Random sample consensus

Согласие случайной выборки
Robert C. Bolles, Martin A. Fischler
1981-06-01

Location Determination ProblemRANSACautomated image analysisminimum-landmark solutionsrobust model fitting
A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing
1
Applies RANSAC to the Location Determination Problem: estimating the observer’s 3D position from an image of landmarks with known locations.
2
Derives new results for the minimum number of landmarks required to obtain a location solution and provides closed-form algorithms for computing such solutions.
3
Introduces Random Sample Consensus (RANSAC), a model-fitting paradigm designed to interpret and smooth data containing a significant percentage of gross errors.
4
RANSAC is particularly suited to automated image analysis because it can handle error-prone feature-detector outputs.
5
These results underpin an automatic system capable of solving the Location Determination Problem under difficult viewing conditions.

Random Sample Consensus (RANSAC) algorithm for model fitting and its application to the Location Determination Problem (LDP)

Robust model fitting and location determination in the presence of a significant proportion of gross errors, including minimum-landmark requirements and closed-form solution algorithms

Publication Details
Publication Date
1981-06-01
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Robert C. Bolles
Martin A. Fischler
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%