A multi-target detection and tracking method in space background

Abstract

The invention discloses a multi-target detection and tracking method in the space and sky background, comprising the following steps: S1: Carry out S and V channel binary segmentation on the original image to realize the segmentation of the target and the background; perform morphological analysis on the segmented target image Filter to obtain the basic outline of each target and perform connected component detection to obtain the number of targets and the information of the external gate; S2: take the position of the centroid of the target on the horizontal and vertical axes of the pixel coordinate axis and the unit displacement in both directions as the state Variables, taking the position of the target on the horizontal and vertical axes of the pixel coordinate axis as observation variables, establishing a motion model, and realizing the prediction and tracking of the track of each detection target; S3: Data association between the detection set and the tracking set to realize the detection target Matching of tracking targets; the invention can realize multi-target detection, tracking and trajectory prediction under the background of space and sky, solve the cross-movement and short-term occlusion methods of moving targets to a certain extent, and improve the speed and stability of target detection and tracking.

Description

technical field [0001] The invention belongs to the technical field of image and video processing, and more particularly relates to a multi-target detection and tracking method in space and sky background. Background technique [0002] Target detection in the air and sky background often adopts target segmentation and pattern recognition fusion method or inter-frame difference method. At the same time, due to the phenomenon that the maneuvering target may have large deformation due to attitude changes, distance changes, etc. during the movement process, and the proportion of the field of view may change drastically, it is relatively difficult to use target shape, size, corner points and other information for segmentation and recognition. Big difficulty. Contents of the invention [0003] Aiming at the above defects or improvement needs of the prior art, the present invention provides a multi-target detection and tracking method in the space and sky background, which can r...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the above defects or improvement needs of the prior art, the present invention provides a multi-target detection and tracking method in the space and sky background, which can realize multi-target detection, tracking and trajectory prediction in the space and space background, and solve the problem of crossing moving targets to a certain extent. The problem of motion and short-term occlusion improves the speed and stability of target detection and tracking

Images