基于改进SIFT算法的矿山井筒视频图像实时配准

金属矿山 ›› 2013, Vol. 42 ›› Issue (08): 92-95.

基于改进SIFT算法的矿山井筒视频图像实时配准

邢远秀^1,2，江成琳¹，柯伟兵¹

1.冶金工业过程系统科学湖北省重点实验室；2.武汉大学计算机学院

出版日期:2013-08-15 发布日期:2013-09-27
基金资助:
* 冶金工业过程系统科学湖北省重点实验室基金项目（编号：Y201317），中央高校基本科研业务费专项（编号：2011274636）。

Real-time Registration of Mineshaft Images Based on Improved SIFT Algorithm

Xing Yuanxiu^1,2，Jiang Chenglin¹，Ke Weibing¹

1.Hubei Province Key Laboratory of Systems Science in Metallurgical Process；2.School of Computer，Wuhan University

Online:2013-08-15 Published:2013-09-27

摘要/Abstract

摘要： 针对尺度不变特征转换（SIFT）算法在矿山井筒视频图像匹配时不满足实时性要求，提出了改进的SIFT算法。在保证配准精度的情况下，通过减少尺度变换，构造简单的特征描述子并将Bray Curtis距离作为相似性度量，可以大幅缩短算法执行时间，提高配准精度。实验结果表明，改进的SIFT算法对图像旋转、尺度及亮度的线性变化具有不变特性，运算速度比改进前至少提高4倍，对矿山井筒视频图像具有较好的实时匹配效果。

关键词: 矿山井筒图像配准, 尺度不变特征转换算法, 特征描述子, 相似性度量

Abstract: In view of the fact that the scale invariant feature transform (SIFT) algorithm matching with the mine shaft image does not meet the real-time requirements，an improved SIFT（scale invariant feature transform）algorithm is proposed.In case of keeping the registration accuracy，the algorithm execution time was greatly reduced and the registration accuracy was improved through the reduced scale transformation，simple feature descriptors and considering the Bray Curtis distance as the similarity measure.Experimental results show that the improved SIFT algorithm keeps the linear of the image rotation，the scale and the brightness be changeless，and increases the operating speed at least 4 times higher than that by the original SIFT，resulting in the mineshaft image displaying a good real-time image matching performance.

Key words: Mineshaft image, SIFT, Feature descriptor, Similarity measurement

邢远秀, 江成琳, 柯伟兵. 基于改进SIFT算法的矿山井筒视频图像实时配准[J]. 金属矿山, 2013, 42(08): 92-95.

XING Yuan-Xiu, JIANG Cheng-Lin, KE Wei-Bing. Real-time Registration of Mineshaft Images Based on Improved SIFT Algorithm[J]. Metal Mine, 2013, 42(08): 92-95.

扫码分享