Fast Gesture Recognition with Multiple Stream Discrete HMMs on 3D Skeletons
This work addresses efficient gesture recognition for human-computer interaction, offering high performance with low computational requirements, though it is incremental in its method.
The paper tackles gesture recognition by proposing a double-stage classification approach using Multiple Stream Discrete Hidden Markov Models (MSD-HMM) on 3D skeleton data, achieving state-of-the-art performances on multiple public datasets and a new HCI dataset.
HMMs are widely used in action and gesture recognition due to their implementation simplicity, low computational requirement, scalability and high parallelism. They have worth performance even with a limited training set. All these characteristics are hard to find together in other even more accurate methods. In this paper, we propose a novel double-stage classification approach, based on Multiple Stream Discrete Hidden Markov Models (MSD-HMM) and 3D skeleton joint data, able to reach high performances maintaining all advantages listed above. The approach allows both to quickly classify pre-segmented gestures (offline classification), and to perform temporal segmentation on streams of gestures (online classification) faster than real time. We test our system on three public datasets, MSRAction3D, UTKinect-Action and MSRDailyAction, and on a new dataset, Kinteract Dataset, explicitly created for Human Computer Interaction (HCI). We obtain state of the art performances on all of them.