A Generalization of CLAP from 3D Localization to Image Processing, A Connection With RANSAC & Hough Transforms
This incremental work provides a general tool for handling noise and uncertainty in various fields, building on a method previously used in RoboCup 2024.
The authors extended their CLAP algorithm from 2D localization to 3D localization and image stitching, demonstrating its robustness against outliers and connecting it to RANSAC and Hough transforms.
In previous work, we introduced a 2D localization algorithm called CLAP, Clustering to Localize Across $n$ Possibilities, which was used during our championship win in RoboCup 2024, an international autonomous humanoid soccer competition. CLAP is particularly recognized for its robustness against outliers, where clustering is employed to suppress noise and mitigate against erroneous feature matches. This clustering-based strategy provides an alternative to traditional outlier rejection schemes such as RANSAC, in which candidates are validated by reprojection error across all data points. In this paper, CLAP is extended to a more general framework beyond 2D localization, specifically to 3D localization and image stitching. We also show how CLAP, RANSAC, and Hough transforms are related. The generalization of CLAP is widely applicable to many different fields and can be a useful tool to deal with noise and uncertainty.