基于图像拼接技术的动漫视频生成方法  

A Method for Generating Anime Videos Based on Image Stitching Technology

作　　者：马景雯 吴颖 MA Jingwen;WU Ying(Maanshan Normal College,Maanshan Anhui 243041,China;Baoxin Software(Anhui)Co.,LTD.,Maanshan Anhui 243000,China)

机构地区：[1]马鞍山师范高等专科学校,安徽马鞍山243041 [2]宝信软件(安徽)股份有限公司,安徽马鞍山243000

出　　处：《长春工程学院学报（自然科学版）》2024年第1期96-101,共6页Journal of Changchun Institute of Technology：Natural Sciences Edition

基　　金：安徽省2024年度优秀青年教师培育项目(YQYB2023118);2022年度安徽省职成教学会教学研究项目(Azcj2022205);2021年安徽省高校人文社科学项目(SK2021A0892)。

摘　　要：针对在动漫图像拼接过程中出现的运算量大、速度慢、特征点提取精度低、维度高以及图像拼接效果差等问题,研究基于图像拼接技术的动漫视频生成方法。通过均值滤波预处理动漫图像,去除图像中的噪声和干扰后,采用加速稳健特征(SURF)算法提取滤波后动漫图像的特征点,经边缘相似匹配法完成图像特征点匹配后,利用加权平滑算法融合匹配后的图像,获得全景图,并将其导入Maya软件生成动漫视频。试验表明:该方法提取特征点精度高、维度低、运算量小、速度快,图像拼接效果清晰、连接紧密、过渡自然、没有色差,生成的动漫视频可以达到更加精美逼真的视觉效果。Aiming at the problems of high computational complexity,slow speed,low accuracy of feature point extraction,high dimensionality,and poor image stitching effect in the process of anime image stitching,a method for generating anime videos based on image stitching technology is studied.By using mean filtering to preprocess anime images,noise and interference are removed from the images.Then,the Accelerated Robust Feature(SURF)algorithm is used to extract the feature points of the filtered anime images.After completing image feature point matching using edge similarity matching method,the weighted smoothing algorithm is used to fuse the matched images to obtain a panoramic image,which is then imported into Maya software to generate anime videos.Experiments show that this method has high accuracy,low dimensionality,low computational complexity,and fast speed in extracting feature points.The image stitching effect is clear,tightly connected,the transition is natural,and there is no color difference.The generated anime video can achieve a more exquisite and realistic visual effect.

关 键 词：图像拼接技术 动漫视频 动画制作 特征点提取 图像匹配 图像融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]