Figure segmentation method based on depth map

Abstract

The present invention discloses a figure segmentation method based on a depth map. The method comprises the concrete steps: (1), collecting a skeleton graph, a color image and a depth map at the same time through adoption of a Kinect sensor, and finding out a human body bone area; (2) mapping node coordinates of the skeleton graph area into the depth map, finding out a minimum rectangular area including all the skeleton nodes, and determining the initial figure area in the depth map; (3) performing area iteration expansion of the initial figure area based on the depth information, and obtaining a final rectangular area including a complete figure object; and (4) taking the rectangular area including the complete figure object as a seed area, designing an energy function according to the depth information and the color information of the image pixels, and obtaining a final figure object segmentation result through adoption of a modulated GrabCut algorithm. The figure segmentation method based on a depth map is able to obtain a rectangular area including a whole figure object through adoption of depth information to obtain an accurate and complete figure object segmentation result.

Description

technical field [0001] The invention relates to the field of image person segmentation, in particular to a method for person segmentation based on a depth map. Background technique [0002] In recent years, with the rapid development of science and technology, the person-object segmentation technology has achieved rapid development. Some domestic and foreign research institutions, experts and scholars have done a lot of theoretical research and practical application work in this area, and have achieved many excellent results. the results. [0003] Hou, Zhang, and Harel et al. studied image saliency from the perspectives of frequency domain, information theory, and graph theory. Cheng et al. first used image segmentation technology to divide the image into several regions, and then used the global color contrast between regions to calculate the image saliency map, which has the advantages of high accuracy and fast speed. Liu et al. used the SLIC pre-segmentation algorithm t...

AI Technical Summary

Problems solved by technology

[0004] However, these models are all calculated based on visual information such as color, orientation, texture, etc., and when these information are not salient, the effect will be poor.

Images