Local registration parallel video stitching method and local registration parallel video stitching system

Abstract

The invention relates to a local registration parallel video stitching method and a local registration parallel video stitching system. The method comprises the steps of 1, carrying out three-dimensional coordinate view angle calibration, acquiring video images so as to obtain multi-channel video images, and decomposing the multi-channel video images into video data; 2, using received a plurality of Nth frame of data as current data, wherein the N is a natural number; 3, carrying out pre-processing on the current data, and acquiring a plurality of clipped video frames; 4, judging a neighboring relation of the clipped video frames, and establishing an adjacent frame spatial relation model according to the neighboring relation; executing a step 5, receiving (N+1)th frame of data to act as the current data, and executing the step 3; 5, carrying out registration on a plurality of video frames having a neighboring relation, and acquiring a homography matrix between the adjacent video frames; and 6, carrying out video scene stitching according to the homography matrix, and completing parallel video stitching. The method and the system provided by the invention can carry out stitching processing on multi-channel video efficiently and accurately, and are low in complexity, high in calculation speed, high degree of parallelism and good expansibility.

Description

technical field [0001] The invention relates to a video splicing method and system, in particular to a local registration parallel video splicing method and system, belonging to the technical field of computer image information processing. Background technique [0002] Video splicing technology is a large-scale video image processing technology that uses video splicing algorithms to splice multi-channel video data with overlapping areas, eliminate overlapping areas, and form wide-angle video images. Due to the limitations of physical factors of image acquisition equipment, current camera equipment cannot capture scenes within a wide field of view. And in daily life: in airports, docks, squares, traffic intersections and other large scenes with a wide view, it is usually necessary to display panoramic image information at the same time. Usually, the monitoring range can be expanded by arranging multiple camera devices, but the display of the scene is divided into multiple su...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem of insufficient real-time video splicing of full-frame registration detection in the prior art, the present invention proposes a local registration parallel video splicing method and system based on oFAST feature points that can efficiently and accurately splice multiple channels of video , the scheme adopts the calculation method of local registration in sub-regions, which has low complexity, fast calculation, high parallelism and good scalability; at the same time, the video frame registration algorithm runs in the CPU, and the fusion algorithm runs in parallel in the FPGA (Field- ProgrammableGateArray) programmable logic template, the program is parallelized to further improve the system processing speed

Images