Title :
Action recognition with discriminative mid-level features
Author :
Cuiwei Liu ; Yu Kong ; Xinxiao Wu ; Yunde Jia
Author_Institution :
Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
Abstract :
This paper presents a novel random forest learning framework to construct a discriminative and informative mid-level feature from low-level features. Since a single low-level feature based representation is not enough to capture the variations of human appearance, multiple low-level features (i.e., optical flow and histogram of gradient 3D features) are fused to further improve recognition performance. The mid-level feature is employed by a random forest classifier for robust action recognition. Experiments on two publicly available action datasets demonstrate that using both the mid-level feature and the fusion of multiple low-level features leads to a superior performance over previous methods.
Keywords :
feature extraction; image classification; image fusion; image sequences; learning (artificial intelligence); random processes; discriminative midlevel features; histogram-of-gradient 3D features; informative midlevel feature; optical flow; random forest classifier; random forest learning framework; robust action recognition; Feature extraction; Histograms; Humans; Integrated optics; Optical sensors; Training; Vegetation;
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
Print_ISBN :
978-1-4673-2216-4