Behavior splicing method of video scene

Abstract

The invention relates to a behavior splicing method of a video scene, so that video scene splicing and behavior splicing of moving objects in different videos can be realized. The method comprises the following steps that: on the basis of image registration, meshing is carried out on a video image so as to form an image block node set and an image block label set; an image block clustering algorithm is utilized to generate an image block label type representative candidate set for each of the image block node; and a two dimensional Markov random field and a three dimensional Markov random fields of the image block node are constructed and solved, so that a static background and a dynamic background are generated; on the basis of extraction of tracks of moving objects, track similarity and position similarity between moving objects of different videos are calculated, so that a splicable property of moving object behaviors is obtained and video alignment is provided at time and space; and a poisson image fusion algorithm is utilized to fuse a panoramic dynamic background video and motions, so that a video scene after behavior splicing is generated.

Description

technical field [0001] The invention relates to the fields of computer vision, video processing and virtual reality, and is a video scene behavior splicing method, specifically a method for recombining and merging moving objects in multiple input videos into a panoramic video scene according to behaviors . Background technique [0002] In the process of generating a virtual scene based on video material, users need to obtain a larger scene as a background, or obtain a higher resolution video image of a large scene. Because the user can only shoot a small part of a large scene by rotating or moving the camera due to the limitation of the equipment and the site in the process of shooting the video / image. Therefore, before the birth of the computer, people began to manually stitch together the captured images. With the development of aerial photography, due to the limitation of the flight height of the aircraft and the requirements for the resolution of the photos, people stil...

AI Technical Summary

Problems solved by technology

Methods based on image feature line segments or feature regions largely rely on image segmentation and edge extraction. These two operations are inherently difficult and computationally intensive. feature line break), it is likely to lead to the failure of image segmentation and edge extraction operations, which makes the efficiency and robustness of the registration algorithm not high, restricting the scope of application of these methods

Images