Two-Stream Networks for Lane-Change Prediction of Surrounding Vehicles
This addresses safety and efficiency for automated driving systems by enabling early anticipation of lane changes, though it is incremental as it applies existing video action recognition methods to this domain.
The paper tackled the problem of predicting lane-change maneuvers of surrounding vehicles in highway scenarios by framing it as an action recognition task using visual cues from video cameras, achieving robust prediction for time horizons of 1 to 2 seconds.
In highway scenarios, an alert human driver will typically anticipate early cut-in and cut-out maneuvers of surrounding vehicles using only visual cues. An automated system must anticipate these situations at an early stage too, to increase the safety and the efficiency of its performance. To deal with lane-change recognition and prediction of surrounding vehicles, we pose the problem as an action recognition/prediction problem by stacking visual cues from video cameras. Two video action recognition approaches are analyzed: two-stream convolutional networks and spatiotemporal multiplier networks. Different sizes of the regions around the vehicles are analyzed, evaluating the importance of the interaction between vehicles and the context information in the performance. In addition, different prediction horizons are evaluated. The obtained results demonstrate the potential of these methodologies to serve as robust predictors of future lane-changes of surrounding vehicles in time horizons between 1 and 2 seconds.