【摘 要】
：
This paper designed a kind of optimization algorithm for image registration.By combining with cultural particle swarm optimization (CPSO),a novel image registration algorithm is outlined in this paper
【机 构】
：
State Key Laboratory of Mechanics and Control of Mechanical Structures,Nanjing University of Aeronau
【出 处】
：
2014全国理论计算机科学学术年会
论文部分内容阅读
This paper designed a kind of optimization algorithm for image registration.By combining with cultural particle swarm optimization (CPSO),a novel image registration algorithm is outlined in this paper.In the algorithm,the search space was divided into two spaces,group space and belief space.In the algorithm,the search space was divided into two spaces,group space and belief space.Group space is the main space and evolved with self-adapted PSO.Particles of group space not only track individual extrema and global extrema to update themselves,but also exchange with the best individuals in belief space to speed up the convergence rate,which overcome the problems in image registration such as the large computation complexity,slow search speed and so on.A wealth of tests show that the proposed algorithm has better registration accuracy and robustness compared with existing PSO registration algorithm.
其他文献
针对肺部图像中边缘等重要特征与背景对比度较低这一问题,本文做了以下三点改进:一,采用基于小波变换的增强算法对图像进行增强,提高图像对比度;二,在数学形态学的基础上,结合结构元素的三个基本选取原则,选取适合于肺部图像的全方位多尺度结构元素,并对一般的膨胀腐蚀型边缘检测算子进行改进;三,对最终进行加权求和的权值计算方法进行改进,将峰值信噪比(PSNR)融入权值中,最后采用选取的结构元素和改进的算子对峰
本文提出了一种符合人眼视觉感知的多视点视频码率控制算法,算法分为四层,分别是视点层、GOP(GroupOfPictures)层、帧层、宏块层.在视点层,采用预先编码一个GOP的方式来确定视点间的码率分配比例;在GOP层,根据HBP(HierarchicalBPictures)结构的特点计算每个GOP的初始量化参数和目标比特数;在帧层,通过预测帧复杂度来确定每帧的目标比特数;在宏块层,根据人眼视觉感
针对移动信道具有多径传播、噪声干扰强等特点,压缩视频流容易发生丢包现象,进而严重影响视频解码质量,因此必须从移动终端设备的实际应用角度出发,尽可能的降低计算复杂度,采取有效的错误隐藏技术提高解码端视频的重建质量.首先,分析了移动立体视频主流的编码结构;然后,基于宏块丢失和整帧丢失两个方面,分别按照隐藏方法对现有的移动立体视频错误隐藏技术进行了研究与分析;最后,提出了移动立体视频错误隐藏进一步研究的
基于高感知质量的视频流的需求,如何对视频流的用户体验质量进行有效而准确的评估成为目前研究的一个热点.本文论述了基于视频流的用户体验质量的预测方法,重点阐述了几种典型的QoE预测模型.首先,对影响用户体验质量的因素进行了分析并指出存在的问题;然后,对用户体验质量的不同预测方法进行了分析和论述;最后,就网络视频流的用户体验质量预测方法的进一步发展提出了若干技术与研究展望.
语音识别作为人机语音通信的一种重要技术手段,其产品在人机交互应用中所占比例越来越大,但其程序繁琐运行时间长是影响其实用化的主要问题.开放式多媒体应用平台OMAP有非对称双核结构优势,但双核间的通讯问题是影响其性能的一项关键技术.DSPGateway作为一种双核通讯架构,具有功能强大、使用灵活等优点,但目前并未得到广泛使用.为此,本论文以DSPGateway为软件架构平台,以OMAP5912为系统硬
The application layer of Distributed Denial of Service (DDoS) has the characteristics of low rate,legitimate messages.The existing methods are mainly based on supervised learning which needs enough la
Over past decades,there has been more and more large scale sensors deployed in a wide range of application areas.Due to the innate imprecision of sensor observations,researchers devote to find an effi
With the rapid development of the Internet of Things,adaptive technology for the Internet of Things has gained a great deal of attention.Environment perception as an technology to support adaptive net
Routing algorithm with more flexibility and fewer virtual channels is essential for high performance multicomputer systems.For three-dimensional mesh-connected networks,the traditional planar-adaptive
It is well-known that model combination can improve prediction performance of regression model.We investigate the model combination of Support Vector Regression (SVR) with regularization path in this