Method for splicing videos in real time based on SURF (Speeded UP Robust Features) algorithm

Abstract

The invention discloses a method for splicing videos in real time and belongs to technical field of video image processing. The method computes the overlapped area of video frame images to be spliced by using a phase correlation method, improves a SURF (Speeded UP Robust Features) algorithm, simplifies the generation process of a characteristic point descriptor in the SURF algorithm, reduces the dimensionality of the descriptor, extracts the characteristic points of the overlapped area of the video frames by using the improved SURF algorithm. The invention provides an image registration method based on characteristic block matching to match the characteristic points, decrease calculated amount, increase computational efficiency, and quickly solve an image conversion model by using the characteristic block matching. Finally the invention provides a projection matrix updating method based on a correlation coefficient. The projection matrix updating method is used for updating a projection matrix, prevents erroneous splicing results, and fusing the video frame images so as to splice the videos in real time.

Description

technical field [0001] The invention relates to a video splicing method, which splices video streams from two cameras in real time, and belongs to the technical field of image and video processing. Background technique [0002] Video stitching is to stitch multiple videos with partial overlapping areas into a wide-field, high-resolution panoramic video. It is developed on the basis of image stitching and is an application and extension of image stitching technology. Video stitching technology is widely used in intelligent monitoring, video conferencing, medical microscope video, aerial video and other fields. [0003] Video stitching is to stitch the video streams captured by multiple cameras into a panoramic video. Different from image splicing, video splicing has relatively high time requirements, so the existing video splicing methods all take into account the time complexity, but the real-time performance is relatively poor. Zheng M et al. [see literature Zheng M, Chen...

AI Technical Summary

Problems solved by technology

Zhang Chaowei et al [Refer to the literature: Zhang Chaowei, Zhou Yan, Wang Yaokang, Cheng Yan. Video stitching method based on SIFT feature tracking and matching [J]. Computer Engineering and Application. 2008,44(10):169-172] through the adjacent The inter-frame feature motion estimation obtains the matching features of subsequent frames, which speeds up the splicing speed, but it can only reach 5 frames per second

Images