节点文献

图像融合在视频交通信息检测中的应用研究

Application Research of Image Fusion Technology in Video Traffic Information Detection

【作者】 李佳奇

【导师】 杨兆选;

【作者基本信息】 天津大学 , 信号与信息处理, 2009, 硕士

【摘要】 近年来,智能交通系统(ITS)产业在世界范围内蓬勃发展,视频交通信息检测系统是ITS的重要组成部分,它利用图像处理的方法采集交通管理所需要的信息。针对信息采集的需要,本文研究了基于小波分析的图像融合算法及其在交通检测系统中的应用,目的在于提高智能交通系统的服务质量。图像融合技术是当代数字图像处理领域的前沿课题之一,而目前基于小波变换的图像融合技术是信息融合领域的热点问题。本文首先简要介绍了国内外视频交通信息检测系统的发展概况及系统的设计方案;然后,对小波变换和图像融合的基本理论、方法及现状做了详细阐述;最后,讨论了基于小波变换的图像融合算法及其在视频交通信息检测系统中的应用。论文重点研究了区域化图像融合设计方案,即在设计视频车辆检测系统时,针对小波图像融合算法计算量大、难以实时处理的难点,只对虚拟检测线覆盖的图像区域进行融合,而不处理与车辆检测无关的区域。与对整幅图像进行的融合相比,区域化图像融合只关注感兴趣区域的图像信息,具有运算量小等特点,适用于对实时性要求高的系统。实验表明,将区域化图像融合应用于视频交通信息检测系统,较好地解决了小波图像融合算法计算量大难以进行实时视频处理的难题。实验结果表明,论文工作研究的区域化图象融合车辆检测算法有效地提高了检测系统的检测正确率,具有较大的应用价值。

【Abstract】 Recent years, Intelligent Transportation System (ITS) technology has made a great progress worldwide. The Video Traffic Information Detection System is an important part of the ITS. The system is used to acquire any needed information of traffic management using image processing technology. For the need of information acquiring, an image fusion scheme based on the wavelet transform are researched, aiming for improving the quality of the system.Image fusion is one of the advanced subjects both in the field of digital image processing and in that of data fusion. The image fusion based on wavelet transform is popular at the present time.Firstly, the paper introduces the general situation of the development of the ITS both in domestic and overseas. Then, the theory and methods of wavelet transform and image fusion are discussed in detail. Finally, the application of wavelet theory in image fusion scheme was analyzed, it was also used for ITS.A design proposal of partition image fusion is brought forward in this dissertation. Focusing on the computational complexity of wavelet domain image fusion algorithm and its low real-time capability, this dissertation proposes a new method that fuses the given partition of images which is covered by the virtual detection line and ignores the the rest partition of this image. Comparing with fusion of the whole image, the partition image fusion has low computational complexity. Experimental results show that partition image fusion method applied in the vehicle detection system not only improves the image quality, but also meets the time-constraints of system requirements.The result of experiment indicates that the computational complexity of wavelet domain image fusion algorithm which is researched in dissertation improves the accuracy rate of detection system effectively, and it also has great value in application.

  • 【网络出版投稿人】 天津大学
  • 【网络出版年期】2011年 S2期
节点文献中: 

本文链接的文献网络图示:

本文的引文网络