摘要
运动目标检测一直是研究的热点和难点之一。由于运动目标的检测容易受到背景、光线变化、目标与其他物体间相互遮挡等因素的影响,如何更好地实现运动目标检测是本文研究的重点。本文运用光流法探究运动图像的目标检测,以光流矢量场作为基础,通过光流模型、背景模型和基于墒等研究途径,在一幅图像上分离出目标和背景,检测出运动目标并作出它运动轨迹。
Moving target detection has always been one of the hot and difficult points in research.Because the detection of moving objects is easily affected by background,light change,mutual occlusion between objects and other factors,how to better achieve the detection of moving objects is the focus of this paper.In this paper,the optical flow method is used to explore the object detection of moving image.Based on the optical flow vector field,the object and background are separated from an image through optical flow model,background model and moisture-based research approaches,and the moving object is detected and its trajectory is made.
作者
吴飞燕
WU Fei-yan(College of Big Data and Software Engineering,Wuzhou University,Wuzhou Guangxi 543300,China)
出处
《科技视界》
2019年第21期45-46,58,共3页
Science & Technology Vision
关键词
运动目标
光流法
熵
数字图像处理
Moving target
Optical flow method
Entropy
Digital image processing
