Apparatus and method for generating panorama image

Abstract

The invention discloses a method for generating a panoramic picture and equipment thereof, which are used for generating multi-viewpoint panoramic pictures of plane dominant scenes, wherein, the method has the functions of evaluating each dominant plane containing at least one plane in input pictures; deforming the input pictures according to the positions thereof corresponding to the dominant plane so as to partially overlap the input pictures; and syncretizing the input pictures to form the panoramic picture. During the application of the equipment and the method of the invention, a priori knowledge is not needed, and pictures are sutured according to the dominant plane in the scene so as to form the multi-viewpoint panoramic picture.

Description

technical field [0001] The present invention relates to computer image processing technology, in particular to a device and method for generating panoramic images, especially a device and method for generating multi-viewpoint panoramic images of plane-dominated scenes. Background technique [0002] In recent years, image stitching technology has been used more and more in both daily life and business. For example, a user may use a camera to capture partial images around a certain location, and then use image stitching technology to stitch these partial images together to form a panoramic image of the location. Or, use the camera on the mobile phone to take multiple pictures with a small field of view, and then use image stitching technology to stitch these images together to form a picture with a large field of view. [0003] For example, Non-Patent Document 1 (M.Shi, and J.Y.Zheng, A Slit Scanning Depth of Route Panorama from Stationary Blur, Proc.of CVPR, Vol.1, pp.1047-1...

AI Technical Summary

Problems solved by technology

[0006] However, the problem with the method proposed in the above-mentioned Non-Patent Document 1 is that the formed panoramic image is distorted as the depth of field changes. Although some distortion can be eliminated by adjusting the width of the narrow strips, the depth of field changes along the vertical axis of the image. In the case of , the resulting depth of field distortion is difficult to eliminate

In addition, it is also very difficult for ordinary users to obtain high-speed video cameras

[0007] In addition, the problem with the method proposed in the above-mentioned non-patent document 2 is that this method can only deal with roughly flat scenes, and it is up to the user to determine the planar scene in the picture.

[0008] In addition, the problem with the method proposed in the above-mentioned non-patent document 3 is that the straight lines in the adjacent images become curves in the overlapping area, so this method can only stitch the images in the non-overlapping area

[0009] Therefore, it is difficult to accurately stitch images together due to the inability to capture accurate depth data for any one scene image, especially in the case of multiple overlapping objects taken from different angles

Images