Mirror image segmentation method based on depth perception

Abstract

The invention belongs to the technical field of scene segmentation in computer vision, and discloses a mirror image segmentation method based on depth perception. The PDNet sequentially comprises a multi-layer feature extractor, a positioning module and a description module, wherein the multi-layer feature extractor acquires context features by using a traditional feature extraction network; the positioning module preliminarily determines the position of the mirror in the image by combining the RGB feature information with the depth feature information; and the description module is used for adjusting and determining the boundary of the mirror by combining depth information on the basis of the RGB feature information of the image. The method is the first method for realizing mirror segmentation in the image by simultaneously using the RGB image and the depth image. According to the method, further testing is carried out, the PDNet segmentation result is still excellent for a mirror with a large area in a complex environment, and the result at the boundary of the mirror is also satisfactory. The method is wider in applicability.

Description

technical field [0001] The invention belongs to the field of scene segmentation (SceneSegmentation) in computer vision, the realization result is the segmentation of image content, and particularly relates to a method for segmenting mirror images in a real environment. Background technique [0002] Two-dimensional image segmentation refers to the technology of distinguishing the pixels belonging to different objects in the image and determining the size, shape and position of the target in the environmental image. It is a key step from image processing to image analysis and has great application value. [0003] However, there are some special objects that cannot be ignored in most scenes, such as mirrors, which will greatly affect the understanding of the scene, and then affect the accuracy of various computer vision tasks and applications. The characteristics of the mirror surface make the mirror area in the image present the mirror image of the scene in front of it. The di...

AI Technical Summary

Problems solved by technology

However, in fact, the reflected content may not necessarily be significant, even if it is significant, it may only be partly significant

Therefore, the existing SOD method is powerless for the mirror segmentation problem.

Images