Human Activity Recognition Based On Mid-Level Representations In Video Surveillance Applications
2016 International Joint Conference on Neural Networks (IJCNN)(2016)
摘要
Human Action Recognition methods have prospered during the last decade. They seek to automatically analyze ongoing activities in different camera views by using machine-learning algorithms in video sequences. Various human action recognition methods match local features and global features using action class labels in which abundant visual spatio-temporal information can hardly be generalized. To overcome this problem, we propose a novel notion of mid-level representations to construct a discriminative and informative semantic concept for human action recognition. This work introduces a mid-level representation based on the Optical Flow (OF) method, Hu and Zernike moment together. First we extract from each video, U-h and U-v motion vectors by forming motions curvatures. Second, we determine the Hu moment and Zernike that serve as the feature vector of an action. Our method was tested and evaluated through a classification of the KTH and Weizmann datasets, with an Artificial Neural Network classifier (ANN). The results prove the accuracy of the suggested approach.
更多查看译文
关键词
human activity recognition,mid-level representations,video surveillance,camera views,machine learning algorithms,video sequences,local features,global features,action class labels,visual spatio-temporal information,discriminative semantic concept,informative semantic concept,optical flow,Hu moment,Zernike moment,video extraction,motion vectors,motions curvatures,feature vector,classification,KTH datasets,Weizmann datasets,artificial neural network classifier,ANN classifier
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络