Trajectory Prediction from a Mass of Sparse and Missing External Sensor Data

In this paper, we predict the movement of objects under the circumstance where external sensors placed on the road-sides (e.g., traffic surveillance cameras) capture their trajectories. This type of trajectories may have very different mobility patterns since they are not restricted to a fleet or a community of users. However, their reported positions are sparse due to the sparsity of the sensor distribution, and incomplete, since the sensors may fail to register the passage of objects. In this paper, we first analyze such external sensor trajectories based on a real dataset, which evidenced the problems of their sparsity and their incompleteness, and hinders the location prediction. In this context, we proposed an approach for coping with the missing data problem. We discussed how to apply this approach in conjunction with the predictors based on Recurrent Neural Networks. In particular, we adjusted the accuracy metrics to account for missing values in the test set, by introducing the distance between the predicted location and the registered next location. We evaluate our approach compared to the baselines, showing an improvement of about 23% in the prediction accuracy while reducing the overall distances. In spite of the contribution of many works in location prediction, at the best of our knowledge, none of those works have studied location prediction for trajectories based on external (road-side) sensors data.