Target following method in complex interference scene

Abstract

The invention discloses a target following method in a complex interference scene, comprising the steps of: detecting a moving target by confirming the initial position of every moving target which appears in video, detecting with self-adapting Gaussian background models and separating a moving target area with a morphologic treating method, modeling for target feature by acquiring a plurality ofmatching feature messages for each detected moving target area, fusing a plurality of feature messages and building a target feature template, searching the matching area by searching the area which is matched with the target feature template in a specific area in current video as a target following location of current video, updating the target feature template by updating the feature of the target feature template of current video to finish the self-adapting update for the target feature template after locating the target according to the feature in the current video target area and the feature of the target feature template in the former three videos.

Description

Technical field [0001] The invention belongs to the field of video monitoring, and particularly relates to a target tracking method in a complex interference scene based on motion and target information. Background technique [0002] The research and application of target tracking methods is an important branch of computer vision technology. The realization of target tracking mainly has the following key points: target extraction, target recognition and real-time algorithm. [0003] In summary, the existing target tracking methods are mainly as follows: [0004] Methods based on motion analysis: including inter-frame difference method, background subtraction method and optical flow method. [0005] The inter-frame difference method and the background subtraction method mainly detect moving targets through the intensity changes of pixels between frames, and track the targets according to the correlation between the detected targets. Among them, the background subtraction method is cur...

AI Technical Summary

Problems solved by technology

[0011] The method based on area template and color histogram matching mainly utilizes the color information of the target. Among them, the area template matching uses the entire target area as a tracking template to perform correlation matching calculations. During the movement of the target, deformation often occurs, or is the size of the target changes, in which case the target is easily lost

Color histogram matching uses the color histogram of the target area as a matching feature. This method mainly uses the target color information without considering the structure of the target or the relationship between the pixels. Therefore, changes in light can easily lead to tracking failure. At the same time, if the target area is similar to the background color information, it is easy to get the best matching result in the background area, thus missing the target

[0012] The contour-based matching method mainly performs matching and tracking based on the contour features of the moving target. The main disadvantage of this method is that it is not adaptable to the change of the target size, and the target tracking effect is very poor for shadows or crowded scenes.

Images