Research Image Mosaic Algorithm Based on Improved SIFT Feature Matching
-
摘要:
基于传统的SIFT特征点匹配方法和图像像素级融合的思想, 提出一种改进的SIFT特征点匹配的图像拼接算法.首先该算法在特征提取的过程中加入Harris角点算子, 筛选出鲁棒性较强的点; 其次采用基于圆形窗口的48维向量来进行特征降维, 并借助匹配特征点对之间的几何一致性来对特征点进行粗提纯, 提高算法运行效率; 最后采用重叠区域线性过渡融合算法对图像进行平滑过渡, 消除拼接缝隙.实验验证了该算法的鲁棒性和快速性.
Abstract:Based on traditional SIFT feature point matching method and image pixel level fusion, an improved SIFT feature matching algorithm is proposed. Firstly the algorithm in the feature extraction process with Harris corner detector and picks out robust points; Followed use of 48 dimensional vector based on a circular window to dimension reduction and the feature points are refined by the geometrical consistency of the matching feature points, to improve the efficiency of the algorithm. Finally, the overlapped area linear transition fusion algorithm of image smoothing the transition to eliminate the splicing gap. The experiment verifies the robustness and rapidity of the proposed method.
-
Key words:
- image mosaic /
- Harris corner /
- SIFT feature /
- RANSAC algorithm /
- image fusion
-
[1] 宋佳乾, 汪西原. 基于改进SIFT特征点匹配的图像拼接算法[J]. 计算机测量与控制, 2015, 23(2): 512-515. doi: 10.3969/j.issn.1671-4598.2015.02.053 [2] 焦丽龙, 韩燮, 李定主. 改进的基于特征点匹配的图像拼接融合算法[J]. 计算机工程与设计, 2014, 35(3): 918-922. doi: 10.3969/j.issn.1000-7024.2014.03.035 [3] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. doi: 10.1023/B:VISI.0000029664.99615.94 [4] 王田甲, 刘国荣. SIFT改进算法在图像配准中的应用[J]. 微电子学与计算机, 2011, 28(5): 184-188. https://www.cnki.com.cn/Article/CJFDTOTAL-WXYJ201105044.htm [5] 尚明姝. 基于改进SIFT特征匹配的快速图像拼接算法[J]. 微电子学与计算机, 2014, 31(1): 64-67. https://www.cnki.com.cn/Article/CJFDTOTAL-WXYJ201401016.htm [6] 王小平, 王建勇, 杨埙. 基于Sobel算子和改进SURF算法的图像拼接方法[J]. 电视技术, 2014, 38(13): 43-46. doi: 10.3969/j.issn.1002-8692.2014.13.012 [7] 胡同喜, 牛雪峰, 谭洋, 等. 基于SURF算法的无人机遥感影像拼接技术[J]. 测绘通报, 2015, 60(1): 55-58. https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201501014.htm [8] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors[C]// Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Washington DC, USA, 2004: 511-517. [9] 王鹤, 谢刚. 基于PCA-SIFT特征的目标识别算法[J]. 电视技术, 2013, 37(15): 30-32. doi: 10.3969/j.issn.1002-8692.2013.15.009 -
下载:
点击查看大图
计量
- 文章访问数: 931
- HTML全文浏览量: 339
- PDF下载量: 27
- 被引次数: 0
