CVRONov 7, 2017

Hidden Markov Random Field Iterative Closest Point

arXiv:1711.05864v17 citations
Originality Incremental advance
AI Analysis

This work addresses point cloud registration for applications like structured light and stereo reconstruction, but it is incremental as it builds on existing iterative closest point methods with a specific prior model.

The paper tackles the problem of registering point clouds with low or moderate overlap by incorporating a hidden Markov random field model into the iterative closest point algorithm to handle outliers that occur together, such as along edges, and demonstrates that this method outperforms other outlier rejection methods in experiments.

When registering point clouds resolved from an underlying 2-D pixel structure, such as those resulting from structured light and flash LiDAR sensors, or stereo reconstruction, it is expected that some points in one cloud do not have corresponding points in the other cloud, and that these would occur together, such as along an edge of the depth map. In this work, a hidden Markov random field model is used to capture this prior within the framework of the iterative closest point algorithm. The EM algorithm is used to estimate the distribution parameters and the hidden component memberships. Experiments are presented demonstrating that this method outperforms several other outlier rejection methods when the point clouds have low or moderate overlap.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes