Keynote lecture pedestrian path prediction and action classification using Computer Vision and body language traits

Driver Assistance Systems have achieved a high level of maturity in the latest years. As an example of that, sophisticated pedestrian protection systems are already available in a number of commercial vehicles from several OEMs. However, accurate pedestrian path prediction is needed in order to go a step further in terms of safety and reliability, since it can make the difference between effective and non-effective intervention. Getting to understand the underlying intent of an observed pedestrian is of paramount interest in a large variety of domains that involve some sort of collaborative and competitive scenarios, such as robotics, surveillance, human-machine interaction, and intelligent vehicles. In contrast to trajectory-based approaches, the consideration of the whole pedestrian body language has the potential to provide early indicators of the pedestrian intentions, much more powerful than those provided by the physical parameters of a trajectory. In this talk, we consider the three-dimensional pedestrian body language in order to perform path prediction in a probabilistic framework. For this purpose, the different body parts and joints are detected using stereo vision. The use of GPDM (Gaussian Process Dynamical Models) is proposed for reducing the high dimensionality of the input feature vector in the 3D pose space and for learning the pedestrian dynamics in a latent space. Experimental results show that accurate path prediction can be achieved at a time horizon of up to 1.0 s.