PROBE-GK: Predictive robust estimation using generalized kernels

Many algorithms in computer vision and robotics make strong assumptions about uncertainty, and rely on the validity of these assumptions to produce accurate and consistent state estimates. In practice, dynamic environments may degrade sensor performance in predictable ways that cannot be captured with static uncertainty parameters. In this paper, we employ fast nonparametric Bayesian inference techniques to more accurately model sensor uncertainty. By setting a prior on observation uncertainty, we derive a predictive robust estimator, and show how our model can be learned from sample images, both with and without knowledge of the motion used to generate the data. We validate our approach through Monte Carlo simulations, and report significant improvements in localization accuracy relative to a fixed noise model in several settings, including on synthetic data, the KITTI dataset, and our own experimental platform.

Authors

• Valentin Peretroukhin
• William Vega-Brown
• Nicholas Roy
• Jonathan Kelly

Keywords

• Predictive models
• Robustness
• Visualization
• Optimization
• Transforms
• Cameras
• Estimation
• Monte Carlo Simulation
• Noise Model
• Computer Vision Algorithms
• KITTI Dataset
• Prediction Model
• Additive Noise
• Points In Space
• Image Pairs
• Nonlinear Programming
• Nonlinear Least Squares
• Least Squares Problem
• Noise Covariance
• Sequence Of Observations
• Random Sample Consensus
• Motion Blur
• Camera Pose
• Stereo Camera
• Ground Truth Information
• Reprojection Error
• Visual Odometry
• Inverse Wishart Distribution
• True Covariance
• Nonlinear Least Squares Problem
• Homogeneous Coordinates
• Test Trials
• Optimization Problem
• Covariance Matrix
• Nonlinear Optimization Problem
• Training Data
• Stereo Images