Background modeling and foreground extraction method based on depth map

Abstract

The present invention relates to a image background modeling and foreground extraction method based on a depth map. The method is characterized by comprising the steps of: step 1, acquiring a depth image for characterizing the distance between an object and a camera; step 2, initializing a real-time depth background model; step 3, updating the real-time depth background model; step 4, acquiring a current depth image for characterizing the distance between the object and the camera; step 5, extracting a foreground image of the current depth image based on the real-time depth background model; step 6, outputting the foreground image and generating a real-time target mask image; and step 7, updating the real-time depth background model: according to the real-time target mask image, updating code group information of each pixel point in the real-time depth background model. The method provided by the present invention has stability incomparable to that of a known color diagram modeling method, high efficiency and superiority in location relationship handling, and initial modeling does not need to be performed on a scene, so that the implementation steps are simplified and the whole efficacy is dramatically improved.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, in particular to a method for image background modeling and foreground extraction based on a depth map. Background technique [0002] At present, the image source for background modeling and foreground extraction is mainly a color map. There is a set of color map background modeling and foreground extraction methods for color maps, mainly including Gaussian background modeling and codebook background modeling. The main problems existing in the existing color map modeling are as follows: first, the background and foreground information can be distinguished only by the change of color, which cannot reflect the orientation relationship between each target in the image; second, the color map is affected by the light and the external environment The impact is large, the result of foreground extraction is greatly affected by it, and the stability is poor; the third is that the data vo...

AI Technical Summary

Problems solved by technology

The main problems existing in the existing color map modeling are as follows: first, the background and foreground information can be distinguished only by the change of color, which cannot reflect the orientation relationship between each target in the image; second, the color map is affected by the light and the external environment The impact is large, the result of foreground extraction is greatly affected by it, and the stability is poor; the third is that the data volume of a single pixel in the color map is large, and the calculation efficiency in the modeling process is low

Although this method can effectively solve the problem of target extraction in complex backgrounds, making the accuracy rate of foreground extraction and feature classification reach 94.04%, there are still the following obvious deficiencies. First, this patent is based on an established background model, which cannot Deal with the situation that the background model cannot provide at the beginning; the second is that the calculation is relatively large, and it is necessary to calculate the gradient feature and use the classifier for identification

Images