[1]游春芝,陈光喜. 改进的梯度投影电子稳像算法[J].计算机技术与发展,2015,25(10):84-83.
　YOU Chun-zhi,CHEN Guang-xi. Improved Gradient Projection Algorithm of Electronic Image Stabilization[J].,2015,25(10):84-83.
点击复制

 改进的梯度投影电子稳像算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年10期
页码:
84-83
栏目:
智能、算法、系统工程
出版日期:
2015-10-10

文章信息/Info

Title:
 Improved Gradient Projection Algorithm of Electronic Image Stabilization
文章编号:
1673-629X（2015)10-0084-04
作者:
 游春芝; 陈光喜
 桂林电子科技大学 数学与计算科学学院
Author(s):
 YOU Chun-zhi; CHEN Guang-xi
关键词:
 ; 电子稳像; 运动估计; 梯度投影; 运动补偿
Keywords:
 ; electronic image stabilization; motion estimation ; gradient projection; motion compensation
分类号:
TP391.14
文献标志码:
A
摘要:
 传统的灰度投影算法是通过视频图像序列的像素值的灰度变化规律来获得图像序列帧间的全局运动矢量，然而该算法在灰度值单一，并且存在小运动物体时，稳像效果不佳，易造成误差。进而在深入分析传统灰度投影算法的基础上，提出了一种分区的梯度投影算法。该算法先对灰度图像进行预处理，继而将图像分成4个区域，若图像存在运动物体，此时可以剔除有运动物体的宏块，然后在每一个区域内用Sobel算子计算其水平、垂直梯度投影，进一步获得每个区域的局部运动矢量，最后采用均值方法得到全局运动矢量。实验结果表明，该方法在处理灰度值单一且存在运动物体的图像时，可以有效地提高精度，且通过分区的方法可以有效地降低运动物体的干扰，从而提高了算法精度。
Abstract:
 The traditional gray projection algorithm obtains the global motion vector of inter-frames in image sequence by the gray pixel values of the video image sequence. However,the image stabilization effect of the algorithm is poor for the image with moving objects and single gray value. Based on analyzing the traditional gray projection algorithm in depth,propose an improved gradient projection algo-rithm. Firstly,the gray image is preprocessed with the Gauss function. Then the image is divided into four regions. If the image has mov-ing objects,so can remove the macroblock with the moving objects. Then,use the Sobel operator to calculate the horizontal and vertical gradient projection,further to obtain the local motion vector. Finally by average method,get the global motion vector. The experimental results show that the method for the image with moving objects and single gray value can improve the estimation accuracy of motion vec-tor. And it can effectively reduce the interference of moving objects by partitioning,which effectively improves the accuracy of the algo-rithm.

相似文献/References:

[1]张宇 黄亚博 焦建彬.一种适用于高分辨率图像的实时电子稳像算法[J].计算机技术与发展,2009,(03):9.
　ZHANG Yu,HUANG Ya-bo,JIAO Jian-bin.A Real Time Stabilization Algorithm for High Resolution Video[J].,2009,(10):9.
[2]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(10):1.
[3]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(10):5.
[4]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(10):13.
[5]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(10):21.
[6]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(10):25.
[7]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(10):29.
[8]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
　LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(10):34.
[9]尚福华,李想,巩淼. 基于模糊框架-产生式知识表示及推理研究[J].计算机技术与发展,2014,24(07):38.
　SHANG Fu-hua,LI Xiang,GONG Miao. Research on Knowledge Representation and Inference Based on Fuzzy Framework-production[J].,2014,24(10):38.
[10]叶偲,李良福,肖樟树. 一种去除运动目标重影的图像镶嵌方法研究[J].计算机技术与发展,2014,24(07):43.
　YE Si,LI Liang-fu,XIAO Zhang-shu. Research of an Image Mosaic Method for Removing Ghost of Moving Targets[J].,2014,24(10):43.

更新日期/Last Update: 2015-11-12