Multi‐scale Feature Extraction on Point‐Sampled Surfaces

Pauly, Mark; Keiser, Richard; Groß, Markus

doi:10.1111/1467-8659.00675

Cited by 459 publications

(335 citation statements)

References 22 publications

Supporting

Mentioning

308

Contrasting

Unclassified

Order By: Relevance

“…Since the point cloud is obtained from a few consecutive frames (or a single frame) we can consider it to be from a single-view. We convert it into a curvature map, where each pixel stores the ratio r. Using hysteresis thresholding [18] we detect connected regions of high r. We perform non-maximal suppression on these regions to get the internal edges. Contours or external edges are regions where depth discontinuities are large.…”

Section: Edgelet Detectionmentioning

confidence: 99%

Robust Instance Recognition in Presence of Occlusion and Clutter

Bonde

Badrinarayanan

Cipolla

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. We present a robust learning based instance recognition framework from single view point clouds. Our framework is able to handle real-world instance recognition challenges, i.e, clutter, similar looking distractors and occlusion. Recent algorithms have separately tried to address the problem of clutter [9] and occlusion [16] but fail when these challenges are combined. In comparison we handle all challenges within a single framework. Our framework uses a soft label Random Forest [5] to learn discriminative shape features of an object and use them to classify both its location and pose. We propose a novel iterative training scheme for forests which maximizes the margin between classes to improve recognition accuracy, as compared to a conventional training procedure. The learnt forest outperforms template matching, DPM [7] in presence of similar looking distractors. Using occlusion information, computed from the depth data, the forest learns to emphasize the shape features from the visible regions thus making it robust to occlusion. We benchmark our system with the state-of-the-art recognition systems [9,7] in challenging scenes drawn from the largest publicly available dataset. To complement the lack of occlusion tests in this dataset, we introduce our Desk3D dataset and demonstrate that our algorithm outperforms other methods in all settings.

show abstract

Section: Edgelet Detectionmentioning

confidence: 99%

Robust Instance Recognition in Presence of Occlusion and Clutter

Bonde

Badrinarayanan

Cipolla

2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…Finally, we note that PCA on mesh vertices is equivalent to least square fitting of a plane, and thus, the method of choice for the local tangent plane estimation required in applications ranging from surface reconstruction (Hoppe et al, 1992) to feature detection (Pauly et al, 2003).…”

Section: Related Workmentioning

confidence: 99%

Mesh Alignment using Grid based PCA

Kaye¹,

Ivrissimtzis²

2015

Proceedings of the 10th International Conference on Computer Graphics Theory and Applications

View full text Add to dashboard Cite

The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. An algorithm is presented to align one mesh to another by means of a regular 3D grid upon which Principal Components Analysis (PCA) is performed. The use of a 3D lattice external to both inputs increases the robustness of PCA, particularly when dealing with meshes of different and possibly uneven vertex density. The proposed algorithm was tested on meshes that have undergone standard mesh processing operations such as smoothing, simplification and remeshing. In several cases the results indicate an improved robustness compared to performing PCA directly on mesh vertices.

show abstract

“…The structural features are detected and extracted following the idea of [8], [29] and [25] of identifying initial seed nodes and performing an edge-growing approach to connect related nodes. The seed nodes for a graph are represented by all points having a minimal type probability.…”

Section: Generating the Feature Graphmentioning

confidence: 99%

“…1(c) and 2c). Rather than using a minimal spanning graph as proposed by Pauly et al [29], this approach provides greater consistency between edges and feature directions.…”

Section: Edge Propagationmentioning

confidence: 99%

Extracting and Visualizing Structural Features in Environmental Point Cloud LiDaR Data Sets

Keller¹,

Kreylos²,

Vanco³

et al. 2010

Mathematics and Visualization

View full text Add to dashboard Cite

Abstract. We present a user-assisted approach to extracting and visualizing structural features from point clouds obtained by terrestrial and airborne laser scanning devices. We apply a multi-scale approach to express the membership of local point environments to corresponding geometric shape classes in terms of probability. This information is filtered and combined to establish feature graphs which can be visualized in combination with the color-encoded feature and structural probability estimates of the measured raw point data. Our method can be used, for example, for exploring geological point data scanned from multiple viewpoints.

show abstract

Multi‐scale Feature Extraction on Point‐Sampled Surfaces

Cited by 459 publications

References 22 publications

Robust Instance Recognition in Presence of Occlusion and Clutter

Robust Instance Recognition in Presence of Occlusion and Clutter

Mesh Alignment using Grid based PCA

Extracting and Visualizing Structural Features in Environmental Point Cloud LiDaR Data Sets

Contact Info

Product

Resources

About