基于Harris角点和SIFT算法的车辆图像匹配

Vehicle Image Matching Based on Harris Corner and SIFT Algorithm

车辆图像匹配广泛应用于车辆识别和跟踪,其中SIFT(Scale Invariant Feature Transform)特征匹配算法是当前国内外特征点匹配研究的热点,但针对车辆等刚体特征明显的目标,SIFT算法在时间复杂度和稳定性方面留出了改进空间.针对车辆图像匹配,本文基于Harris角点检测对SIFT算法进行改进.实验结果表明:该方法在车辆图像匹配时,稳定性和实时性优于SIFT算法.

Vehicle image matching algorithms are widely used in the field of vehicle identification and tracking,and SIFT（ Scale invariant feature transform） is the research focus both at home and abroad for feature points matching. However,SIFT still needs to be improved in time complexity and stability for the objects which have obvious rigid-body characteristics like vehicles. For vehicle image matching,SIFT is improved in this paper on the basis of the Harris corner detection. The experiment results show that this improved algorithm has better stability and real-time performance than SIFT when matching vehicle images.