系统仿真学报 ›› 2016, Vol. 28 ›› Issue (1): 63-69.

• 仿真系统与技术 • 上一篇    下一篇

基于视频的静态场景与运动物体三维融合研究

何坤金1, 王淋1, 刘建新2, 陈正鸣1, 陈小中1   

  1. 1.河海大学物联网工程学院,江苏 常州 213022;
    2.宿迁市普元软件科技有限公司,江苏 宿迁 223800
  • 收稿日期:2014-09-01 修回日期:2015-05-12 发布日期:2020-07-02
  • 通讯作者: 何坤金(1974-),男,安徽芜湖,博士,副教授,研究方向为CAD&CG。
  • 基金资助:
    江苏省经信委项目(宿财工贸2014-3号); 常州市工业支撑项目(CE20140008); 中央高校基本科研业务费资助项目(BZX/13B101-33); 江苏省普通高校研究生科研创新计划项目(KYZZ15_0152)

Research of Merging Three-dimensional Static Scene and Moving Objects Based on Video

He Kunjin1, Wang Lin1, Liu Jianxin2, Chen Zhengming1, Chen Xiaozhong1   

  1. 1. College of IOT Engineering, Hohai University, Changzhou 213022, China;
    2. Puyuan Software Technology Co., LTD, Suqian 223800, China
  • Received:2014-09-01 Revised:2015-05-12 Published:2020-07-02

摘要: 针对含有运动物体的场景在三维实时呈现方面存在的困难,提出一种基于视频的静态场景与运动物体快速三维构建与融合方法。建立静态场景的三维模型,并对运动物体进行分类,生产参数化模型库;基于视频检测识别运动物体并提取其基本特征信息和动态特征信息;根据所提取运动物体的基本特征信息,从物体参数化模型库中提取类型相符的模型并对其进行实例化;根据所提取运动物体的动态特征信息,实现三维静态场景与运动物体模型的融合,并使运动物体能够根据监控视频实时变化。实验以运河航道为静态场景,船舶为运动物体验证所提方法。

关键词: 参数化模型库, 特征提取, 参数化设计, 模型融合

Abstract: Against the difficulty in three-dimensional real-time rendering of scene that contains moving objects, a video-based method in building and merging three-dimensional static scene and moving objects was proposed. According to the classification of moving objects, a three-dimensional static scene was established and a parameterized model base was produced. Based on the video, moving objects were detected and features (including basic features and dynamic features) were extracted. Based on basic features, corresponding type model in the parameterized model base was instantiated. Based on the dynamic features, the three-dimensional static scene and moving object models were merged and the moving objects could move according to the change of surveillance video. Experiment with the inland waterway as static scene, ships as moving objects verify the method.

Key words: parameterized model base, feature extraction, parametric design, model merge

中图分类号: