Print Email Facebook Twitter SUM Title SUM: A benchmark dataset of Semantic Urban Meshes Author Gao, W. (TU Delft Urban Data Science) Nan, L. (TU Delft Urban Data Science) Boom, Bas (CycloMedia Technology) Ledoux, H. (TU Delft Urban Data Science) Date 2021 Abstract Recent developments in data acquisition technology allow us to collect 3D texture meshes quickly. Those can help us understand and analyse the urban environment, and as a consequence are useful for several applications like spatial analysis and urban planning. Semantic segmentation of texture meshes through deep learning methods can enhance this understanding, but it requires a lot of labelled data. The contributions of this work are three-fold: (1) a new benchmark dataset of semantic urban meshes, (2) a novel semi-automatic annotation framework, and (3) an annotation tool for 3D meshes. In particular, our dataset covers about 4 km2 in Helsinki (Finland), with six classes, and we estimate that we save about 600 h of labelling work using our annotation framework, which includes initial segmentation and interactive refinement. We also compare the performance of several state-of-the-art 3D semantic segmentation methods on the new benchmark dataset. Other researchers can use our results to train their networks: the dataset is publicly available, and the annotation tool is released as open-source. Subject Benchmark datasetMesh annotationOver-segmentationSemantic segmentationTexture meshesUrban scene understanding To reference this document use: http://resolver.tudelft.nl/uuid:60576e57-a195-4fcf-89d8-0890414c5c53 DOI https://doi.org/10.1016/j.isprsjprs.2021.07.008 ISSN 0924-2716 Source ISPRS Journal of Photogrammetry and Remote Sensing, 179, 108-120 Part of collection Institutional Repository Document type journal article Rights © 2021 W. Gao, L. Nan, Bas Boom, H. Ledoux Files PDF 1_s2.0_S0924271621001854_main.pdf 8.85 MB Close viewer /islandora/object/uuid:60576e57-a195-4fcf-89d8-0890414c5c53/datastream/OBJ/view