Efficient Partial Shape Matching of Outer Contours

Donoser, Michael; Riemenschneider, Hayko; Bischof, Horst

doi:10.1007/978-3-642-12307-8_26

Cited by 33 publications

(44 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and observe that Γ(i, j, l, k) can be computed efficiently by utilizing the integral image algorithm, since it allows to access any element in the 4D matrix in constant time [5,22]. Intuitively, when very few points are involved in a matching, the shape similarity is neither reliable nor discriminative enough.…”

Section: Partial Matching Between Edge Fragments and Model Contourmentioning

confidence: 99%

From partial shape matching through local deformation to robust global shape similarity for object detection

Latecki

2011

CVPR 2011

View full text Add to dashboard Cite

show abstract

Section: Partial Matching Between Edge Fragments and Model Contourmentioning

confidence: 99%

From partial shape matching through local deformation to robust global shape similarity for object detection

Latecki

2011

CVPR 2011

View full text Add to dashboard Cite

show abstract

“…For efficient shape matching we adapt a recently proposed method [7] for this purpose. This paper introduced a partial shape matching method which uses sampled contour points as underlying representation and solves an order preserving assignment problem.…”

Section: Frame-to-frame Segment Matchingmentioning

confidence: 99%

“…In [7] each shape with N sampled contour points is described by an N × N descriptor matrix containing angles between chords connecting the sampled points. The invariance of angles to translation and rotation leads to the aforementioned properties.…”

Section: Frame-to-frame Segment Matchingmentioning

confidence: 99%

“…To make the approach sensitive to rotation (which is desired in our scenario), one has to find a novel N × N descriptor. The rest of the method stays exactly the same (see [7] for details).…”

Section: Frame-to-frame Segment Matchingmentioning

confidence: 99%

“…For each segment these angles are calculated over all possible point combinations. The resulting descriptor matrix is non-symmetric, translation invariant and encodes the rotational orientation, which is strongly in contrast to the descriptor of [7]. Based on this descriptor, we can apply the same, highly efficient matching scheme with encoded orientation information.…”

Section: Frame-to-frame Segment Matchingmentioning

confidence: 99%

See 2 more Smart Citations

Highly Consistent Sequential Segmentation

et al. 2011

Self Cite

View full text Add to dashboard Cite

Abstract. This paper deals with segmentation of image sequences in an unsupervised manner with the goal of getting highly consistent segmentation results from frame-to-frame. We first introduce a segmentation method that uses results of the previous frame as initialization and significantly improves consistency in comparison to a single frame based approach. We also find correspondences between the segmented regions from one frame to the next to further increase consistency. This matching step is based on a modified version of an efficient partial shape matching method which allows identification of similar parts of regions despite topology changes like merges and splits. We use the identified matched parts to define a partial matching cost which is then used as input to pairwise graph matching. Experiments demonstrate that we can achieve highly consistent segmentations for diverse image sequences, even allowing to track manually initialized moving and static objects.

show abstract

Signature of Geometric Centroids for 3D Local Shape Description and Partial Shape Matching

Tang

Song

Chen

2017

Computer Vision – ACCV 2016

View full text Add to dashboard Cite

Abstract. Depth scans acquired from different views may contain nuisances such as noise, occlusion, and varying point density. We propose a novel Signature of Geometric Centroids descriptor, supporting direct shape matching on the scans, without requiring any preprocessing such as scan denoising or converting into a mesh. First, we construct the descriptor by voxelizing the local shape within a uniquely defined local reference frame and concatenating geometric centroid and point density features extracted from each voxel. Second, we compare two descriptors by employing only corresponding voxels that are both non-empty, thus supporting matching incomplete local shape such as those close to scan boundary. Third, we propose a descriptor saliency measure and compute it from a descriptor-graph to improve shape matching performance. We demonstrate the descriptor's robustness and effectiveness for shape matching by comparing it with three state-of-the-art descriptors, and applying it to object/scene reconstruction and 3D object recognition.

show abstract

Efficient Partial Shape Matching of Outer Contours

Cited by 33 publications

References 19 publications

From partial shape matching through local deformation to robust global shape similarity for object detection

From partial shape matching through local deformation to robust global shape similarity for object detection

Highly Consistent Sequential Segmentation

Signature of Geometric Centroids for 3D Local Shape Description and Partial Shape Matching

Contact Info

Product

Resources

About