Three-dimensional reconstruction method of target based on attention

Abstract

The invention relates to a three-dimensional reconstruction method of a target based on attention, comprising the steps: step S1, dividing video for three-dimensional reconstruction into video frames, analyzing the visual attention distribution in the video frames in the static state, the position and the dynamic state and obtaining significance level diagrams; fusing the significance level diagrams in the static state, the position and the dynamic state so as to obtain the significance level diagrams based on the video of each video frame, wherein the significant areas described by the significance level diagrams are interested areas in three-dimensional reconstruction; step S2: utilizing the concept global features to cluster all the video frames, picking out a candidate keyframe set according to the significance level diagram generated by each video frame, and finally extracting the video keyframes for three-dimensional reconstruction by analyzing geometric constraint and visual constraint; and step S3: using the video keyframes and the significance level diagram corresponding to the video keyframes to carry out three-dimensional reconstruction only on the significant areas in the video frames so as to obtain accurate three-dimensional models on the interested areas and increase the reconstruction speed.

Description

technical field [0001] The invention belongs to the technical fields of computer vision, image processing and multimedia analysis, and relates to a method for three-dimensional reconstruction of an object based on attention degree. Background technique [0002] With the development of digital images, high-quality video has become more abundant. Since video-based 3D reconstruction can improve ensemble accuracy and visual quality by using rich video data, it has become a popular research topic in computer vision, image processing, and multimedia analysis. [0003] In general, video / image-based 3D reconstruction systems can be divided into two categories: non-calibration-based systems and self-calibration-based systems. Unlabeled-based systems require image and camera parameters for 3D reconstruction, such as the patch-based multi-view stereo method (PMVS), which recovers the 3D structure of objects or scenes by enhancing local optical consistency and global visual constraints...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the accuracy of 3D reconstruction in the prior art is unsatisfactory, the purpose of the present invention is to propose a method of spatio-temporal attention region detection to enhance 3D reconstruction based on video, and to provide a target based on attention Object 3D Reconstruction Method

Images