Hirokatsu KATAOKA, Ph.D.
National Institute of Advanced Industrial Science and Technology (AIST), Japan

[Top] [Research] [Curriculum Vitae] [Publications]

"Human Action Recognition with Feature Integration"
Hirokatsu Kataoka (Keio Univ), Kiyoshi Hashimoto (Keio University), Yoshimitsu Aoki (Keio Univ)

  This paper presents an approach for real-time human activity recognition. Three different kinds of features (flow, shape, and a keypoint-based feature) are applied in activity recognition. We use random forests for feature integration and activity classification. A forest is created at each feature that performs as a weak classifier. The international classification of functioning, disability and health (ICF) proposed by WHO is applied in order to set the novel definition in activity recognition. Experiments on human activity recognition using the proposed framework show - 99.2% (Weizmann action dataset), 95.5% (KTH human actions dataset), and 54.6% (UCF50 dataset) recognition accuracy with a real-time processing speed. The feature integration and activity-class definition allow us to accomplish high-accuracy recognition match for the state-of-the-art in real-time.

  In this research, we propose effective approach to combine multiple features with random forests. The right figure shows feature integration with random forests. The outputs of random forests are integrated to understand human activities. Here we employed extended co-occurrence HOG (ECoHOG), SURF+bag-of-features (SURF+BoF), and histograms of oriented optical flow (HOOF) from different input as edge, keypoint and flow.


References

- Hirokatsu Kataoka, Kiyoshi Hashimoto, Yoshimitsu Aoki, "Feature Integration with Random Forests for Real-time Human Activity Recognition", International Conference on Machine Vision (ICMV), Nov. 2014. (Acceptance rate: 40.0%) [PDF]




Copyright Hirokatsu Kataoka