基于RANSAC的PCA-SIFT立体匹配方法研究
The Research of PCA-SIFT Stereo Matching Method Based on RANSAC

作者: 刘奥丽 * , 肖永强 , 王子维 , 章刘斌 :武汉工程大学计算机科学与工程学院,湖北 武汉; 王海晖 :智能机器人湖北省重点实验室(武汉工程大学),湖北 武汉;

关键词: 立体匹配SIFTPCA-SIFTRANSACStereo Matching SIFT PCA-SIFT RANSAC

摘要:
针对传统的SIFT (Scale-Invariant Feature Transform)匹配算法数据量大,耗时长的问题,采用主成分不变特征变换PCA-SIFT (Principal Component Analysis, PCA)匹配算法。PCA-SIFT匹配算法将传统SIFT算法中的直方图法换做主元分析法,降低了传统SIFT特征描述符的维数,减少了数据量,提高了匹配效率。首先提取出两幅待匹配图像中的所有特征描述子,其次将提取出的特征描述子采用距离比阈值筛选出匹配点对,再采用RANSAC (Random Sample Consensus)法消除错配,最后得到精确的匹配结果。实验结果表明,PCA-SIFT + RANSAC算法较稳定、精确、快速。

Abstract: Principal Component Analysis of Traditional Scale-Invariant Feature Transform (PCA-SIFT) is used instead of Traditional Scale-Invariant Feature Transform (SIFT) method which has a large amount of data, and needs long time. Principal Component Analysis of Traditional Scale-Invariant Feature Transform (PCA-SIFT) changed histogram method for main element analysis method, effectively reducing the dimension of the feature descriptor, decreasing data, improving the matching rate. Firstly we extract all the feature descriptors from the two matching images, and match them with the enulidean distance ratio, and then we use the Random Sample Consensus (RANSAC) algorithm to remove false matching. The experimental results show that the PCA-SIFT + RANSAC algorithm is more stable, more accurate and more rapid.

文章引用: 刘奥丽 , 王海晖 , 肖永强 , 王子维 , 章刘斌 (2016) 基于RANSAC的PCA-SIFT立体匹配方法研究。 图像与信号处理, 5, 105-111. doi: 10.12677/JISP.2016.53014

参考文献

[1] Ke, Y. and Sukthankar, R. (2004) PCA-SIFT: A More Distinctive Representation for Local Image Descriptors. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, 27 June-2 July, 506-513.

[2] Juan, L. and Gwun, O. (2009) A Comparison of SIFT, PCA-SIFT and SURF. International Journal of Image Processing, 3, 143-152.

[3] Fischler, M.A. and Bolles, R.C. (1981) Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartogramphy. Communications of the ACM, 24, 381-395. http://dx.doi.org/10.1145/358669.358692

[4] 马莉, 韩燮. 主成分分析法(PCA)在SIFT匹配算法中的应用[J]. 电视技术, 2012, 36(1): 129-132.

[5] Lowe, D.G. (2004) Distinctive Image Features from Scale-Invariant Keypoints. Journal of Computer Vision, 60, 91-110. http://dx.doi.org/10.1023/B:VISI.0000029664.99615.94

[6] Plum, J.P.W., Maintz, J.B.A. and Viergever, M.A. (2011) Mulual Information Matching in Multiresolution Contexts. http://www.docin.com/p-43905533.html

[7] Bay, H., Ess, A., Tuytelaars, T., et al. (2008) Speeded-Up Robust Features (SURF). International Journal on Computer Vision and Image Understanding, 110, 346-359. http://dx.doi.org/10.1016/j.cviu.2007.09.014

[8] 甄艳, 刘学军, 王美珍. 一种改进RANSAC的基础矩阵估计方法[J]. 测绘通报, 2014(4): 39-43.

[9] Mikolajczy, K. and Schmid, C. (2005) A Performance Evaluation of Local Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 1615-1630. http://dx.doi.org/10.1109/TPAMI.2005.188

分享
Top