Multi-target tracking method based on variable processing windows and variable coordinate systems

Abstract

A multi-target tracking method based on variable processing windows and variable coordinate systems includes: step one, performing an initialization process; step two, constructing a space-time processing block for the k frame image; step three, solving a position energy density of the space-time processing block constructed in the step two; step four, extracting position parameters of all targets in the k frame image; step five, matching the target with the position parameter in each processing block to obtain a position observed value Z (k+1) of each target; step six, calculating target speed parameters with the Kalman filter algorithm with weighted gain to reduce calculated amount, amending the position observed value of each object, and strengthening accuracy and robustness of the tracking; and step seven, calculating the motion scale of each target in the k frame image. According to the multi-target tracking method, the variable window, variable projection method and Kalman motion estimation are introduced on the basis of continuous wavelet transform and expectation maximization (EM) fitting algorithm, motion parameters are accurately extracted; and calculated amount is reduced; and accurate tracking of a plurality of motion targets is achieved.

Description

technical field [0001] The invention relates to a multi-target tracking method based on a variable processing window and a variable coordinate system, which belongs to the field of machine vision and pattern recognition. It specifically involves a time-space filter based on continuous wavelet transform for the image area in the processing window, and then performs variable coordinate system projection to reduce the dimensionality of the filter results, and then extracts the motion parameters of the target from the one-dimensional energy density curve, and finally realizes multi- A method for moving target tracking. Background technique [0002] The basic problem of target tracking is to estimate the motion state of the target in real time and accurately according to the observation data. With the development of modern navigation, aviation and aerospace, the research of target tracking technology has been highly valued by various countries. Whether in maritime and air traff...

AI Technical Summary

Problems solved by technology

[0007] 1. A separate processing window is designed for each target, which makes the calculation amount have a positive linear relationship with the number of targets, which is not conducive to real-time tracking;

[0008] 2. When the coordinate values ​​of a certain dimension of multiple targets are similar, the coordinate value of this dimension obtained by EM fitting will have a large deviation, which will easily lead to data association errors and eventually lead to tracking failure;

[0009] 3. When extracting the speed and motion direction parameters of the target, it is necessary to obtain the two-dimensional velocity energy density surface through wavelet transformation, which will increase the amount of calculation

Images