Robust Camera Pose Estimation via Consensus on Ray Bundle and Vector Field

Estimating the camera pose requires point correspondences. However, in practice, correspondences are inevitably corrupted by outliers, which affects the pose estimation. We propose a general and accurate outlier removal strategy for robust camera pose estimation. The proposed strategy can detect outliers by leveraging the fact that only inliers comply with two effective consensuses, i. e. , 3D ray bundle consensus and 2D vector field consensus. Our strategy has a nested structure. First, the outer module utilizes the 3D ray bundle consensus. We define the likelihood based on the probabilistic mixture model and maximize it by the expectation-maximization (EM) algorithm. The inlier probability of each correspondence and the camera pose are determined alternately. Second, the inner module exploits the 2D vector field consensus to refine the probabilities obtained by the outer module. The refinement based on the Bayesian rule facilitates the convergence of the outer module and improves the accuracy of the entire framework. Our strategy can be integrated into various existing camera pose estimation methods which are originally vulnerable to outliers. Experiments on both synthesized data and real images have shown that our approach outperforms state-of-the-art outlier rejection methods in terms of accuracy and robustness.

Authors

• Haoang Li
• Ji Zhao 0001
• Jean-Charles Bazin
• Lei Luo
• Junlin Wu
• Jian Yao 0002

Keywords

• Cameras
• Pose estimation
• Two dimensional displays
• Three-dimensional displays
• Robot vision systems
• Robustness
• Probabilistic logic
• Vector Field
• Camera Pose
• Camera Pose Estimation
• Ray Bundle
• Mixture Model
• Expectation Maximization
• General Strategy
• Estimation Strategy
• Corresponding Points
• Pose Estimation Methods
• Outlier Rejection
• Bayesian Rule
• 2D Vector
• Normal Distribution
• Uniform Distribution
• Latent Variables
• Linear System
• 3D Point
• Null Space
• Simultaneous Localization And Mapping
• 2D Point
• Breakdown Point
• Reprojection Error
• Structure From Motion
• Query Image
• Probability Matrix
• World Frame
• Intrinsic Matrix
• Regular Trend