Scalable Symmetry Detection for Urban Scenes
| dc.contributor.author | Kerber, J. | en_US |
| dc.contributor.author | Bokeloh, M. | en_US |
| dc.contributor.author | Wand, M. | en_US |
| dc.contributor.author | Seidel, H.-P. | en_US |
| dc.contributor.editor | Holly Rushmeier and Oliver Deussen | en_US |
| dc.date.accessioned | 2015-02-28T15:16:44Z | |
| dc.date.available | 2015-02-28T15:16:44Z | |
| dc.date.issued | 2013 | en_US |
| dc.description.abstract | In this paper, we present a novel method for detecting partial symmetries in very large point clouds of 3D city scans. Unlike previous work, which has only been demonstrated on data sets of a few hundred megabytes maximum, our method scales to very large scenes: We map the detection problem to a nearest-eighbour problem in a low-dimensional feature space, and follow this with a cascade of tests for geometric clustering of potential matches. Our algorithm robustly handles noisy real-world scanner data, obtaining a recognition performance comparable to that of state-of-the-art methods. In practice, it scales linearly with scene size and achieves a high absolute throughput, processing half a terabyte of scanner data overnight on a dual socket commodity PC.In this paper we present a novel method for detecting partial symmetries in very large point clouds of 3D city scans. Unlike previous work, which has only been demonstrated on data sets of a few hundred megabytes maximum, our method scales to very large scenes: We map the detection problem to a nearest-eighbor problem in a lowdimensional feature space, and follow this with a cascade of tests for geometric clustering of potential matches. Our algorithm robustly handles noisy real-world scanner data, obtaining a recognition performance comparable to that of state-of-the-art methods. In practice, it scales linearly with scene size and achieves a high absolute throughput, processing half a terabyte of scanner data overnight on a dual socket commodity PC. | en_US |
| dc.description.number | 1 | |
| dc.description.seriesinformation | Computer Graphics Forum | en_US |
| dc.description.volume | 32 | |
| dc.identifier.issn | 1467-8659 | en_US |
| dc.identifier.uri | https://doi.org/10.1111/j.1467-8659.2012.03226.x | en_US |
| dc.publisher | The Eurographics Association and Blackwell Publishing Ltd. | en_US |
| dc.subject | I.4.8 [IMAGE PROCESSING AND COMPUTER VISION] | en_US |
| dc.subject | Scene Analysis | en_US |
| dc.subject | Shape | en_US |
| dc.subject | I.3.5 [COMPUTER GRAPHICS] | en_US |
| dc.subject | Computational Geometry and Object Modeling | en_US |
| dc.subject | Hierarchy and geometric transformations | en_US |
| dc.subject | I.5.3 [PATTERN RECOGNITION] | en_US |
| dc.subject | Clustering | en_US |
| dc.subject | Similarity measures | en_US |
| dc.subject | symmetry detection | en_US |
| dc.subject | feature detection | en_US |
| dc.subject | large scene processing | en_US |
| dc.subject | clustering | en_US |
| dc.title | Scalable Symmetry Detection for Urban Scenes | en_US |