Characterizing Human Behaviours Using Statistical Motion Descriptor

TL;DR

This paper introduces a novel statistical motion descriptor for human behavior recognition in videos, achieving 72.1% accuracy and outperforming existing methods on public datasets.

Contribution

The paper proposes a new motion descriptor based on statistical features of dense optical flow, improving behavior classification accuracy.

Findings

Achieved 72.1% classification accuracy.

Outperforms state-of-the-art methods.

Effective on publicly available datasets.

Abstract

Identifying human behaviors is a challenging research problem due to the complexity and variation of appearances and postures, the variation of camera settings, and view angles. In this paper, we try to address the problem of human behavior identification by introducing a novel motion descriptor based on statistical features. The method first divide the video into N number of temporal segments. Then for each segment, we compute dense optical flow, which provides instantaneous velocity information for all the pixels. We then compute Histogram of Optical Flow (HOOF) weighted by the norm and quantized into 32 bins. We then compute statistical features from the obtained HOOF forming a descriptor vector of 192- dimensions. We then train a non-linear multi-class SVM that classify different human behaviors with the accuracy of 72.1%. We evaluate our method by using publicly available human action data set. Experimental results shows that our proposed method out performs state of the art methods.