[1]张凯[],杨红雨[][],兰时勇[][].基于CUDA的SIFT特征与拼接缝的全景图生成[J].计算机技术与发展,2015,25(09):22-26.
　ZHANG Kai[],YANG Hong-yu[][],LAN Shi-yong[][]. Panorama Generation of SIFT and Stitch Line Based on CUDA[J].,2015,25(09):22-26.
点击复制

基于CUDA的SIFT特征与拼接缝的全景图生成()
分享到：

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

卷:
25
期数:
2015年09期
页码:
22-26
栏目:
智能、算法、系统工程
出版日期:
2015-09-10

文章信息/Info

Title:
 Panorama Generation of SIFT and Stitch Line Based on CUDA
文章编号:
1673-629X（2015)09-0022-05
作者:
 张凯[1];  杨红雨[1][2];  兰时勇[1][2]
1. 四川大学 计算机学院；2.视觉合成图形图像技术国家重点学科实验室
Author(s):
 ZHANG Kai[1] ; YANG Hong-yu[1][2];  LAN Shi-yong[1][2]
关键词:
 ; 计算统一设备架构; SIFT特征; 图像拼接; 图像配准; 图像融合
Keywords:
 ; CUDA; SIFT feature; image mosaics; image registration; image fusion
分类号:
TP391.41
文献标志码:
A
摘要:
 针对大场景高清全景图的生成需求，提出了一种基于CUDA的SIFT特征与动态规划拼接缝的全景图生成方法。首先进行柱面投影保持各通道视频在重叠区域内成像的视觉一致性，并设计了基于CUDA的SIFT特征提取并行算法和基于RANSAC与特征点的变换模型鲁棒估计算法；然后通过基于HIS色彩空间与梯度空间的动态规划拼接缝实现相邻图像的缝合，并在缝合线两边采用基于三角函数的图像融合算法实现平滑过渡，最终生成高清晰度高分辨率的全景图。结果表明，该方法在满足图像无缝拼接精度的前提下，可消除重叠区域内的重影问题，并大幅度提高拼接速度。
Abstract:
 Aiming at the effect of high-definition panorama generation of large scenes,propose a panorama generation method based on dynamic programming seam and SIFT based on CUDA. Firstly,the visual consistency of the overlap regions is guaranteed by the cylindri-cal projection,also design a parallel algorithm of SIFT feature extraction based on CUDA and a robust parameter estimation algorithm based on RANSAC and feature points. Then,the adjacent images are stitched by dynamic programming stitch line based on HIS color space and gradient space. A trigonometric-based image fusion algorithm is used on both sides of the stitch line to realize the smooth tran-sition. The high-definition and high-resolution panorama is finally generated. The proposed method can eliminate the ghosting problem in the overlapping area and significantly improve the stitching speed,on the premise of high-accuracy seamless image mosaic.

相似文献/References:

[1]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(09):1.
[2]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(09):5.
[3]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(09):13.
[4]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(09):21.
[5]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(09):25.
[6]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(09):29.
[7]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(09):34.
[8]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(09):38.
[9]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(09):43.
[10]余松平[][],蔡志平[],吴建进[],等. GSM-R信令监测选择录音系统设计与实现[J].计算机技术与发展,2014,24(07):47.
　YU Song-ping[][],CAI Zhi-ping[] WU Jian-jin[],GU Feng-zhi[]. Design and Implementation of an Optional Voice Recording System Based on GSM-R Signaling Monitoring[J].,2014,24(09):47.

更新日期/Last Update: 2015-10-16