A Mechanism for Range Image Integration without Image Registration

Zagorchev, Lyubomir

doi:10.1109/3dim.2005.10

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, p n } were randomly generated with uniform distribution within 3D space [10,20] × [10,20] × [10,20]. These points were then subjected to a rotation angle from 4 • to 66 • at intervals of 2 • around a fixed rotation axis h, subject to normalisation, randomly generated with uniform distribution within 3D space [1,3] followed by a constant translation vector t randomly generated with uniform distribution within 3D space [10,20] × [10,20] × [10,20]. Let the transformed points be P = {p 1 , p 2 , .…”

Section: Synthetic Data With Sparse Pointsmentioning

confidence: 99%

“…All these approaches have their own advantages and disadvantages and can succeed in one situation, but degrade catastrophically in another. Since feature extraction and matching approaches are susceptible to outliers and common ambiguities [17] and the establishment of possible correspondences and the camera motion parameter estimation from these possible correspondences are often interwoven [9], image registration still remains a major hurdle in 3D data acquisition [20].…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

A mean field annealing approach to accurate free form shape matching

Liu

2007

Pattern Recognition

View full text Add to dashboard Cite

Section: Synthetic Data With Sparse Pointsmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

A mean field annealing approach to accurate free form shape matching

Liu

2007

Pattern Recognition

View full text Add to dashboard Cite

“…Iterative camera motion search requires prior knowledge about range and desired accuracy of the camera motion parameters and is usually computationally intensive. Consequently, automatic range image matching still remains a major hurdle in 3D data acquisition (Zagorchev and Goshtasby 2005).…”

Section: Previous Workmentioning

confidence: 99%

Replicator Dynamics in the Iterative Process for Accurate Range Image Matching

Liu

2009

Int J Comput Vis

View full text Add to dashboard Cite

Iterative algorithms are often used for range image matching. In this paper, we treat the iterative process of range image matching as a live biological system: evolving from one generation to another. Whilst different generations of the population are regarded as range images captured at different viewpoints, the iterative process is simulated using time. The well-known replicator equations in theoretical biology are then adapted to estimate the probabilities of possible correspondences established using the traditional closest point criterion. To reduce the effect of image resolutions on the final results for efficient and robust overlapping range image matching, the relative fitness difference (rather than the absolute fitness difference) is employed in the replicator equations in order to model the probability change of possible correspondences being real over successive iterations. The fitness of a possible correspondence is defined as the negative of a power of its squared Euclidean distance. While the replicator dynamics penalize those individuals with low fitness, they are further penalised with a parameter, since distant points are often unlikely to represent their real replicators. While the replicator equations assume that all individuals are equally likely to meet each other and thus treat them equally, we penalise those individuals competing for the same points as their possible replicators. The estimated probabilities of possible correspondences being real are finally embedded into the powerful deterministic annealing scheme for global optimization, resulting in the camera motion parameters being estimated in the weighted least squares sense. A comparative study based on real range Y. Liu ( ) Department of Computer Science, Aberystwyth University, Ceredigion SY23 3DB, Wales, UK e-mail: yyl@aber.ac.uk images with partial overlap has shown that the proposed algorithm is promising for automatic matching of overlapping range images.

show abstract

A Mechanism for Range Image Integration without Image Registration

Cited by 2 publications

References 19 publications

A mean field annealing approach to accurate free form shape matching

A mean field annealing approach to accurate free form shape matching

Replicator Dynamics in the Iterative Process for Accurate Range Image Matching

Contact Info

Product

Resources

About