摘要
为提高对足球射门视频图像的自动识别和动作纠正能力,提出一种基于机器视觉和特征提取的足球射门视频图像轨迹跟踪方法。通过视觉信息融合和模糊跟踪识别方法进行足球射门视频图像的轨迹线跟踪识别,建立足球射门视频图像的关键动作特征点提取模型,通过空间三维信息融合方法进行机器视觉下的图像信息融合和有效动作特征点检测,结合角点的动态分布特征提取方法,实现足球射门视频图像的相关性动作特征点提取和轨迹跟踪。仿真结果表明,与传统方法相比,采用该方法进行足球射门视频图像轨迹跟踪的准确性最高达到0.8,该方法的准确性较高,特征提取能力较好,提高了足球射门视频图像识别和动作纠正能力。
In order to improve the ability of automatic recognition and action correction of football shooting video images,a trajectory tracking method of football shooting video images based on machine vision and feature extraction is proposed.It uses visual information fusion and fuzzy tracking recognition methods to track and recognize the trajectory of the football shot video image,establishes the key action feature point extraction model of the football shot video image,and uses the spatial three-dimensional information fusion method to perform image information fusion and effective action under machine vision Feature point detection,combined with the corner point dynamic distribution feature extraction method,realizes the correlation action feature point extraction and trajectory tracking of the football shooting video image.The simulation results show that,compared with the traditional method,the accuracy of this method for football shooting video image trajectory tracking is up to 0.8.It can be seen that this method has higher accuracy and better feature extraction ability,which improves the recognition of football shooting video images.And the ability to correct movements.
作者
郑夕雯
ZHENG Xi-wen(Tongji University,Shanghai 200433 China)
出处
《自动化技术与应用》
2023年第10期144-147,共4页
Techniques of Automation and Applications
关键词
机器视觉
射门视频图像
轨迹跟踪
machine vision
shooting video image
trajectory tracking
