Planar 3D object detection by using the generalized Hough transform

The problem of estimating the pose of metallic objects with shiny surfaces is studied. A new application has been developed using state-of-the-art 3D object segmentation (euclidean clustering) and pose estimation (ICP) methods. We analyze the planar surfaces of the metallic objects in 3D laser scanner data. First we segment these planar objects using euclidean clustering based on surface normals. Thereafter to estimate the pose of these segmented objects we compute Fast Point Feature Histograms (FPFH) descriptors. Finally we use an ICP algorithm that computes the rigid transformation with Singular Value Decomposition(SVD). Two different round of experiments are conducted:-one for the clustering and the other one for the pose estimation. We present the experimental results and analysis along with the possible application scenario and future work.

show abstract

“…A Generalized Hough Transform based 3d object detection method has been proposed by N. Guil et. al [3].…”

Section: Related Workmentioning

confidence: 98%

“…We have collected the data using the hand held laser scanner ModelMaker D100 [3]. This can make scans with stripes of width 50,100 and 200 mm and provides better scans with glossy and highly changing contrast surfaces.…”

Section: Data Acquisitionmentioning

confidence: 99%

Segmentation and Pose Estimation of Planar Metallic Objects

Ali

Figueroa

2012

2012 Ninth Conference on Computer and Robot Vision

View full text Add to dashboard Cite

show abstract

“…Normally, the number of edge points in the template is lower than in the image, where several different shapes can appear. This makes the computational complexity of our method to be lower than other algorithms using the image shape [15].…”

Section: Table Generation and Comparisonmentioning

confidence: 99%

Planar Object Detection under Scaled Orthographic Projection

Cózar

Guil

Zapata

2000

Discrete Geometry for Computer Imagery

View full text Add to dashboard Cite

In this work a new method to detect objects under scaled orthographic projections is shown. It also calculates the parameters of the transformations the object has suffered. The method is based on the use of the Generalized Hough Transform (GHT) that compares a template with a projected image. The computational requirements of the algorithm are reduced by restricting the transformation to the template edge points and using invariant information during the comparison process. This information is obtained from a precomputed table of the template that is directly transformed and compared with the image table. Moreover, a multiresolution design of the algorithm speeds-up the parameters calculation.

show abstract

“…The works of Jeng and Tsai (1991) and Guil et al (1999) both propose a new approach where transformations are applied to the original R-Table, obtaining rotation and scale invariance. In Jeng and Tsai (1991) a new table called the SI-PSF is used that aids in scale and subsequently rotation invariance.…”

Section: Introductionmentioning

confidence: 99%

“…This method requires a high number of increments for each image point. In Guil et al (1999) the creation of five new tables and a three-stage detection process is disclosed. The scheme's complexity is high because image and template points are repeatedly tested using different tables to obtain invariant values.…”

Section: Introductionmentioning

confidence: 99%

A pose‐invariant approach for hypothesis support

Amador

2003

Int J Imaging Syst Tech

View full text Add to dashboard Cite

This article presents a tractable and empirically accurate algorithm realizing a midlevel visual process for pattern recognition. The algorithm takes advantage of hypotheses provided by a highlevel visual process, thereby, attempting to extract a region in an image based on these hypotheses. The main focus is to recognize quadrilateral as well as arbitrarily shaped objects from synthetic and real-world images. The novel approach is based on a study of the Hough Transform and its generalized version. To show overall usefulness of the algorithm, an extensive series of experiments was performed. In particular, occlusion and multiple object-instances were tested, indicating the effectiveness of this work's approach.

show abstract

Planar 3D object detection by using the generalized Hough transform

Cited by 6 publications

References 11 publications

Segmentation and Pose Estimation of Planar Metallic Objects

Segmentation and Pose Estimation of Planar Metallic Objects

Planar Object Detection under Scaled Orthographic Projection

A pose‐invariant approach for hypothesis support

Contact Info

Product

Resources

About