Object modeling method and device, electronic equipment and storage medium

Abstract

The invention relates to an object modeling method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a plurality of to-be-processed images and corresponding camera parameter information, wherein the plurality of to-be-processed images are acquired from different angles of a target object; identifying an area where the target object is located in the to-be-processed image as a connected domain of the to-be-processed image; determining a view angle vertex corresponding to the image acquisition equipment according to the camera parameter information; connecting each vertex of a connected domain with the view angle vertex to obtain a polygonal pyramid corresponding to the connected domain, the vertexes of the polygonal pyramid respectively corresponding to each vertex of the connected domain and the image acquisition device; and determining an intersection of the polygonal pyramids corresponding to the plurality of to-be-processed images as a three-dimensional model of the target object. Thus, in the three-dimensional model construction process, a complex stereo matching algorithm does not need to be used, the influence of the texture and illumination of the object on the model precision is small, and therefore high robustness is achieved.

Description

technical field [0001] The present disclosure relates to the field of computer images, and in particular, to an object modeling method, apparatus, electronic device, and storage medium. Background technique [0002] In some scenes, in order to facilitate the analysis of the object, the data of the object can be collected by the sensor, and then, the data collected by the sensor can be used to construct a 3D model of the object. The 3D model can be used in cultural relics protection, game development, architectural design, clinical medicine, etc. Areas of research can play a supporting role. [0003] In the prior art, a three-dimensional model of an object can be constructed by using a binocular camera. Specifically, two cameras are used to photograph the object to obtain two pictures of the same object from different angles, and then the two pictures are stereo matched. Disparity is used to calculate the depth of each matching point, thereby reconstructing the entire scene ...

AI Technical Summary

Problems solved by technology

[0005] The present disclosure provides an object modeling method, device, electronic equipment, and storage medium to at least solve the problem of the high complexity of the stereo matching algorithm in the related art, and it is easily interfered by the texture and light of the object, resulting in the difference between the two images. The accuracy of stereo matching is reduced, and the accuracy of the obtained 3D model is not high enough

Images