• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 图形与图像 • 上一篇    下一篇

基于SIFT算法的物体运动方向快速识别方法

李洪锋1,魏镜弢1,付亚伟2,王家涛1   

  1. (1.昆明理工大学机电工程学院,云南 昆明 650093;2.中国铁建高新装备股份有限公司,云南 昆明 650093)
  • 收稿日期:2018-08-20 修回日期:2018-12-29 出版日期:2019-06-25 发布日期:2019-06-25

A fast object motion direction recognition
method based on SIFT algorithm

LI Hongfeng1,WEI Jingtao1,FU Yawei2,WANG Jiatao1
 
  

  1. (1.College of Electrical and Mechanical Engineering,Kunming University of Science and Technology,Kunming 650093;
    2.CRCC HighTech Equipment Corporation Limited,Kunming 650093,China)
  • Received:2018-08-20 Revised:2018-12-29 Online:2019-06-25 Published:2019-06-25

摘要:

为了解决成像设备只能在较低的分辨率成像且不能区分运动方向的问题,提出了一种基于SIFT算法的快速识别物体运动方向的方法。首先,根据块匹配算法中的角点特征提取法确定块的位置,并将该块命名为检测块。然后,用已经确定的块遍历下一帧图像,找到相匹配的块,命名为目标块并确定检验块与目标块之间的运动方向。最后,采用SIFT算法对2幅图像的特征点进行匹配,选取3个特征点构建三角形,对2个对应三角形的变换关系构建数学模型,做出运动方向的判断。实验结果表明,与块匹配相比,运动方向判断速度提高了3.3倍,匹配的准确程度提高了2.9倍,获得了更高的判断速度和准确度。
2种方法的比较结果显示,基于SIFT算法的识别方法具有较强的可行性,能够更快地确定多帧图像中物体的运动方向。

 

关键词: 运动方向, SIFT, 快速识别, 块匹配

Abstract:

Due to the limitation of objective conditions, imaging devices can only image at a lower resolution, and cannot distinguish the motion direction. We propose a
fast object direction recognition method based on the SIFT. Firstly, according to the block matching algorithm, we use the corner feature extraction method to determine the position of the block, which is named as a detection block. The next frame image is traversed with the determined block, the matching block is found and named as the target block, and the motion direction between the check block and the target block is determined. Finally, the SIFT algorithm is used to match the feature points of two pictures. Each picture selects three corresponding feature points to construct a triangle, and the transformation relationship of two corresponding triangles constructs a mathematical model to identify the motion direction. Experimental results show that the motion direction recognition speed of our proposal is increased by 3.3 times compared with the block matching, and the matching accuracy is increased by 2.9 times, achieving higher judgment speed and accuracy. By comparison, the SIFT search algorithm has stronger feasibility and can determine the moving direction of objects faster in multi-frame images.
 

Key words: motion direction, SIFT, fast recognition, block matching