摘要
针对尺度不变特征变换(SIFT)算法的计算量大、速度慢等缺点,提出了一种融合压缩感知的图像匹配算法。首先对目标图像和待匹配图像进行预处理,利用压缩感知技术进行图像压缩,结合SIFT算法提取图像的特征点,通过自适应阈值序贯相似性检测(SSDA)匹配算法进行图像快速匹配搜索,从而找到最佳匹配位置。
Aiming at the disadvantages of massive calculation and slow speed of traditional scale invariant feature transform(SIFT) algorithm, this paper proposes an improved image matching method which combines compressed sensing(CS) algorithm. Firstly, target images and images to be matched are preprocessed and compressed by using compressed sensing technology. Then, image feature points are extracted in combination with SIFT algorithm.Finally, sequential similarity detection algorithm(SSDA) with adaptive threshold is used for fast search of image matching to find an optimal matching position, and a matching image is obtained. Experimental results demonstrate that the method realizes fast image matching, efficiently overcomes the shortcomings of heavy computation and low efficiency in the process of extracting image features, and guarantees the matching accuracy and efficiency, which meets the real-time requirements in machine vision system.
出处
《华东交通大学学报》
2015年第6期115-121,152,共8页
Journal of East China Jiaotong University
基金
国家自然科学基金项目(61272197)
江西省自然科学基金(20132BAB201027
20142BAB207007)
江西省科技厅工业支撑计划(20151BBE50055)
赣鄱英才555工程领军人才培养计划(S2013-57)
江西省研究生创新专项基金项目(YC2015S254)
关键词
尺度不变特征变换
压缩感知
序贯相似性检测算法
自适应阈值
scale invariant feature transform
compressed sensing
sequential similarity detection algorithm
adaptive threshold value