Texture and geometric attribute combined model based indoor target analytic method

Abstract

The invention relates to a texture and geometric attribute combined model based indoor target analytic method, which comprises the following steps: first, evaluating a static area in an image; then, adopting a slide window; in the static area, calculating the similarity between the texture attribute of the combined model and the texture attribute of the image in the slide window, so as to obtain a probability map of tested images, wherein the number of each pixel of the images represents the probability of the point belonging to the target; obtaining a super pixel set of the images through a segmentation method, and extracting semantic segmentation of the target in the images based on the super pixel set in combination with the probability map obtained from the last step; and finally, evaluating the directed enclosure surface of the target, namely the geometric attribute of the target, in the images through the method, in combination with the geometric attribute of the combined model, semantic marks and line segmentation of the image in a way of utilizing energy minimum. The method can be widely applied to indoor scene target analysis, scene comprehension and three-dimensional reconstruction of computer vision system of monitoring, robot and the like.

Description

technical field [0001] The invention relates to the fields of computer vision and image scene understanding, in particular to an indoor object analysis method based on a joint model of texture and geometric attributes. Background technique [0002] Scene understanding includes scene semantic segmentation and geometric attribute estimation, which is a basic and important research problem in the field of computer vision. In the past, the scientific research results paid more attention to the processing of outdoor scenes, but because of the variability of indoor scenes, the clutter of objects, and the lack of distinguishing features between objects, indoor scene understanding has received less attention. At present, indoor scene understanding mainly uses Kinect to capture two-dimensional images and scene depth images. Problems become easier to solve through depth information. In addition, there are also models or data-driven methods for scene semantic segmentation and object ...

AI Technical Summary

Problems solved by technology

[0004] The above research status shows that although scholars in this field pay attention to the understanding of indoor scenes, they only focus on the derivation of geometric attributes in the scene, cannot identify the semantic segmentation of objects, and can only represent objects with several common units, which limits The scene understanding ability of the method when the unit changes greatly

Images