基于改进局部不变特征的兴趣点匹配精选.pdf

第31 卷第11 期 电 子 与 信 息 学 报 Vol.31No.11 2009 年11 月 Journal of Electronics Information Technology Nov..2009 基于改进局部不变特征的兴趣点匹配 张 良 王海丽 吴仁彪 (中国民航大学智能信号与图像处理天津市重点实验室 天津 300300) 摘 要：该文提出了一种适用于目标跟踪的局部特征点检测与匹配方法，在尺度不变特征(Scale Invariant Feature Transform, SIFT)算法基础上进行了多方面的改进。在高斯差分尺度空间仅检测局部极大值，提高算法的稳定性； 采用基于圆形邻域统计梯度方向直方图，来确定兴趣点的主方向和描述子，避免了图像旋转的运算代价；最后采用 最近邻与次近邻之比来对96 维的描述子进行匹配。所提方法在有效地提高匹配准确率的同时，大大提高了运算速 度, 适用于对实时性要求较高的场合。 关键词：图像处理；局部特征；尺度不变特征；特征匹配；方向直方图 中图分类号：TN911.73 文献标识码：A 文章编号：1009-5896(2009)11-2620-06 Matching of Interesting Points Based on Improved SIFT Algorithm Zhang Liang Wang Hai-li Wu Ren-biao (Tianjin Key Lab for Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, China) Abstract: This paper presents an improved SIFT(Scale Invariant Feature Transform) descriptor for local feature detection and matching in object tracking. Only the local maxima in DOG scale space are detected as candidate interesting points to improve the stability. In order to avoid rotating the image, the main orientations and descriptors are determined statistically, according to oriented gradients histograms in circular neighborhood around the interesting point. Finally, ratio between the first and the second closest distance is used to match the 96-dimensional vectors. This method exhibits very good performance in high reliable applications, for its effectiveness and reduced complexity. Key words: Image processing; Local features; Scale Invariant Feature Transform(SIFT); Feature matching; Orientation histogram