A multi-extension target tracking method under space-time neighbor target detection and grid clustering measurement division

Abstract

The invention discloses a multi-extended target tracking method under space-time neighbor target detection and grid clustering measurement division, and mainly solves the problem of multi-extended target tracking under measurement division. The method comprises the following steps of firstly, according to a space-time correlation principle, centralizing current measurement into survival expansionand newly-expanded target measurement; secondly, dividing survival extension target measurement by using an FCM algorithm; carrying out dynamic grid processing on the measurement space of the newly-generated extended target, removing clutter measurement according to the grid density and the look-up distance, and carrying out grid clustering method division; Finally, utilizing a GM-PHD filter and an ET-GM-PHD filter to estimate the states of the survival and new multi-expansion target states to obtain the motion trails of the survival and new multi-expansion target states. The method can accurately track multiple extended targets, and particularly has the advantages of accurate measurement division, accurate target number estimation, high tracking precision, good real-time performance and the like at the target intersection moment.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

This patented system allows two or three different types of objects (targets) are trackled together simultaneously during an experiment without losing any data about them due to their spatial proximity. By introducing space time correlations between these object measurements sets, it divides up the entire dataset into smaller subsets that work better when analyzing specific areas within those parts compared against random selection methods like Kernigh et al., resulting in improved precision and efficiency in measuring various aspects such as vital signs. Additionally, this approach helps reduce computational complexity while still maintain good results over long periods of observation. Overall, this innovation enhances the ability to monitor complex systems quickly and efficiently.

Problems solved by technology

The technical problem addressed in this patented text relates to efficiently dividing up complex measured data from multiple sources such as long range surveillance systems onto smaller ones like near sea vessels due to limitations associated with existing techniques. Existing approaches either require significant calculations or involve excessive computation resources leading to decreased track quality.

Images