Long-term visual tracking method and device based on structured model

Abstract

The invention discloses a long-term visual tracking method and a long-term visual tracking device based on a structured model, which are used for solving the problems of model expression capability degradation and tracking target loss caused by limited expression capability of a single model of visual tracking and feature expression disorder of multiple models. The method comprises the following steps: constructing a plurality of representative target appearance models according to different characteristics of a target object; adopting the target appearance model to respectively perform similarity comparison and identification on a plurality of candidate target pictures of the current frame, and determining a tracking result and a target appearance model matched with the tracking result from the plurality of candidate target pictures; updating the matched target appearance model according to the comparison and recognition result and a preset rule, or newly establishing the target appearance model; and clustering the templates of the target appearance model by adopting a sparse subspace clustering algorithm to ensure that the intra-class templates are in the same feature subspace soas to establish a visual tracking structured multi-representative target appearance model.

Description

technical field [0001] The present application relates to the technical field of visual tracking, in particular to a structured model-based long-term visual tracking method and device. Background technique [0002] Visual tracking is a technology that uses computer vision technology to process, analyze and understand video signals to achieve continuous tracking of target objects. The target appearance model in the visual tracker is used to express the characteristics of the target object, so as to realize the tracking of the target object according to the characteristics of the target object. [0003] At present, when tracking a target object, 2D models are usually used to express the characteristics of the target object, including single models and multiple models. [0004] Target objects are often dynamically changing in videos, however, the expressive power of a single model is limited. Therefore, when a single model is used for visual tracking, the expressive ability o...

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present application provides a long-term visual tracking method and device based on a structured model, which is used to solve the problem that a single model of visual tracking has limited expression ability, and multi-models may cause feature expression confusion, resulting in degradation of model expression ability and loss of tracking targets. The problem

Images