Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans. Systems must be able to recognize and assess human actions in real-time. To train the corresponding data-driven algorithms, a significant amount of annotated training data is required. We demonstrate a pipeline to detect humans, estimate their pose, track them over time and recognize their actions in real-time with standard monocular camera sensors. For action recognition, we transform noisy human pose estimates in an image like format we call Encoded Human Pose Image (EHPI). This encoded information can further be classified using standard methods from the computer vision community. With this simple procedure, we achieve competitive state-of-the-art performance in pose-based action detection and can ensure real-time performance. In addition, we show a use case in the context of autonomous driving to demonstrate how such a system can be trained to recognize human actions using simulation data.
Simple yet efficient real-time pose-based action recognition
2019-10-01
2764142 byte
Conference paper
Electronic Resource
English
Real-Time Body Pose Recognition Using 2D or 3D Haarlets
| British Library Online Contents | 2009
Coupled Action Recognition and Pose Estimation from Multiple Views
| British Library Online Contents | 2012
Real-Time Pose Graph SLAM based on Radar
| IEEE | 2019