Foreground extraction method in gesture tracking process

Abstract

The invention discloses a foreground extraction method in a gesture tracking process. The foreground extraction method in the gesture tracking process comprises the following steps: building and updating a background, using a present frame image to minus a background image, acquiring a preliminary foreground image, carrying out binaryzation process, removing non-complexion pixel points in a foreground, removing points which are oversized in difference between pixel values and tracking palm mean values, and finally using a corrosion expansion algorithm to remove miscellaneous points. The foreground extraction method in the gesture tracking process makes full use of characteristics of a tracking object namely a palm, under the premise that small number of operation of a algorithm and small data size are ensured, not only can accurately extract foregrounds in static and motor processes of objects, but also removes disturbance of similar-complexion objects to palm tracking in a gesture control process, and provides convenient and effective input namely foreground images for a subsequent tracking matching process.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and more specifically relates to a foreground extraction method in a hand gesture tracking process during human-computer interaction using a manual control mode. Background technique [0002] Due to the limited information collected by the 2D camera, we cannot recognize the depth information in the process of tracking the palm. For example, the face behind the palm, the furniture with similar skin color, and the walking bystanders, etc., from the perspective of the plane, the palm cannot be accurately extracted, which easily leads to misjudgment of the tracking algorithm. [0003] At present, the commonly used background modeling methods include: Gaussian model, mixed Gaussian model, codebook model, etc., but the application in actual engineering will involve problems such as large amount of calculation, large amount of data, or the model cannot be updated in time. However, some...

AI Technical Summary

Problems solved by technology

[0002] Due to the limited information collected by the 2D camera, we cannot recognize the depth information in the process of tracking the palm

For example, the face behind the palm, the furniture with similar skin color, and the walking bystanders, etc., from the perspective of the plane, the palm cannot be accurately extracted, which easily leads to misjudgment of the tracking algorithm

[0003] At present, the commonly used background modeling methods include: Gaussian model, mixed Gaussian model, codebook model, etc., but the application in actual engineering will involve problems such as large amount of calculation, large amount of data, or the model cannot be updated in time

And some oversimplified modeling methods will introduce the tracking object as the background to be learned, which will bring new problems such as tracking loss.

Images