基于ORB和改进的RANSAC图像拼接算法

摘要/Abstract

摘要： 传统的特征点匹配存在较多的误匹配,且效率不高。针对误匹配,提出了基于二值化互信息的筛选方法,可根据特征点的互信息判断特征点是否匹配正确。此外,用ORB算法提取的特征点分布在颜色变化区域,较为集中。但RANSAC算法得到的变换矩阵仅适用于特征点分布区域,使得拼接结果有误差。针对这个问题,文中用改进的RANASC算法,先筛选出内点,再用内点得到新的特征点,可以使特征点分散;且用迭代的方式得到最佳变换矩阵。实验结果表明,使用二值化互信息筛选特征点,提高了匹配的正确率,也增加了特征点匹配的数目;改进的RANSAC算法能够有效地解决特征点少且集中的问题,使得图像拼接的结果更准确。

关键词: RANSCAC, 互信息, 特征点分布, 图像拼接

Abstract: There are many mismatches in traditional feature point matching,and the efficiency is not high.Aiming at mismatching,this paper proposed a method of screening based on binary mutual information.According to the mutual information of feature points,the matching of feature points is judged correctly.In addition,the feature points extracted by ORB algorithm are distributed in the region of color change,which is more centralized.The transformation matrix obtained by RANSAC algorithm is only applicable to the region of feature points distribution,which makes the stitching result error.In order to solve this problem,this paper used the improved RANASC algorithm to screen out the interior points firstly,and then used the interior points to get the new feature points.In this way,feature points can be disper-sed,and the iterative method is used to get the best transformation matrix.The results show that when binary mutual information is used to screen feature points,it improves the accuracy of matching and increases the number of feature points matching.The improved RANSAC algorithm can effectively solve the problem of few and more concentrated feature points and make the result of image mosaic more accurate.

Key words: Feature point distribution, Image stitch, Mutual information, RANSCAC

中图分类号:

TP391

张美玉, 王洋洋, 侯向辉, 秦绪佳. 基于ORB和改进的RANSAC图像拼接算法[J]. 计算机科学, 2019, 46(11A): 294-298. https://doi.org/

ZHANG Mei-yu, WANG Yang-yang, HOU Xiang-hui, QIN Xu-jia. Image Stitching Algorithm Based on ORB and Improved RANSAC[J]. Computer Science, 2019, 46(11A): 294-298. https://doi.org/

参考文献

[1]LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[2]CALONDER M,LEPETIT V,OZUYSAL M,et al.BRIEF:Computingalocal binary descriptor very fast[J].IEEETransactionson Patten Analysis and Machine Intelligence,2012,34(6):1281-1298.
[3]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An efficient alternative to SIFT or SURF[C]∥International Conference on Computer Vision.IEEE Computer Society,2011,2564-2571.
[4]张岩,李建增,李德良,等.特征匹配算法鲁棒性与速度的对比分析.飞航导弹,2017(1):71-79.
[5]VIOLA P,WELLS W.Alignment by maximization of mutualin for mation[C]∥Proceedings of the 5th International Conference on Computer Vision.Boston:MA,1995:16-23.
[6]WU Y,MA W P.A Novel Point-Matching Algorithm Based on Fast Sample Consensus for Image Registration[J].IEEEGeoscience and Remote Sensing Letters,2015,12(1):43-47.
[7]ZENG Q H,CHEN Y.A fast matching method for large viewpoint changes images based on ORB algorithm[J].Control and Decision,2017,32(12):2233-2239.
[8]SHI B,HAN L,YAN H.Adaptive clustering algorithm based on KNN and density[J].Pattern Recognition Letters,2018,104:37-44.
[9]WANG L,CHEN Z.MR image registration based on an improved maximum mutual information[J].Journal of Biomedical Engineering,2012,29(2):201.
[10]张詹,张修如,基于信息熵的指纹图像二值化算法[J].计算机系统应用,2010(6):148-152.
[11]AMANKWAH A.Mutual Information for Image Registration[J].Computer technology and Application,2015,2(1):9-14.
[12]BENNASAR M,HICKS Y,SETCHI R.Feature selection using Joint Mutual Information Maximisation[J].Expert Systems with Applications,2015,42(22):8520-8532.
[13]ZHAO Y,JIANG J G,HONG R C.An optimized SIFT matching based on RANSAC[J].Opto-Electronic Engineering,2014,41(8):58-65.
[14]张古,穆铁英.改进的RANSAC基础矩阵估计算法[J].小型微型计算机系统,2016,37(9):2084-2087.

相关文章 15

[1]	雷阳, 姜瑛. 云计算环境下关联节点的异常判断 Anomaly Judgment of Directly Associated Nodes Under Cloud Computing Environment 计算机科学, 2021, 48(1): 295-300. https://doi.org/10.11896/jsjkx.191200186
[2]	王毛妮, 彭长根, 何文竹, 丁兴, 丁红发. 基于图论与互信息量的差分隐私度量模型 Privacy Metric Model of Differential Privacy via Graph Theory and Mutual Information 计算机科学, 2020, 47(4): 270-277. https://doi.org/10.11896/jsjkx.190400098
[3]	庞荣来,林静,张磊. 网格驱动的双向图像拼接算法 Grid-driven Bi-directional Image Stitching Algorithm 计算机科学, 2020, 47(3): 130-136. https://doi.org/10.11896/jsjkx.190100239
[4]	林朗, 张自力. 基于多头绒泡菌的贝叶斯网络结构学习 Bayesian Structure Learning Based on Physarum Polycephalum 计算机科学, 2019, 46(9): 206-210. https://doi.org/10.11896/j.issn.1002-137X.2019.09.030
[5]	郭鹏, 李仁发, 胡慧. 一种基于超图Markov链松弛的聚类学习方法 Clustering Method Based on Hypergraph Morkov Relaxation 计算机科学, 2019, 46(6A): 452-456.
[6]	彭晓冰, 朱玉全. 基于特征内相关和互信息的加权SVM算法 Weighted Support Vector Machine Algorithm Based on Inner-correlations and Mutual Information of Features 计算机科学, 2018, 45(12): 182-186. https://doi.org/10.11896／j.issn.1002-137X.2018.12.029
[7]	宋哲理, 王超, 王振飞. 基于MapReduce的多级特征选择机制 Multi-level Feature Selection Mechanism Based on MapReduce 计算机科学, 2018, 45(11A): 468-473.
[8]	卢嘉铭,朱哲. 基于GPU加速的实时4K全景视频拼接 Real-time 4K Panoramic Video Stitching Based on GPU Acceleration 计算机科学, 2017, 44(8): 18-21. https://doi.org/10.11896/j.issn.1002-137X.2017.08.003
[9]	李鹏,李英乐,王凯,何赞园,李星,常振超. 基于交互行为和连接分析的社交网络社团检测 Community Detection Based on User Interaction and Link Analysis in Social Networks 计算机科学, 2017, 44(7): 197-202. https://doi.org/10.11896/j.issn.1002-137X.2017.07.035
[10]	苏慧嘉,郑继明. 结合游程长度与共生矩阵的图像拼接篡改检测方法 Image Splicing Blind Detection Method Combined RLRN with GLCM 计算机科学, 2017, 44(6): 150-154. https://doi.org/10.11896/j.issn.1002-137X.2017.06.025
[11]	魏霖静,宁璐璐,练智超,代永强,王联国. 采用预编码的GSM网络最大互信息优化方法研究 Research on Maximum Mutual Information Optimization in GSM Networks with Precoding 计算机科学, 2017, 44(5): 71-74. https://doi.org/10.11896/j.issn.1002-137X.2017.05.013
[12]	刘哲,宋余庆,王栋栋. 自适应变异差分算法与Powell算法相结合的医学图像配准 Medical Image Registration Based on Self-adaptive DE Algorithm and Powell Algorithm 计算机科学, 2017, 44(11): 297-300. https://doi.org/10.11896/j.issn.1002-137X.2017.11.045
[13]	杨程,徐晓刚,王建国. 图像配准技术研究 Research on Importance of Image Mosaic Technology 计算机科学, 2016, 43(Z11): 133-135. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.028
[14]	瞿中,林嗣鹏,鞠芳蓉. 一种改进的降低扭曲误差的快速图像拼接算法 Improved Algorithm of Fast Image Stitching by Reducing Panoramic Distortion 计算机科学, 2016, 43(5): 279-282. https://doi.org/10.11896/j.issn.1002-137X.2016.05.053
[15]	钱揖丽,蔡滢滢. 采用无标注语料和词“粘连”剔除策略的韵律短语识别 Recognition of Prosodic Phrases Based on Unlabeled Corpus and “Adhesion” Culling Strategy 计算机科学, 2016, 43(2): 51-56. https://doi.org/10.11896/j.issn.1002-137X.2016.02.011

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed