Direct Inverse Randomized Hough Transform for Incomplete Ellipse Detection in Noisy Images

Lu, Wei; Yu, Jinhua; Tan, Jinglu

doi:10.13176/11.512

Cited by 7 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Hough transform may be generalized to detect groups of points belonging to a curve, but this increases the complexity of the algorithm whether the defining function has too many independent variables (such as for ellipses). A modification of Hough transform for circles and ellipses detection has been well studied [18][19][20][21], as well as some methods reducing the complexity of the Hough transform for ellipses in unknown environments have been developed [22], [23]. In this context, VILEMEM proposes a simple and efficient method that transforms the original image to a circumference, reducing the computational effort.…”

Section: The Lmm Bottom Identificationmentioning

confidence: 99%

Measuring Fluid Level through a Recalibrating-Free Hough Transform Methodology

Flores¹,

Lima²,

Thome³

et al. 2015

computer

View full text Add to dashboard Cite

Fluid level monitoring is an important control process in engineering systems. The level measurement of fluids having changeable densities is a complex task. Most measurement methodologies use sensors that are periodically paused for recalibrations. For flammable liquids, this may be unsafe and even dangerous. This paper proposes a safe recalibrating-free computer-based methodology for measurement of fluid levels, which is based on Hough transform, image processing and normalization. This paper also describes experiments using a prototype of a distillation unit that was built especially to test the proposed methodology. The results from these experiments have demonstrated robustness, low-cost and suitability of the methodology for real crude oil level measurement in distillation processes.

show abstract

Section: The Lmm Bottom Identificationmentioning

confidence: 99%

Measuring Fluid Level through a Recalibrating-Free Hough Transform Methodology

Flores¹,

Lima²,

Thome³

et al. 2015

computer

View full text Add to dashboard Cite

show abstract

“…In the following, we show that the usual method of center accumulation is well described within the framework of the the dual equation. We also show that the set of parameters of the direct equation of the framework was introduced in [10] for fitting applications (see [11], [12]), but has never been used explicitly in the accumulation process of the EHT. This direct form accumulates a pair of parameters, which are equivalent to the eccentricity and orientation of the ellipse.…”

Section: Introductionmentioning

confidence: 99%

Dual Approaches for Elliptic Hough Transform: Eccentricity/Orientation vs Center Based

Latour

Droogenbroeck

2019

Discrete Geometry for Computer Imagery

View full text Add to dashboard Cite

Ellipse matching is the process of extracting (detecting and fitting) elliptic shapes from digital images. It appears that it requires the determination of typically five parameters, which can be determined by using an Elliptic Hough Transform (EHT) algorithms.In this paper, we focus on Elliptic Hough Transform (EHT) algorithms based on two edge points and their associated image gradients. For this scenario, authors first reduce the dimension of the 5D EHT by means of some geometrical observations, and then apply a simpler HT. We present an alternative approach, more specifically an algebraic framework, based on the pencil of bi-tangent conics, expressed in two dual forms: the point or the tangential forms. It appears that, for both forms, the locus of the ellipse parameters is a line in a 5D space.With this framework, we can split the EHT into two steps. The first step accumulates 2D lines, which are computed from planar projections of the parameter locus (5D line). The second part backprojects the peak of the 2D accumulator into the 5D space, to obtain the three remaining parameters that we then accumulate in a 3D histogram, possibly represented as three separated 1D-histograms.For the point equation, the first step extracts parameters related to the ellipse orientation and eccentricity, while the remaining parameters are related to the center and a sizing parameter of the ellipse. For the tangential equation, the first process is the known center extraction algorithm, while the remaining parameters are related to the ellipse half-axes and orientation.

show abstract

“…However, it is time-consuming owing to low calculation efficiency and computation complexity. As a result, much work has been done to improve the Hough transform method, such as Generalized Hough Transform, Probabilistic Hough Transform, Randomized Hough Transform (RHT) and Digital Hough Transform [36,37]. Nevertheless, these improved algorithms are still not satisfactory for the rapid processing of high-speed videogrammetric measurements.…”

Section: Introductionmentioning

confidence: 99%

Tri-Camera High-Speed Videogrammetry for Three-Dimensional Measurement of Laminated Rubber Bearings Based on the Large-Scale Shaking Table

et al. 2018

View full text Add to dashboard Cite

Laminated rubber bearings are widely used for the mitigation of seismic damage of large-scale structures and equipment. However, owing to the flexibility in horizontal direction, the traditional contacted transducer is difficult to acquire the displacement data accurately in the three directions, respectively. In this paper, three-dimensional displacement measurement of laminated rubber bearing based on the large-scale shaking table is achieved by the use of a tri-camera high-speed videogrammetric system consisting of three complementary-metal-oxide-semiconductor (CMOS) cameras, one synchronous controller, and one pair of 1000 watt light sources, which are used to simultaneously acquire the tri-camera image sequences of laminated rubber bearing at a speed of 300 frames per second (fps). Firstly, this paper proposes a fast image block technique for detecting and tracking targets in tri-camera image sequences by integration of techniques morphological edge detection, attribute based ellipse extraction and least-squares-based fitting adjustment. Secondly, this paper presents an integrated bundle adjustment approach, which brings continuous tracking points into one collinearity condition equation, to reconstruct the three dimensional coordinates of continuous tracking points, for the purpose of improving the accuracy of three-dimensional coordinates of tracking points based on tri-camera image sequences. At last, an empirical experiment was conducted to measure the three-dimensional displacement of laminated rubber bearings on the shaking table by the use of the proposed method. The experimental results showed that the proposed method could obtain three-dimensional displacement of laminated rubber bearings with an accuracy of more than 0.5 mm.

show abstract

Direct Inverse Randomized Hough Transform for Incomplete Ellipse Detection in Noisy Images

Cited by 7 publications

References 0 publications

Measuring Fluid Level through a Recalibrating-Free Hough Transform Methodology

Measuring Fluid Level through a Recalibrating-Free Hough Transform Methodology

Dual Approaches for Elliptic Hough Transform: Eccentricity/Orientation vs Center Based

Tri-Camera High-Speed Videogrammetry for Three-Dimensional Measurement of Laminated Rubber Bearings Based on the Large-Scale Shaking Table

Contact Info

Product

Resources

About