Real-time pedestrian detection and pose classification on a GPU

In this contribution, we present a real-time pedestrian detection and pose classification system which makes use of the computing power of Graphical Processing Units (GPUs). The aim of the pose classification presented here is to determine the orientation and thus the likely future movement of the pedestrian. We focus on the evaluation of pose detection performance and show that, without resorting to complex tracking or attention mechanism, a small number of safety-relevant pedestrian poses can be reliably distinguished during live operation. Additionally, we show that detection and pose classification can share the same visual low-level features, achieving a very high frame rate at high image resolutions using only off-the-shelf hardware.