Encoding Motion Cues for Pedestrian Path Prediction in Dense Crowd Scenarios

Pedestrian path prediction is an emerging topic in the crowd visual analysis domain, notwithstanding its practical importance in many respects. To date, the few contributions in the literature proposed quite straightforward approaches, and only a few of them have taken into account the interaction between pedestrians as a paramount cue in forecasting their potential walking preferences in a given scene. Moreover, the typical trend was to evaluate the proposed algorithms on sparse scenarios. To cope with more realistic cases, in this paper, we present an efficient approach for pedestrian path prediction in densely crowded scenes. The proposed approach initiates by extracting motion features related to the target pedestrian and his/her neighbors. Second, in order to further increase the representativeness of the extracted motion cues, an autoencoder feature learning model is considered, whose outcome finally feeds a Gaussian process regression prediction model to infer the potential future trajectories of the target pedestrians given their walking records in the scene. Experimental results demonstrate that our framework scores plausible results and outperforms traditional methods in the literature.