Video semantic analysis method based on self-adaption probability hypergraph and semi-supervised learning

Abstract

The invention provides a video semantic analysis method based on a self-adaption probability hypergraph and incremental semi-supervised learning. The video semantic analysis method based on the self-adaption probability hypergraph and the semi-supervised learning comprises the steps that (S1) a hypergraph model is established by means of a self-adaption probability hypergraph establishment method, (S2) the semi-supervised learning is conducted on the hypergraph model by means of the spectrogram segmenting principle, (S3) a semi-supervised model based on the self-adaption probability hypergraph is perfected by means of an increment mechanism, and (S4) semantic analysis is conducted on a tested video by means of the perfected hypergraph model. According to the video semantic analysis method based on the self-adaption probability hypergraph and the semi-supervised learning, the establishment of the self-adaption probability hypergraph and an incremental semi-supervised learning method are combined for use, the sensibility to a radium parameter when an ordinary hypergraph model is established is eliminated, and the accuracy and the robustness of the model are improved; in addition, under the incremental semi-supervised learning mechanism, semantic searching accuracy and semantic searching completeness are improved remarkably.

Description

technical field [0001] The invention relates to the technical field of video semantic detection, in particular to a video semantic analysis method based on an adaptive probability hypergraph and an incremental semi-supervised learning model. Background technique [0002] In order to achieve multi-semantic learning of complex videos, a hypergraph model is proposed to describe the correlation information between multiple semantic concepts of complex videos. Experiments have proved that the hypergraph model can well complete various clustering and classification tasks. However, one of the shortcomings of this kind of hypergraph model is that it treats all vertices in the hyperedge equally, and ignores the differences between these vertices, which will lead to the loss of some information, which may cause certain damage to the analysis and detection results of video semantics. Impact. In addition, the construction method of the model is sensitive to the radius parameter k in th...

AI Technical Summary

Problems solved by technology

Although this method can adaptively determine a better radius parameter, the selection range of parameters is still a limited number given artificially, and the amount of calculation is large, so it cannot be completely adaptive.

Images