A method and system for target tracking based on multi-scale feature quantities

Abstract

The invention discloses a target tracking method and system based on multi-scale feature quantities. The method calculates the moving distance between the clusters to which position points at different time points belong, and determines the current time by comparing the moving distance with a predetermined scale threshold The cluster where the point's location point is located and the cluster of the location point of the time point within the preset time period before the current time point belong to large-scale movement or small-scale movement respectively. The threshold value is set to judge, and the scope of application is wider. According to the Tracking the spatial scale of the object's movement for prediction can accurately predict the dynamic movement trajectory of the tracked target at different scales, improving the prediction accuracy, and accurately tracking the tracked target according to the prediction result.

Description

technical field [0001] The invention relates to the field of target tracking, in particular to a target tracking method and system based on multi-scale feature quantities. Background technique [0002] In the application scenarios of smart cities, it is of great value to track the location changes of targets. For example, public security or security departments can deploy and control the monitoring objects of concern based on target tracking to prevent illegal incidents and maintain public safety. In traffic management, the traffic conditions of vehicles can be measured based on target tracking, and then by summarizing the traffic conditions of many vehicles, the smoothness of each section of road traffic can be determined, and so on. [0003] Traditional target tracking only obtains the position of the target in real time or quasi-real time, so it can only reflect the past and current position of the target. In order to better serve the above application scenarios, people ...

AI Technical Summary

Problems solved by technology

[0007] In view of the above problems, the purpose of the present invention is to solve the problem that the dynamic prediction and tracking technology of the target in the prior art does not take into account the influence of the moving spatial scale, which makes the position point prediction of the target prone to deviation and cannot be accurately targeted at different spaces. The Problem of Range Prediction of Potential Location Points

Images