A non-parametric method based on neural networks and particle filtering for camera lens distortion estimation

Official URL: https://dx.doi.org/10.1109/CAMSAP66162.2025.11423981

A non-parametric method is introduced to estimate the measurement model of dynamical systems. The method uses a neural network trained in an unsupervised manner integrated into a particle filter framework. The network learns the measurement likelihood directly from the distribution of particles. The performance of the resulting neural network particle filter is first evaluated on synthetic data with a known measurement model showing a very interesting performance. The particle filter is then applied to sensor calibration with a specific focus on camera distortion estimation. Experimental results show that the method provides a reliable alternative to traditional parametric calibration techniques.