In this paper, we propose a method to recognize human behavior by combining motion history images (MHI) and non-negative matrix factorization (NMF). The MHI can preserve the temporal information of behavior by holding the temporal motion appearance. Then, the NMF is applied to extract the middle-level features of the moving object. Finally, we design a multi-layer judgment method to correct the misjudgment result and strengthen the accuracy of our approach. The experimental results show that the proposed scheme can achieve robust recognition results using the public dataset.
為了持續優化網站功能與使用者體驗,本網站將Cookies分析技術用於網站營運、分析和個人化服務之目的。
若您繼續瀏覽本網站,即表示您同意本網站使用Cookies。