Improved logic-based track initiation method

Abstract

The invention provides an improved logic-based track initiation method. The improved logic-based track initiation method comprises the steps of registering a temporary track for each tracking target by taking a measuring point of the tracking target in a first frame image as an initial point, and taking the correlation coefficient of each tracking target as the correlation coefficient of the corresponding temporary track; by taking the measuring point, in the circular correlation area of measuring points of the first frame image, of a second frame image as a second point, adding into the corresponding temporary track; when one measuring point is added into the temporary track of the tracking target, accumulating the correlation coefficient of the temporary track, and when the accumulation sum of the correlation coefficients is greater than or equal to a preset judgment threshold, adding the temporary track into a queue of temporarily successful track for carrying out track pruning, and then outputting an effective track. The improved logic-based track initiation method has different track initiation requirements after different targets are achieved, the track initiation precision can be enhanced, and the calculation time can be shortened.

Description

Technical field [0001] The invention belongs to the field of image detection and processing, and in particular relates to a track starting method based on improved logic. Background technique [0002] Due to the long distance of the target at the beginning of the track, the low detection resolution of the sensor and the poor measurement accuracy, coupled with the appearance of true and false targets, there is no real statistical law, especially under complex background conditions, which will affect conventional processing. The starting mass of the track under In order to reliably complete the target correlation, filter out clutter points, and complete the reliable start of the respective real target trajectory among many targets, a certain processing convergence time is required. Therefore, the rapid start of the trajectory requires a high trajectory. The initial success rate of the trace is contradictory. [0003] The existing track initiation methods mainly include heuristic ru...

AI Technical Summary

Problems solved by technology

According to the track association algorithm of the general logic method described in Document 3 (Yan Kang, multi-sensor multi-target track tracking and fusion algorithm research [D], Nanjing University of Science and Technology, 2012), the track initial length and response of the target The time is fixed, and the response time cannot be changed dynamically. It is very likely to lose the target or misdetect the target.

Images