基于图像深度信息的尺度不变特征变换算法误匹配点对剔除

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3554-3559.

基于图像深度信息的尺度不变特征变换算法误匹配点对剔除

刘政¹,刘本永²

1. 贵州大学计算机科学与技术学院,贵阳 550025
2. 贵州大学大数据与信息工程学院,贵阳 550025

收稿日期:2014-06-30 修回日期:2014-08-26 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 刘政
作者简介:刘政(1990-),男,湖北黄冈人,硕士研究生,主要研究方向:图像处理、模式识别；刘本永(1966-),男,贵州兴仁人,教授,博士生导师,博士,主要研究方向:图像处理、模式识别。
基金资助:
国家自然科学基金资助项目;科技部国际合作项目;贵州省工业科技攻关项目;教育部高等院校博士点基金资助项目;贵州大学研究生创新基金资助项目

Removal of mismatches in scale-invariant feature transform algorithm using image depth information

LIU Zheng¹,LIU Yongben²

1. College of Computer Science and Technology, Guizhou University, Guiyang Guizhou 550025, China;
2. College of Big Data and Information Engineering, Guizhou University, Guiyang Guizhou 550025, China

Received:2014-06-30 Revised:2014-08-26 Online:2014-12-01 Published:2014-12-31
Contact: LIU Zheng

摘要/Abstract

摘要：

特征点匹配是基于特征点的图像配准技术中的一个重要环节。针对现有基于尺度不变特征变换(SIFT）图像配准技术特征点匹配不理想,也无法较客观、快速地筛选正确匹配点对的问题,提出结合图像深度信息进行特征点误匹配筛选剔除的方法。该算法首先根据模糊聚焦线索和机器学习算法估计出待配准图像的深度信息图,再提取SIFT特征点,并在特征点匹配环节利用随机抽样一致性(RANSAC)算法迭代循环,结合深度局部连续性的原理来进一步提高匹配精度。实验结果表明,该算法具有很好的误匹配点对剔除功能。

Abstract:

Feature point matching is of central importance in feature-based image registration algorithms such as Scale-Invariant Feature Transform (SIFT) algorithm. Since most of the existed feature matching algorithms are not so powerful and efficient in mismatch removing, in this paper, a mismatch removal algorithm was proposed which adopted the depth information in an image to improve the performance. In the proposed approach, the depth map of an acquired image was produced using the clues of defocusing blurring effect, and machine learning algorithm, followed by SIFT feature point extraction. Then, the correct feature correspondences and the transformation between two feature sets were iteratively estimated using the RANdom SAmple Consensus (RANSAC) algorithm and exploiting the rule of local depth continuity. The experimental results demonstrate that the proposed algorithm outperforms conventional ones in mismatch removing.

中图分类号:

TP391.4

刘政刘本永. 基于图像深度信息的尺度不变特征变换算法误匹配点对剔除[J]. 计算机应用, 2014, 34(12): 3554-3559.

LIU Zheng LIU Yongben. Removal of mismatches in scale-invariant feature transform algorithm using image depth information[J]. Journal of Computer Applications, 2014, 34(12): 3554-3559.

参考文献

［1］BROWN L G. A survey of image registration techniques［J］. ACM Computing Surveys, 1992, 24(4): 325-376.
［2］HARRIS C, STEPHENS M. A combined corner and edge detector［C］// Proceedings of the 4th Alvey Vision Conference. Manchester: Alvey Vision Club, 1988: 147-151.
［3］FONSECA L M G, COSTA M H M. Automatic registration of satellite images［C］// Proceedings of the Brazilian Symposium on Computer Graphic and Image Processing. Piscataway: IEEE, 1997: 219-226.
［4］TON J, JAIN A K. Registering landsat images by point matching［J］. IEEE Transactions on Geoscience and Remote Sensing, 1989, 27(5): 642-651.
［5］FISCHLER M, BOLLES R. Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography［J］. Communication of ACM, 1981, 24(6): 381-395.
［6］TORR P H S, ZISSERMAN A. MLESAC: a new robust estimator with application to estimating image geometry［J］. Computer Vision and Image Understanding, 2000, 78(1): 138-156.
［7］ZHUO S J, SIM T. On the recovery of depth from a single defocused image［J］. Computer Analysis of Images and Patterns, 2009, 44(9): 1852-1858.
［8］PENTLAND A P. A new sense for depth of field［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(4): 523-531.
［9］KONRAD J, WANG M, ISHWAR P. 2D-to-3D image conversion by learning depth from examples［C］// Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2012: 16-22.
［10］KONRAD J, BROWN G, WANG M, et al. Automatic 2D-to-3D image conversion using 3D examples from the Internet［C］// Proceedings of SPIE: Stereoscopic Displays and Applications. Bellingham: SPIE, 2012: 82880F1-82880F12.
［11］DALAL N, TRIGGS B. Histograms of oriented gradients for human detection［C］// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2005: 886-893.
［12］LIU C, YUEN J, TORRALBA A. Sift flow: dense correspondence across scenes and its applications［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(5): 978-994.
［13］YUAN Z, YAN P M, LI S. Super resolution based on scale invariant feature transform［C］// Proceedings of the 2008 International Conference on Audio, Language and Image Processing. Piscataway: IEEE, 2008: 1550-1554.
［14］SONKA M, HLAVAC V,BOYLE R. Image processing, analysis, and machine vision［M］. AI H, WU B, translated. 2nd ed. Beijing: Posts and Telecom Press, 2003: 310-312. (SONKA M, HLAVAC V, BOYLE R. 图像处理、分析与机器视觉［M］.艾海舟,孟小峰,译.2版.北京:人民邮电出版社,2004.310-312.)
［15］SILBERMAN N, KOHLI P, HOIEM D, FERGUS R. Indoor segmentation and support inference from RGBD images［DB/OL］. ［2012-11-13］.http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html.

[1]	罗圣钦陈金怡李洪均. 基于注意力机制的多尺度残差UNet实现乳腺癌灶分割[J]. 计算机应用, 0, (): 0-0.
[2]	杨鼎康黄帅王顺利翟鹏李一丹张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0.
[3]	秦庭威赵鹏程秦品乐曾建朝柴锐黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0.
[4]	鲁永帅唐英杰马鑫然. 基于深度特征融合的无纺布低对比度浆丝缺陷检测方法[J]. 计算机应用, 0, (): 0-0.
[5]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[6]	许学斌, 张佳达, 刘伟, 路龙宾, 赵雨晴. 融合空间和通道特征的高精度乳腺癌分类方法[J]. 计算机应用, 2021, 41(10): 3025-3032.
[7]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[8]	魏淳武, 赵涓涓, 唐笑先, 强彦. 基于多时期蒸馏网络的随访数据知识提取方法[J]. 计算机应用, 2021, 41(10): 2871-2878.
[9]	韩建栋, 李晓宇. 基于多尺度特征融合的行人重识别方法[J]. 计算机应用, 2021, 41(10): 2991-2996.
[10]	张凯悦, 张鸿. 基于注意力机制网络的航运监控图像识别模型[J]. 计算机应用, 2021, 41(10): 3010-3016.
[11]	李自强, 王正勇, 陈洪刚, 李林怡, 何小海. 基于外观和动作特征双预测模型的视频异常行为检测[J]. 计算机应用, 2021, 41(10): 2997-3003.
[12]	高世伟, 张长柱, 王祝萍. 基于可分离金字塔的轻量级实时语义分割算法[J]. 计算机应用, 2021, 41(10): 2937-2944.
[13]	卓禹心, 韩素雅, 张榆锋, 李支尧, 董毅峰. 基于超声谐波包络Nakagami参数图像的微波消融区域自动分割方法[J]. 计算机应用, 2021, 41(10): 3089-3096.
[14]	李敬虎邢前国郑向阳李琳王丽丽. 基于深度学习的无人机影像夜光藻赤潮提取方法[J]. 计算机应用, 0, (): 0-0.
[15]	任炜白鹤翔. 基于全局与局部的多标签图像分类方法[J]. 计算机应用, 0, (): 0-0.