Handling Missing Observations with an RNN-based Prediction-Update Cycle
This addresses a domain-specific issue in tracking applications where missing data is common, offering an incremental improvement over existing RNN methods.
The paper tackles the problem of missing observations in time-series data for tasks like tracking by introducing an RNN-based prediction-update cycle inspired by Kalman filters, which handles missing data and outliers without relying on imputation, as demonstrated on synthetic pedestrian tracking data.
In tasks such as tracking, time-series data inevitably carry missing observations. While traditional tracking approaches can handle missing observations, recurrent neural networks (RNNs) are designed to receive input data in every step. Furthermore, current solutions for RNNs, like omitting the missing data or data imputation, are not sufficient to account for the resulting increased uncertainty. Towards this end, this paper introduces an RNN-based approach that provides a full temporal filtering cycle for motion state estimation. The Kalman filter inspired approach, enables to deal with missing observations and outliers. For providing a full temporal filtering cycle, a basic RNN is extended to take observations and the associated belief about its accuracy into account for updating the current state. An RNN prediction model, which generates a parametrized distribution to capture the predicted states, is combined with an RNN update model, which relies on the prediction model output and the current observation. By providing the model with masking information, binary-encoded missing events, the model can overcome limitations of standard techniques for dealing with missing input values. The model abilities are demonstrated on synthetic data reflecting prototypical pedestrian tracking scenarios.