基于全局特征与局部特征的图像分级匹配算法研究及应用

摘要/Abstract

摘要： 移动机器人基于拓扑地图导航时要求图像特征提取与匹配算法具有高的精度和鲁棒性、良好的实时性，针对此，提出了基于全局特征和局部特征的图像分级匹配算法。首先对输入的待匹配图像应用改进的形状上下文算法提取全局特征与图像库中图像进行遍历粗匹配，得到与当前待匹配图像相似度最高的3幅图像并构建临时图像库;然后利用改进的SIFT算法提取输入图像局部特征与临时图像库中3幅图像的局部特征进行精确匹配，最终得到与待匹配图像相似度最高的图像作为匹配结果输出。所提出的图像分级匹配算法将基于全局特征的改进形状上下文算法和基于局部特征的改进SIFT算法相结合，从而达到优势互补的目的。实验结果表明，该算法在机器人基于拓扑地图导航过程中有效地提高了图像匹配效率，缩短了运行时间。

关键词: 移动机器人, 图像匹配, 改进形状上下文, 改进SIFT

Abstract: Aiming at the problems that the image feature extraction and match algorithm should have high accuracy, good performance in real-time and robustness when the mobile robot navigated based on topological map, the paper proposed a new image hierarchical matching algorithm based on the global feature and local fusion. First, the improved shape context algorithm was applied to the input images to be matched to extract the global features which were matched roughly with the images in the database, obtaining 3 images that had the highest similarity to the current image which constituted a temporary image database. Then, the improved SIFT algorithm were used to extract local feature of the input images which were matched accurately with the local feature of the 3 images in the temporary image database, finally obtaining the image with highest similarity as the match results. The image hierarchical matching algorithm based on the global feature and local feature combined the improved shape context algorithm based on global features and the improved SIFT algorithm based on local features, so as to achieve the purpose of complementary advantages. The experimental results show that this algorithm can effectively improve the matching efficiency and reduce the running time when the mobile robots navigate based on topological map.

Key words: mobile robot, image matching, improved shape context, improved SIFT

中图分类号:

TP391

朱奇光, 王梓巍, 陈颖. 基于全局特征与局部特征的图像分级匹配算法研究及应用[J]. 中国机械工程.

Zhu Qiguang, , Wang Ziwei , Chen Ying. Investigation and Application on Image Hierarchical Matching Algorithm Based on Global Feature and Local Feature[J]. China Mechanical Engineering.

参考文献

[1]王殿军.双目视觉在移动机器人定位中的应用[J].中国机械工程，2013，24(9)：1155-1158.

Wang Dianjun. Application on Binocular Vision System of a Mobile Robot[J]. China Mechanical Engineering，2013，24(9)：1155-1158.

[2]陈卫东，张兴家，朱奇光，等. 基于混合特征的移动机器人图像匹配算法[J]. 中国机械工程, 2015,26(9): 1137-1141.

Chen Weidong， Zhang Xingjia， Zhu Qiguang， et al. An Image Matching Algorithm for Mobile Robot Localization Based on Hybrid Features[J]. China Mechanical Engineering, 2015, 26(9): 1137-1141.

[3]刘佳, 傅卫平, 王雯,等. 基于改进SIFT算法的图像匹配[J]. 仪器仪表学报, 2013, 34(5):1107-1112.

Liu Jia，Fu Weiping, Wang Wen, et al. Image Matching Based on Improved SIFT Algorithm[J]. Chinese Journal of Scientific Instrument, 2013, 34(5):1107-1112.

[4]Lowe D G. Distinctive Image Features from Scale- Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

[5]Lu B, Whangbo T K. A SIFT-Color Moments Descriptor for Object Recognition[C]// 2014 International Conference on IT Convergence and Security (ICITCS). Beijing, 2014:1-3.

[6]陈抒瑢, 李勃, 董蓉,等. Contourlet-SIFT特征匹配算法[J].电子与信息学报, 2013,35(5): 1215-1221.

Chen Shurong, Li Bo, Dong Rong, et al. Contourlet-SIFT Feature Matching Algorithm[J]. Journal of Electronics & Information Technology, 2013,35(5): 1215-1221.

[7]Zhong Jinqin， Tan Jieqing， Gu Lichuan. SIFT Feature Matching Algorithm with Local Shape Context [J]. International Journal of Applied Mathematics & StatisticsTM, 2013, 46(16):93-101.

[8]高晶, 吴育峰, 吴昆,等. 基于角点检测的图像匹配算法[J]. 仪器仪表学报, 2013, 34(8): 1717-1725.

Gao Jing, Wu Yufeng, Wu Kun, et al. Image Matching Method Based on Corner Detection[J]. Chinese Journal of Scientific Instrument, 2013, 34(8):1717-1725.

[9]周瑜, 刘俊涛, 白翔. 形状匹配方法研究与展望[J]. 自动化学报, 2012, 38(6):889-910.

Zhou Yu, Liu Juntao, Bai Xiang. Research and Perspective on Shape Matching[J]. Acta Automatica Sinica, 2012, 38(6):889-910. [10]鲍文霞, 梁栋, 程志友,等. 一种基于图理论的非刚体形状匹配算法[J]. 仪器仪表学报, 2009, 30(10):2027-2032.

Bao Wenxia, Liang Dong, Cheng Zhiyou,et al. Graph Theory Based Non-rigid Shape Matching Algorithm[J]. Chinese Journal of Scientific Instrument, 2009, 30(10):2027-2032.

[11]史思琦. 基于轮廓特征的目标识别研究[D].西安：西安电子科技大学, 2012.

[12]李洪波. 基于减法聚类和快速紧密性函数的 SF-FCM[J]. 控制与决策, 2011, 26(7): 1074-1078.

Li Hongbo. SF-FCM Based on Fast Close Function and Subtractive Clustering[J].Control and Decision, 2011, 26(7): 1074-1078.

[13]Alitappeh R J, Saravi K J, Mahmoudi F. Key Point Reduction in SIFT Descriptor Used by Subtractive Clustering[C]// Information Science, Signal Processing and their Applications (ISSPA), 11th International Conference on IEEE. Montreal, 2012:906 - 911.

[14]毋立芳, 侯亚希, 周鹏,等. 基于最大位平均熵的SIFT描述子二值化及相似度匹配方法[P]. 中国专利: 103617431A, 2014-03-05.

[15]Belongie S J, Malik J, Puzicha J. Shape Matching and Object Recognition Using Shape Contexts[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24(4):509-522.

[16]Haibin L, Jacobs D W. Shape Classification Using the Inner-distance[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007, 29(2):286-299.