Preprocessing method of multi-viewpoint image

Abstract

The invention discloses a pretreatment method for multi-viewpoint image, which carries out the extremum detection to the object image and the source image in the scale space via the invariant scale characteristics transform algorithm, picks up the invariant scale characteristics transform eigenvector of the object image and the source image key points, acquires the accurate matching key point pair set of the object image and the source image by the feature matching algorithm and corrects the color of the source image by computing the multiplicative error and the additive error of the key point pair set, carries out the geometric calibration to the rectifying image after color correction by establishing the affine transformation between the key points, the advantages of which lies in that under the prerequisite of ensuring the accuracy of the multi-viewpoint image color correction and the geometric calibration, the invention greatly improves the robustness and the mapping accuracy of the color correction, reduces the complicatedness of the geometric calibration and enhances the coding performance of the multi-viewpoint image.

Description

technical field [0001] The invention relates to a method for processing multi-viewpoint images, in particular to a preprocessing method for multi-viewpoint images. Background technique [0002] In the real world, the visual content seen by the observer depends on the position of the observer relative to the observed object, and the observer can freely choose various angles to observe and analyze things. In traditional video systems, the real scene relative to a viewpoint is determined by the cameraman or director. Users can only passively watch the video image sequence captured by the camera at a single viewpoint, but cannot freely choose other viewpoints. To observe the real scene. These unidirectional video sequences can only reflect one side of the real-world scene. The free-viewpoint video system allows users to freely choose a viewpoint to watch any side within a certain range in real-world scenes, and is called the development direction of the next-generation video s...

AI Technical Summary

Problems solved by technology

However, if the multi-viewpoint image undergoes changes such as rotation, scaling, viewing angle transformation, and illumination transformation, or due to factors such as occlusion and noise, area matching and histogram matching cannot maintain good matchability, and the mapping accuracy is low.

[0006] Geometric calibration usually needs to obtain the internal parameters and external parameters of the camera to realize the transformation of the coordinate system, so as to achieve the goal of consistent geometric positions, but the computational complexity of this geometric calibration method is relatively high

Images