Abstract:Surface topography refers to the geometric micro-structure of a surface and defines its tactile characteristics (typically in the sub-millimeter range). High-resolution 3D scanning techniques developed recently enable the 3D reconstruction of surfaces including their surface topography. In this paper, we present an efficient image-space technique for the extraction of surface topography from high-resolution 3D reconstructions. Additionally, we filter noise and enhance topographic attributes to obtain an improv… Show more
“…This normalization can be efficiently performed in a pre-processing step by subtracting a smoothed version of the depth map (Gaussian filter with σ = 12.5 mm) from the depth map. This operation results in a local constrast equalization across the depth map [12] that better enhances the fine geometric details of the surface texture.…”
Section: Baseline Resultsmentioning
confidence: 99%
“…Second, we apply Convolutional Neural Networks (CNNs) [22], [23], which currently show best performance on standard semantic segmentation benchmarks [17]- [19], [24], [25] and compare them with the RF-based approach. We have shown previously that surface segmentation with 3D descriptors computed directly from the 3D point clouds is computationally demanding and with current state-of-the-art methods not performing well, see [12] for respective results for a subset of our dataset. Hence, we employ the depth maps and orthophotos generated from the point clouds as input to segmentation.…”
Section: B Methodsmentioning
confidence: 99%
“…This paper builds upon a series of incremental previous works on 3D surface segmentation and classification [12]- [14] and intends to consolidate and extend the achieved results. Our contribution beyond previous research are as follows:…”
Abstract-The development of powerful 3D scanning hardware and reconstruction algorithms has strongly promoted the generation of 3D surface reconstructions in different domains. An area of special interest for such 3D reconstructions is the cultural heritage domain, where surface reconstructions are generated to digitally preserve historical artifacts. While reconstruction quality nowadays is sufficient in many cases, the robust analysis (e.g. segmentation, matching, and classification) of reconstructed 3D data is still an open topic. In this paper, we target the automatic and interactive segmentation of high-resolution 3D surface reconstructions from the archaeological domain. To foster research in this field, we introduce a fully annotated and publicly available large-scale 3D surface dataset including high-resolution meshes, depth maps and point clouds as a novel benchmark dataset to the community. We provide baseline results for our existing random forest-based approach and for the first time investigate segmentation with convolutional neural networks (CNNs) on the data. Results show that both approaches have complementary strengths and weaknesses and that the provided dataset represents a challenge for future research.
“…This normalization can be efficiently performed in a pre-processing step by subtracting a smoothed version of the depth map (Gaussian filter with σ = 12.5 mm) from the depth map. This operation results in a local constrast equalization across the depth map [12] that better enhances the fine geometric details of the surface texture.…”
Section: Baseline Resultsmentioning
confidence: 99%
“…Second, we apply Convolutional Neural Networks (CNNs) [22], [23], which currently show best performance on standard semantic segmentation benchmarks [17]- [19], [24], [25] and compare them with the RF-based approach. We have shown previously that surface segmentation with 3D descriptors computed directly from the 3D point clouds is computationally demanding and with current state-of-the-art methods not performing well, see [12] for respective results for a subset of our dataset. Hence, we employ the depth maps and orthophotos generated from the point clouds as input to segmentation.…”
Section: B Methodsmentioning
confidence: 99%
“…This paper builds upon a series of incremental previous works on 3D surface segmentation and classification [12]- [14] and intends to consolidate and extend the achieved results. Our contribution beyond previous research are as follows:…”
Abstract-The development of powerful 3D scanning hardware and reconstruction algorithms has strongly promoted the generation of 3D surface reconstructions in different domains. An area of special interest for such 3D reconstructions is the cultural heritage domain, where surface reconstructions are generated to digitally preserve historical artifacts. While reconstruction quality nowadays is sufficient in many cases, the robust analysis (e.g. segmentation, matching, and classification) of reconstructed 3D data is still an open topic. In this paper, we target the automatic and interactive segmentation of high-resolution 3D surface reconstructions from the archaeological domain. To foster research in this field, we introduce a fully annotated and publicly available large-scale 3D surface dataset including high-resolution meshes, depth maps and point clouds as a novel benchmark dataset to the community. We provide baseline results for our existing random forest-based approach and for the first time investigate segmentation with convolutional neural networks (CNNs) on the data. Results show that both approaches have complementary strengths and weaknesses and that the provided dataset represents a challenge for future research.
“…Next, we enhance the depth map to extract and emphasize the fine geometric structures related to the peck-marks that make up petroglyph shapes with the method of Zeppelzauer & Seidl [21]. A classifier is trained on the enhanced map that generates probabilities for each pixel.…”
Section: D Segmentation Approachmentioning
confidence: 99%
“…3(b)). To enhance local structures of peck-marks we locally filter the deviation map by a Gaussian filter, see [21] for a detailed description. Locations where the filter matches well (e.g.…”
Section: A Data Preprocessing and Enhancementmentioning
Petroglyphs (rock engravings) are important artifacts for the documentation and analysis of early human life. Recent improvements in 3D scanning and 3D reconstruction enable the accurate 3D reconstruction of petroglyphs from rock surfaces at sub-millimeter resolution. To enable the indexing, matching, and recognition of petroglyphs in petroglyph databases, the shapes must first be segmented from the reconstructed rock surface. The absence of robust 3D segmentation methods for petroglyphs leaves a gap in the digital processing workflow. In this paper, we present a semi-automatic method for petroglyph segmentation for high-resolution 3D surface reconstructions. A comprehensive evaluation shows that our method is able to robustly segment petroglyphs with high accuracy and that the incorporation of 3D information is crucial to solve the segmentation problem. The presented method represents a major step towards the completion of a full 3D digital processing workflow of petroglyphs.
Methods to document rock art in all three dimensions have become a standardized workflow. In this article, we discuss their advantages and disadvantages when compared to older reductive approaches to rock art documentation. Furthermore, some misunderstandings regarding 3D documentation are addressed. As the majority of the problems presented by the 3D documentation of rock art can be solved through advanced visualization workflows, recent developments in this area are described. The rock art documentation described in this contribution also serves wider research purposes, which will be discussed. Newly discovered images and newly developed machine learning algorithms will also be introduced.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.