic data, enhancing our ability to map and analyze trends that span across different locations and environments with more authenticity and reliability. Existing techniques have made progress in addressing data fusion; however, challenges persist in fusing and harmonizing data from different sources, scales, and modalities. This research presents a comprehensive investigation into the challenges and solutions in vector map alignment, focusing on developing methods that enhance the precision and usability of geospatial data. We explored and developed three distinct methodologies for polygonal vector map alignment: ProximityAlign, which excels in precision within urban layouts but faces computational challenges; the Optical Flow Deep Learning-Based Alignment, noted for its efficiency and adaptability; and the Epipolar Geometry-Based Alignment, effective in data-rich contexts but sensitive to data quality. In practice, the proposed approaches serve as tools to benefit from as much as possible from existing datasets while respecting a spatial reference source. It also serves as a paramount step for the data fusion task to reduce its complexity.

show abstract

Section: Dataset Overviewmentioning

confidence: 99%

Novel Approaches for Aligning Geospatial Vector Maps

Cherif,

Tripodi,

Tarabalka

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Recent studies extracted building outlines using a polygonal partitioning of the space and a discrete optimization. They delivered accurate and simple vectorized building rooftops [13]. [155] introduced a multitask learning network that produced pixel-wise segmentation, directional information about the building contours, and the mid-level attraction fields of line segments.…”

Section: Geometric Feature Learning From Imagesmentioning

confidence: 99%