Research Of Human Action Recognition Based On Video

Action recognition has received increasing attentions from the computer vision and machine learning community in the last decades.Ever since then,the recognition task has evolved from single view recording under controlled laboratory environment to unconstrained environment(i.e.,surveillance environment or user generated videos).Furthermore,recent work focused on other aspect of action recognition problem,such as cross-view classification,cross domain learning,multi-modality learning,and action localization.Despite the large variations of studies,we observed limited works that explore the open-set and open view classification problem,which is a genuine inherited properties in action recognition problem.In other words,a well designed algorithm should robustly identify an unfamiliar action as “unknown” and achieved similar performance across sensors with similar field of view.To address this issue,we introduce a novel dataset,namely Multi-Camera Surveillance Action(MCSA)dataset,which is designed to evaluate the open view classification problem under surveillance environment.This dataset contains 14,298 action sample from 18 action categories.Inspired by the well received evaluation approach on LFW dataset,we design a standard evaluation protocol and systematically benchmark several state-of-the-art methods.The benchmark results demonstrate that the constraints of both open-set and open view significantly reduce the state-of-the-art performance.We also designed a new method for open-view action recognition based on linear discriminant analysis which promise a better performance.