A RANSAC-Based Approach to Model Fitting and Its Application to Finding Cylinders in Range Data

By R. Bolles, M. Fischler. 1981

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Survey on Structure from Motion (2017, methodology): “A relatively recent method studied in [59], which fuses an expectation maximization (EM) algorithm to estimate camera poses and a sampling technique (similar to RANSAC [9]) to identify erroneous matches, aims to disambiguate such instances.”
Computer Methods and Programs in Biomedicine (unknown): “The main innovation consists in the inclusion of the RANdom SAmple Consensus (RANSAC) [189] .”
Object Recognition in the Geometric Era: A Retrospective (2006, methodology): “In retrospect, given recent advances in video feature tracking, it would have been a much better strategy for planar object recognition to compute the plane-to-plane projective transformation using all the features in a consistent statistical optimization strategy such as RANSAC [12, 26].”
EFFICIENT HOUGH TRANSFORM FOR AUTOMATIC DETECTION OF CYLINDERS IN POINT CLOUDS (2005, methodology): “The methods belonging to the second category try to avoid these problems by processing raw point clouds using robust fitting methods like RANSAC (Fischler and Bolles, 1987, Chaperon and Goulette, 2001, Bolles and Fischler, 1981).”
Toward automated driving in cities using close-to-market sensors: An overview of the V-Charge Project (2013, methodology): “To initialize the system, we allow for more extensive data associations between the sparse map and the observed frame by using NP3P-fitting (the Non-Perspective 3-Point Problem) combined with RANSAC [20], followed by a linear NPnP step for refinement.”
From Point Clouds to Mesh Using Regression (2017, methodology): “At ﬁrst the 3D reconstruction process is initialized by tracking 2D feature points between consecutive images and estimating the camera pose between the current frame and the ﬁrst camera frame using the 5-point algorithm [18] embedded in a RANSAC [2] framework.”
Incremental smoothing and mapping (2008, methodology): “Almost all visual odometry work use the random sample consensus (RANSAC) algorithm [9] for robust model estimation, and are therefore susceptible to problems arising from nearly degenerate situations.”