A Content-Adaptively Adaptively Sparse Reconstruction Method for Abnormal Events Detection With Low Low-Rank Property
Abstract: This paper presents a content content-adaptively adaptively sparse reconstruction method for abnormal events detection by exploiting the low low-rank rank property of video sequences. In dictionary learning phase, the bases which describe more important characteristics of the normal behavior patterns are assigned with lower reconstruction costs. Based on the low low-rank rank property of the bases captured by the low-rank rank approximation, a weighted sparse reconstruction method is proposed to measure the abnormality of testing samples. Multiscale Multiscal 3-D gradient features, which encode the spatiotemporal information, are adopted as the low level descriptors. The benefits of the proposed method are threefold: first, the low-rank rank property is utilized to learn the underlying normal dictionaries, which can an represent groups of similar normal features effectively; second, the sparsitysparsity based algorithm can adaptively determine the number of dictionary bases, which makes it a preferable choice for representing the dynamic scene semantics; and third, based on the he weighted sparse reconstruction method, the proposed method is more efficient for detecting the abnormal events. Experimental results on the public datasets have shown that the proposed method yields competitive performance comparing with the state state-of-the-art methods.