Rejecting Outliers in 2D-3D Point Correspondences from 2D Forward-Looking Sonar Observations

2025-03-20

AI Summary

This paper addresses the failure of pose estimation in underwater 2D forward-looking sonar (2D FLS) due to an extremely high outlier ratio—up to 90%—in 2D–3D point correspondences. To tackle this, we propose a robust outlier rejection method leveraging the narrow elevation field-of-view of FLS. We introduce, for the first time, a pairwise length-range test and a four-point coplanarity compatibility test, applicable to both general and coplanar scenarios. A compatibility graph model is constructed, where maximal clique search enables generic, task-agnostic inlier identification without requiring scene-specific priors. Our method significantly improves inlier recall under severe outlier contamination: it reliably identifies high-quality correspondences even at 80% and 90% outlier ratios, thereby substantially increasing the success rate of subsequent pose estimation.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Rejecting outliers before applying classical robust methods is a common approach to increase the success rate of estimation, particularly when the outlier ratio is extremely high (e.g. 90%). However, this method often relies on sensor- or task-specific characteristics, which may not be easily transferable across different scenarios. In this paper, we focus on the problem of rejecting 2D-3D point correspondence outliers from 2D forward-looking sonar (2D FLS) observations, which is one of the most popular perception device in the underwater field but has a significantly different imaging mechanism compared to widely used perspective cameras and LiDAR. We fully leverage the narrow field of view in the elevation of 2D FLS and develop two compatibility tests for different 3D point configurations: (1) In general cases, we design a pairwise length in-range test to filter out overly long or short edges formed from point sets; (2) In coplanar cases, we design a coplanarity test to check if any four correspondences are compatible under a coplanar setting. Both tests are integrated into outlier rejection pipelines, where they are followed by maximum clique searching to identify the largest consistent measurement set as inliers. Extensive simulations demonstrate that the proposed methods for general and coplanar cases perform effectively under outlier ratios of 80% and 90%, respectively.

Problem

• Rejecting 2D-3D point correspondence outliers in 2D forward-looking sonar observations.
• Developing compatibility tests for general and coplanar 3D point configurations.
• Enhancing outlier rejection under high outlier ratios (80%-90%).

Innovation

• Pairwise length in-range test for general cases
• Coplanarity test for coplanar point configurations
• Maximum clique searching for consistent inlier identification