Recognizing human actions: a local SVM approach

TLDR

Local space‑time features capture local events in video and can be adapted to the size, frequency, and velocity of moving patterns. The paper demonstrates using these features to recognize complex motion patterns. The authors build video representations from local space‑time features, classify them with SVMs, and evaluate on a new database of 2,391 sequences of six actions by 25 people across four scenarios. Results show the method outperforms other action‑recognition approaches.

Abstract

Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition. For the purpose of evaluation we introduce a new video database containing 2391 sequences of six human actions performed by 25 people in four different scenarios. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action recognition.