Vanishing Point Detection by Segment Clustering on the Projective Space

Andaló, Fernanda A.; Taubin, Gabriel; Goldenstein, Siome

doi:10.1007/978-3-642-35740-4_25

Cited by 9 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regard to the number of detected VPs, these algorithms aim at estimating three estimate three orthogonal VPs, 4,5 or any present nonorthogonal VP. 3,6,7 Based on their estimation strategy, line classification algorithms are roughly divided into two categories; algorithms that specify accumulator spaces and those that perform the clustering directly on the image plane.…”

Section: Vanishing Point Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Vanishing point detection based on an artificial bee colony algorithm

Han

Fan

Zheng

et al. 2015

J. Electron. Imaging

View full text Add to dashboard Cite

Vanishing points (VPs) are crucial for inferring the three-dimensional structure of a scene and can be exploited in various computer vision applications. Previous VP detection algorithms have been proven effective but generally cannot guarantee a strong performance in both accuracy and computational time. We propose an artificial bee colony algorithm called dynamic clustering artificial bee colony (DCABC) that accurately and efficiently detects VPs in the image plane. The task is regarded as a dynamic line-clustering problem, and the line clusters are initialized by their orientation information. Inspired by the foraging behavior of bees, DCABC selects the clustering center and reclassifies the line segments based on a distance criterion until the terminating condition is met. The optimal line clusters determine the estimated VP. The dissimilarity among solutions is measured by the Hamming distance between two binary vectors, which simplifies the new solution construction. The performances of the proposed and existing algorithms are evaluated on the York Urban database. The results verify the efficiency and accuracy of our proposed algorithm.

show abstract

Section: Vanishing Point Detectionmentioning

confidence: 99%

“…In the latter category, the workspace is the actual image plane. 6,9 Line clustering is generally decided by computations, such as the distances among points and lines. Typical computational methods are random sample consensus (RANSAC) and its variants (such as multi-RANSAC and J-Linkage).…”

Section: Vanishing Point Detectionmentioning

confidence: 99%

Vanishing point detection based on an artificial bee colony algorithm

Han

Fan

Zheng

et al. 2015

J. Electron. Imaging

View full text Add to dashboard Cite

show abstract

“…The number n is an overestimation of the number of trials needed to obtain a certain number of "good" models [13,31,37]. Then, we compute the CS of each model hypothesis using Equation (4). Let U be the set of all these consensus sets.…”

Section: Introductionmentioning

confidence: 99%

“…. n} do 3 Select at random a minimal sample set (MSS) X mms(j) of size b from X ; 4 Estimate θ j from X mms(j) by solving (∀x ∈ X mms(j) ) f µ (x; θ) = 0; 5 U ← {C µ (X , θ j , δ)} n j=1 , see Equation (4); algorithm that introduced this framework, detects a single model by taking the CS from U with the largest size, and uses it to estimate θ from C as in Equation (5).…”

Section: Introductionmentioning

confidence: 99%

Fast L1-NMF for Multiple Parametric Model Estimation

Tepper,

Sapiro

2016

Preprint

View full text Add to dashboard Cite

In this work we introduce a comprehensive algorithmic pipeline for multiple parametric model estimation. The proposed approach analyzes the information produced by a random sampling algorithm (e.g., RANSAC) from a machine learning/optimization perspective, using a parameterless biclustering algorithm based on L1 nonnegative matrix factorization (L1-NMF). The proposed framework exploits consistent patterns that naturally arise during the RANSAC execution, while explicitly avoiding spurious inconsistencies. Contrarily to the main trends in the literature, the proposed technique does not impose non-intersecting parametric models. A new accelerated algorithm to compute L1-NMFs allows to handle medium-sized problems faster while also extending the usability of the algorithm to much larger datasets. This accelerated algorithm has applications in any other context where an L1-NMF is needed, beyond the biclustering approach to parameter estimation here addressed. We accompany the algorithmic presentation with theoretical foundations and numerous and diverse examples.

show abstract

“…Briefly, these techniques typically introduce computationally expensive algorithms or they suffer robustness. Although vanishing points and their roles in plane detection of two-dimensional (2-D)/3-D color images have been indicated in the literature, 17,18 it is almost impossible to utilize them for depth images due to the following reasons. First of all, it is required to cover a relatively large area in an image to detect vanishing points, which is not the case for depth images targeted in this paper (e.g., urban scenes versus the Kinect indoor depth images).…”

Section: Introductionmentioning

confidence: 99%