Abstract

This paper proposes a novel path prediction algorithm for progressing one step further than the existing works focusing on single target path prediction. In this paper, we consider moving dynamics of co-occurring objects for path prediction in a scene that includes crowded moving objects. To solve this problem, we fifirst suggest a two-layered probabilistic model to fifind major movement patterns and their cooccurrence tendency. By utilizing the unsupervised learning results from the model, we present an algorithm to fifind the future location of any target object. Through extensive qualitative/quantitative experiments, we show that our algorithm can fifind a plausible future path in complex scenes with a large number of moving objects.