Track modeling and searching method

Abstract

The invention discloses a track modeling method based on a viscous multi-modal dual layered dirichlet process hidden markov model (SMD-HDP-HMM). The method comprises the following steps: expressing each track as a visual document to form a training set comprising a plurality of visual documents; learning the SMD-HDP-HMM model by using the visual documents in the training set. The invention also discloses a track searching method. The track searching method adopts the SMD-HDP-HMM model generated by the track modeling method. The track searching method comprises the following steps: expressing a new input track as a visual document; matching the visual document of the new input track with the SMD-HDP-HMM model, judging that whether the visual document of the new input track is abnormal and / or searching a most similar track in the SMD-HDP-HMM model.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to behavior understanding technology. Background technique [0002] In the field of computer vision, especially in behavior understanding based on video analysis, trajectory is an important feature, and trajectory modeling can be applied to fields such as visual surveillance and action recognition. By modeling motion trajectories, many useful functions can be realized, such as discovering typical trajectory patterns, detecting whether new motion trajectories are abnormal, retrieving motion trajectories or video clips similar to new trajectories, etc. [0003] Since the trajectory patterns contained in different scenarios are different, it is very important to develop unsupervised trajectory modeling methods to provide a unified and convenient solution for applications in different scenarios. The trajectory modeling methods mentioned later are all unsupervised. The existing trajector...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a trajectory modeling and retrieval method based on unsupervised learning to solve the technical problems of automatically discovering trajectory patterns and / or realizing trajectory retrieval efficiently and accurately

Images