Sopc-based binocular video stitching device and binocular video stitching method

Abstract

The invention provides a binocular video splicing device based on an SOPC. The binocular video splicing device comprises an SOPC system making a NiosII soft-core processor as a core, wherein a pair of CMOS imaging sensors are connected with a pair of binocular video acquisition modules respectively through FPGA ports; the binocular video acquisition modules are connected with a binocular video storage module; one path of the output end of the binocular video storage module is connected with a binocular video output module through a feature extraction co-processor, and the other path of the output end of the binocular video storage module is connected with a binocular video display module; the binocular video output module is further respectively provided with the NiosII processor and an upper computer, and the binocular video display module is further connected with a VGA displayer. According to a binocular video splicing method, feature points are roughly matched through a Euclidean distance method, then partial mismatching points are extracted by means of a KNN method, a homograph matrix is calculated by the adoption of a RANSAC method at last, and real-time splicing for single-frame binocular video data is achieved through cylinder space conversion and linear weighing fusion.

Description

technical field [0001] The invention relates to binocular vision technology, in particular to an SOPC-based binocular video splicing device and a binocular video splicing method. Background technique [0002] As an important part of machine vision, binocular vision technology has always been a research hotspot in the fields of video stitching, industrial inspection and 3D reconstruction. In recent years, with the continuous development of binocular vision technology, traditional solutions based on video capture cards and host computers have been unable to meet user needs due to shortcomings such as high cost, poor versatility, and slow processing speed, especially in the binocular video capture and transmission part. Whether polling or time-division multiplexing is used, the existing design methods cannot meet the design requirements of the system in terms of synchronization and real-time performance. [0003] The patent document "A Two-way Video Fusion Processing Device Ba...

AI Technical Summary

Problems solved by technology

In recent years, with the continuous development of binocular vision technology, traditional solutions based on video capture cards and host computers have been unable to meet user needs due to shortcomings such as high cost, poor versatility, and slow processing speed, especially in the binocular video capture and transmission part. Whether polling or time-division multiplexing is adopted, the existing design methods cannot meet the design requirements of the system in terms of synchronization and real-time performance.

[0003] The patent document "A Two-way Video Fusion Processing Device Based on SOPC and Its Fusion Method" (Patent No. CN102523389A) proposes a method for realizing two-way video fusion through the SOPC system, but it still uses the traditional design method and does not incorporate The parallelism of FPGA and the advantages of SOPC in programmability are brought into play, and the synchronization and real-time performance cannot be guaranteed. Two-way video fusion only uses bilinear interpolation method, and the fusion effect is not good.

[0004] At this stage, most of the binocular video splicing devices are processed by the host computer, which cannot realize the embedded binocular video splicing device in the true sense, and the host computer software implements the video splicing algorithm, the execution efficiency is not high, and the real-time performance and splicing effect cannot be realized. balance

Images