Learning temporal structures for human activity recognition - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Learning temporal structures for human activity recognition

Edward K Wong
  • Function : Author
  • PersonId : 1029189

Abstract

We propose a hierarchical method for learning temporal structures for the recognition of complex human activities or actions in videos. Low level features (HOG, HOF, MBH x and MBH y) are first computed from video snippets to form concatenated feature vectors. A novel segmentation algorithm based on K-means clustering is then used to divide the video into segments, with each segment corresponding to a sub-action with uniform motion characteristics. Using low level features as inputs, a many-to-one encoder is trained to extract generalized features for the snippets in each segment. A second many-to-one encoder is then used to compute higher-level features from the generalized features. The higher-level features from individual segments are then concatenated together and used to train a third many-to-one encoder to extract a high-level feature representation for the entire video. The final descriptor is the concatenation of higher-level features from individual segments and the high-level feature for the entire video. Using the proposed descriptor and a mutli-class linear support vector machine (SVM), we achieved state-of-the-art results on datasets Olympic Sports and UCF50, and beat the state-of-the-art result on the challenging HMD51 dataset by a wide margin of 17%.
Fichier principal
Vignette du fichier
0727.pdf (1.85 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01726528 , version 1 (08-03-2018)

Identifiers

  • HAL Id : hal-01726528 , version 1

Cite

Tiantian Xu, Edward K Wong. Learning temporal structures for human activity recognition. British Machine Vision Conference (BMVC) 2017, Sep 2017, London, United Kingdom. ⟨hal-01726528⟩
50 View
198 Download

Share

Gmail Facebook X LinkedIn More