Method for generating depth map and device thereof

Abstract

The invention relates to a method for generating a depth map and a device thereof. The method comprises the following steps: according to a dense matching method, obtaining a first depth map representing the pixel depth of a second frame by using a first frame and a second frame of monocular video streaming; detecting the characteristic points of the second frame and a third frame of the monocular video streaming, matching the characteristic point of the third frame with the characteristic point with the second frame to obtain a characteristic vector, and dividing the first depth map into a plurality of areas according to the pixel depth of the second frame; estimating the motion of the detected characteristic point to obtain motion parameters, and updating the parameters of the areas according to the motion parameters and the characteristic vector, thereby updating the areas to be used as a part of the second depth map representing the pixel depth of the third frame; and detecting a new area in the third frame, and calculating the pixel depth of the new area in the third frame to serve as another part of the second depth map, thereby obtaining a second depth map.

Description

technical field The present invention relates to a method for generating a depth map and its device, and more particularly, to a method for generating a depth map from a monocular video and its device. Background technique In recent years, with the continuous development of 3D technology, a variety of electronic products equipped with 3D features (such as displays, televisions, mobile terminals, etc.) equipped with 3D features appear on the market. However, most of the existing videos are captured by common monocular cameras, so these videos cannot be directly used as input content for 3D products. How to effectively extract 3D information from these monocular videos becomes a major task. Aiming at the above tasks, many methods have emerged. Most of the methods are mainly used to generate a single depth map rather than a sequence of depth maps, so it is impossible to generate a depth map of a video played online in real time. In addition, existing methods are highly affe...

AI Technical Summary

Problems solved by technology

Most of the methods are mainly used to generate a single depth map, rather than a sequence of depth maps, so it is impossible to generate a depth map of a video played online in real time

In addition, existing methods are highly affected and constrained by camera motion, for example, using these methods requires the camera to keep moving horizontally all the time

Moreover, these methods use the structure of motion estimation (SFM) to calculate the parameters of the camera, which will lead to a high error in the calculated camera parameters, which will greatly affect the final result

At the same time, together with the smoothing time, these methods require a lot of time

Images