Understanding method of non-parametric RGB-D scene based on probabilistic graphical model

Abstract

The invention discloses an understanding method of a non-parametric RGB-D scene based on a probabilistic graphical model. The method comprises the steps of carrying out global feature matching between a marked image and an image marked in a training seat, and building a retrieval set of a similar image of an image to be marked; cutting the image to be marked and the image in the similar image retrieval set, so as to generate super-pixels, and carrying out characteristic extraction on the super-pixels extracted; calculating the proportions of all categories in the training set, building a dictionary of rare categories, and taking the training set and the retrieval set of the similar images as a label source of the image to be marked; carrying out characteristics matching on each super-pixel of the image to be marked and all super-pixels in an image label source; and building a probabilistic graphical model, converting the maximum posterior probability into a minimal energy function by using a Markov random field, and resolving the semantic annotation of each super-pixel of the image to be marked obtained by solving the problem through a graph cutting method. According to the method provided by the invention, the overall and local geometric information can be integrated, and the understanding performance of the RGB-D scene can be improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a non-parametric RGB-D scene understanding method based on a probability graph model. Background technique [0002] Scene understanding is to use pattern recognition and artificial intelligence methods to analyze, describe, classify and interpret scene images, and finally obtain the technology of pixel-by-pixel semantic annotation of scene images. It is an important topic of computer vision. It has a wide range of applications in the field of monitoring and network search. [0003] Scene understanding methods are mainly divided into two categories: parametric methods and non-parametric methods. Most of the parametric methods are based on generative models that rely on training, while the non-parametric methods do not need to rely on any training, and transfer semantic labels through the similarity between images. In the parameterized method, it is necessary...

AI Technical Summary

Problems solved by technology

However, the existing scene understanding of RGB-D images is based on parametric methods. How to realize non-parametric RGB-D scene understanding quickly, efficiently, and robustly is a difficult problem at present.

Images