Depth map real-time acquisition algorithm based on array camera

Abstract

The invention discloses a depth map real-time acquisition algorithm based on array camera; the camera array thereof comprises a 3D camera and a plurality of visible light cameras; the algorithm obtains the high-resolution depth maps on the viewports of each visible light camera according to a low-resolution depth map provided by the 3D camera. The algorithm comprises the steps of: at first, calibrating the camera array and projecting the depth map of the 3D camera in the field of view of each visible light camera to obtain an initial depth map in the field of view of the visible light cameras; and secondarily, using the new energy function which is defined in the algorithm and fused with color information and initial depth information and taking the color maps or grey-scale maps of the visible light cameras as references to iteratively correct the initial depth map so as to obtain the final high-resolution depth map. The algorithm is a method capable of obtaining the high-resolution depth map in the field of view of common cameras in real time and can meet the demands on multi-aspect application such as stereoscopic television, virtual reality and the like.

Description

technical field [0001] The invention relates to a three-dimensional depth information acquisition system, in particular to an array camera-based depth map acquisition algorithm. Background technique [0002] In recent years, the acquisition of 3D depth information has become a very popular research direction in the field of computer vision. Many institutions and experts at home and abroad have done a lot of related work and proposed some methods and technologies. However, these methods and technologies have their own shortcomings, and no method or technology can satisfy various applications, so there are still many challenges in the acquisition of depth information. [0003] Although the traditional stereo matching method based on the visible light camera array is perfect in theory, in practical application, because the exact matching point cannot be found, this method is helpless for non-textured planar areas and gradient surfaces. In addition, the traditional depth inform...

AI Technical Summary

Problems solved by technology

This kind of sensor has been applied to a certain extent, but it also has the following shortcomings: the depth information is not accurate at the edge, sensitive to noise and object materials, not easy to be calibrated, and low resolution, etc.

They process every point in the high-resolution depth map, which tends to destroy the 3D raw data in flat areas, and doesn't get good results on those points with approximately the same depth value but in texture-rich areas, which will Unnecessary deep mutations

Moreover, it processes every point of the high-resolution depth map, and it is difficult to meet real-time requirements

Images