Real-time Online Action Detection Forests using Spatio-temporal Contexts

TL;DR

This paper introduces a real-time online action detection method using random forests that leverage efficient skeletal features and CNN-based spatio-temporal contexts to improve accuracy without sacrificing speed.

Contribution

It presents a novel RF-based framework that incorporates high-quality CNN features during training to enhance split functions, enabling accurate real-time action detection.

Findings

Significant accuracy improvements over state-of-the-art methods.

Achieves real-time performance with high detection accuracy.

Effective use of CNN features in training RF classifiers.

Abstract

Online action detection (OAD) is challenging since 1) robust yet computationally expensive features cannot be straightforwardly used due to the real-time processing requirements and 2) the localization and classification of actions have to be performed even before they are fully observed. We propose a new random forest (RF)-based online action detection framework that addresses these challenges. Our algorithm uses computationally efficient skeletal joint features. High accuracy is achieved by using robust convolutional neural network (CNN)-based features which are extracted from the raw RGBD images, plus the temporal relationships between the current frame of interest, and the past and future frames. While these high-quality features are not available in real-time testing scenario, we demonstrate that they can be effectively exploited in training RF classifiers: We use these spatio-temporal contexts to craft RF's new split functions improving RFs' leaf node statistics. Experiments with challenging MSRAction3D, G3D, and OAD datasets demonstrate that our algorithm significantly improves the accuracy over the state-of-the-art online action detection algorithms while achieving the real-time efficiency of existing skeleton-based RF classifiers.