Scale Selection for the Analysis of Point-Sampled Curves

Unnikrishnan, R.; Lalonde, Jean‐François; Vandapel, Nicolas; Hebert, Martial

doi:10.1109/3dpvt.2006.123

Cited by 17 publications

(16 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During a supervised learning phase, different types of local descriptors, depending upon their distinctiveness for a particular class of objects, are transformed to form a CDD which is used for object retrieval. Unnikrishnan et al [34] estimate the scale, for a point sampled curve, as a neighbourhood for which the principal eigenvector of the points is best aligned with the tangent of the curve in an iterative procedure. This idea has been extended to point clouds for identifying multi-scale interest regions [35] where the mean curvature is used to identify scale-space extrema.…”

Section: Related Workmentioning

confidence: 99%

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

2009

View full text Add to dashboard Cite

3D object recognition from local features is robust to occlusions and clutter. However, local features must be extracted from a small set of feature rich keypoints to avoid computational complexity and ambiguous features. We present an algorithm for the detection of such keypoints on 3D models and partial views of objects. The keypoints are highly repeatable between partial views of an object and its complete 3D model. We also propose a quality measure to rank the keypoints and select the best ones for extracting local features. Keypoints are identified at locations where a unique local 3D coordinate basis can be derived from the underlying surface in order to extract invariant features. We also propose an automatic scale selection technique for extracting multi-scale and scale invariant features to match objects at different unknown scales. Features are projected to a PCA subspace and matched to find correspondences between a database and query object. Each pair of matching features gives a transformation that aligns the query and database object. These transformations are clustered and the biggest cluster is used to identify the query object. Experiments on a public database revealed that the proposed quality measure relates correctly to the repeatability of keypoints and the multi-scale features have a recognition rate of over 95% for up to 80% occluded objects.

show abstract

Section: Related Workmentioning

confidence: 99%

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

2009

View full text Add to dashboard Cite

show abstract

“…Examples of such descriptors include curvature-based quantities [9], [18], [5], shape index [4], integral volume descriptor [7], [11]. These descriptors are computed around a small neighborhood.…”

Section: Related Workmentioning

confidence: 99%

“…We are particularly interested in low-dimensional geometric descriptors, such as curvature and various curvature-based quantities [9], [18], [5], [7]. These descriptors measure how gently or strongly curved a surface is around a point.…”

Section: Raw Point Clouds and Local Surface Descriptorsmentioning

confidence: 99%

Pairwise region-based scan alignment

Rocha

Druon

Crosnier

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-In this paper, we present a new algorithm for the alignment of two 3D scans. The approach uses a region-based matching technique. We make no assumptions about the initial positions of the scans. Regions are described by a probability density function (pdf) computed from low dimensional surface descriptors (curvature or normal cone). The algorithm allows registering directly raw noisy data, possibly with the presence of outliers, without any pre-processing, such as filtering, denoising, or reconstruction. Region correspondence is found using similarity function based on the comparison of regions pdf and under geometry constraints. Results on raw scan data sets are presented to illustrate and evaluate the algorithm.

show abstract

“…However, the estimation of both these quantities is errorprone. Estimation of differential quantities like surface normals and tangents is difficult in the presence of noise even for relatively smooth surfaces [7,10], and is of course not even well-defined at intersections.…”

Section: Related Workmentioning

confidence: 99%

“…One strategy to identify points that have a large influence on the estimated model parameters, such as using eigenvector perturbation bounds [10] for the generalized eigenvalue problem (12) or using influence functions. In our experiments, we use a simple greedy strategy of evaluating leave-one-out fitting score and ignoring the point as an outlier if it is not a good fit with its neighbors.…”

Section: Algorithm and Implementationmentioning

confidence: 99%

Denoising Manifold and Non-Manifold Point Clouds

Unnikrishnan

Hebert

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

The faithful reconstruction of 3-D models from irregular and noisy point samples is a task central to many applications of computer vision and graphics. We present an approach to denoising that naturally handles intersections of manifolds, thus preserving high-frequency details without oversmoothing. This is accomplished through the use of a modified locally weighted regression algorithm that models a neighborhood of points as an implicit product of linear subspaces. By posing the problem as one of energy minimization subject to constraints on the coefficients of a higher order polynomial, we can also incorporate anisotropic error models appropriate for data acquired with a range sensor. We demonstrate the effectiveness of our approach through some preliminary results in denoising synthetic data in 2-D and 3-D domains. *

show abstract

Scale Selection for the Analysis of Point-Sampled Curves

Cited by 17 publications

References 8 publications

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

Pairwise region-based scan alignment

Denoising Manifold and Non-Manifold Point Clouds

Contact Info

Product

Resources

About