A Novel Hierarchical Technique for Range Segmentation of Large Building Exteriors

Hesami, Reyhaneh; Bab–Hadiashar, Alireza; Hosseinnezhad, Reza

doi:10.1007/978-3-540-76856-2_8

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ground-truth matching points were perturbed by random noise assumed to be normally distributed N 0, s 2 n and the residual for segmentation, in terms of Sampson distances d 2 i , was calculated for all points using the true F a in (7). The segmentation was performed using the modified selective statistical estimator (MSSE) [38] because of its desired performance in terms of consistency [29] and it has been shown to be successful in segmenting closely-spaced structures [30,31]. It is important to note that, although we use MSSE in our experiments, the analysis is general and similar results would be obtained if other robust estimators are used.…”

Section: Methodsmentioning

confidence: 99%

“…The analysis aims to determine the smallest amount of relative motion that can be detected by a robust estimator. In addition, any cost function of a robust estimator for a given structure is dismissive of the influence of the other structures in a dataset [29][30][31] and the effect is higher when the structures are close together, that is, small differences between the values of the cost function associated with each structure. Thus, for multiple-motion scenarios, the separability conditions derive here are also applicable.…”

Section: Segmentation Of Motions With Affine Fundamental Matrixmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of planar‐motion segmentation using affine fundamental matrix

Basah

Bab–Hadiashar

Hoseinnezhad

2014

IET Computer Vision

View full text Add to dashboard Cite

Various computer-vision applications involve estimation of multiple motions from images of dynamic scenes. The exact nature of 3D-object motions and the camera parameters are often not known a priori and therefore, the most general motion model (fundamental matrix) is applied. Although the estimation of fundamental matrix and its use for motion segmentation are established, the conditions for segmentation of different types of motions are largely unaddressed. In this study, we analysed the feasibility of motion segmentation using affine-fundamental matrix, focusing on a scene includes multiple planar-motions, viewed by an uncalibrated camera. We show that the successful segmentation of planar motion depends on several scene and motion parameters. Conditions to guarantee successful segmentation are proposed via extensive experiments using synthetic images. Experiments using real-image data were set up to examine the relevance of those conditions to the scenarios in real applications. The experimental results demonstrate the capability of the proposed conditions to correctly predict the outcome of several segmentation scenarios and show the relevance of those conditions in real applications. In practice, the success of motion segmentation could be predicted from obtainable scene and motion parameters. Therefore these conditions serve as a guideline for practitioners in designing motion-segmentation solutions.

show abstract