Figure behavior identification method based on random projection and Fisher vectors

Abstract

The invention discloses a figure behavior identification method based on random projection and Fisher vectors. The method employs a random projection theorem method to replace a principal component analysis method for characteristic dimension reduction, for the purpose of solving the problems of large time consumption, indeterminate reservation of principle components and the like. A random projection theorem indicates that through a compression measurement matrix, original signals with a sparse property can be projected to a certain low-dimension subspace, and the point distance between a vector after mapping and an original high-dimension characteristic vector maintains basically unchanged, i.e., data distortion is not generated in a whole compression process. Besides, different from hard division of a BoW model, the method provided by the invention employs a GMM-Fisher vector hybrid model for soft division of locus characteristic vectors, is integrated with the characteristics of a Fisher nucleus generation mode and a discrimination mode, can calculate the occurrence frequency of each characteristic descriptor, can also describe the probability distribution conditions of these characteristic descriptors in the perspective of statistics, enriches characteristic expression of behavior motion and also improves the behavior identification efficiency.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a character behavior recognition method based on random projection and Fisher vector. Background technique [0002] Behavior recognition technology is widely used in video surveillance, video retrieval, military detection, medical diagnosis and monitoring, and has broad application prospects and economic value. The traditional behavior recognition method is to embed the extracted trajectory features into the visual bag-of-words (Bag-of-Words, BoW) model, construct a rich visual dictionary by extracting local trajectory features in the video, and use the central clustering The frequency of the local feature vector relative to the central word is counted by the method, and the histogram formed by the visual word frequency is used to represent a type of video and finally achieve the purpose of character behavior recognition. The key to the BoW model is to construct a very...

AI Technical Summary

Problems solved by technology

However, this method cannot handle data on nonlinear manifolds, and the calculation process is quite time-consuming, requiring a large amount of storage space, which seriously affects the efficiency of classifier training and classification.

Images