Comparing curved-surface range image segmenters

Powell, Mark W.; Bowyer, Kevin W.; Jiang, Xiaoyi; Bunke, Horst

doi:10.1109/iccv.1998.710732

Cited by 43 publications

(45 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The range image sets reported in [5,13] have become popular for evaluating range image segmentation algorithms. Totally, three image sets with manually specified ground truth are available: ABW and Perceptron for planar surfaces and K2T for curved surfaces.…”

Section: Validation On Synthetic Datamentioning

confidence: 99%

See 1 more Smart Citation

Image Segmentation Evaluation by Techniques of Comparing Clusterings

Jiang

Marti

Irniger

et al. 2005

Image Analysis and Processing – ICIAP 2005

View full text Add to dashboard Cite

Abstract. The task considered in this paper is performance evaluation of region segmentation algorithms in the ground truth (GT) based paradigm. Given a machine segmentation and a GT reference, performance measures are needed. We propose to consider the image segmentation problem as one of data clustering and, as a consequence, to use measures for comparing clusterings developed in statistics and machine learning. By doing so, we obtain a variety of performance measures which have not been used before in computer vision. In particular, some of these measures have the highly desired property of being a metric. Experimental results are reported on both synthetic and real data to validate the measures and compare them with others.

show abstract

Section: Validation On Synthetic Datamentioning

confidence: 99%

“…These measures are based on the degree of mutual overlap required between a region in MS and a region in GT, and are controlled by a threshold T . This evaluation method is widely used for texture segmentation [2] and range image segmentation [5,7,8,12,13].…”

Section: Related Workmentioning

confidence: 99%

Image Segmentation Evaluation by Techniques of Comparing Clusterings

Jiang

Marti

Irniger

et al. 2005

Image Analysis and Processing – ICIAP 2005

View full text Add to dashboard Cite

show abstract

“…The literature of range image segmentation is vast and comprises works that deal with comparisons among different algorithms (see [28,30,42]). Besides segmentation into parts using geometric characterizations, we are also interested in recovering primitives [10,23,33,41,57] as well as in analyzing the interconnections among the parts [19].…”

Section: Low-level Processing-3d Segmentationmentioning

confidence: 99%

Efficient search and verification for function based classification from real range images

Rivlin

Shimshoni

Soldea

2007

Computer Vision and Image Understanding

View full text Add to dashboard Cite

In this work we propose a probabilistic model for generic object classification from raw range images. Our approach supports a validation process in which classes are verified using a functional class graph in which functional parts and their realization hypotheses are explored. The validation tree is efficiently searched. Some functional requirements are validated in a final procedure for more efficient separation of objects from non-objects. The search employs a knowledge repository mechanism that monotonically adds knowledge during the search and speeds up the classification process. Finally, we describe our implementation and present results of experiments on a database that comprises about 150 real raw range images of object instances from 10 classes.

show abstract

“…Comparisons of B. Dellen is with the RheinAhrCampus der Hochschule Koblenz, JosephRovan-Allee 2, 53424 Remagen, Germany, (email: dellen@hs-koblenz.de). different range image segmentation algorithms can be found in [9], [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Consistent Depth Video Segmentation Using Adaptive Surface Models

Husain

Dellen

Torras

2015

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Abstract-We propose a new approach for the segmentation of 3-D point clouds into geometric surfaces using adaptive surface models. Starting from an initial configuration, the algorithm converges to a stable segmentation through a new iterative splitand-merge procedure, which includes an adaptive mechanism for the creation and removal of segments. This allows the segmentation to adjust to changing input data along the movie, leading to stable, temporally coherent, and traceable segments. We tested the method on a large variety of data acquired with different range imaging devices, including a structured-light sensor and a time-of-flight camera, and successfully segmented the videos into surface segments. We further demonstrated the feasibility of the approach using quantitative evaluations based on ground-truth data.

show abstract

Comparing curved-surface range image segmenters

Cited by 43 publications

References 10 publications

Image Segmentation Evaluation by Techniques of Comparing Clusterings

Image Segmentation Evaluation by Techniques of Comparing Clusterings

Efficient search and verification for function based classification from real range images

Consistent Depth Video Segmentation Using Adaptive Surface Models

Contact Info

Product

Resources

About