一种基于机器学习的运动目标阴影检测新方法

A new method for shadow detection of moving object based on machine learning

运动目标检测是物联网智能视频监控中的一个重要环节。通过对各种阴影检测方法的研究,我们发现仅仅通过一种特征进行处理并不能准确的检测出阴影。因此,本文提出了一种基于机器学习的运动目标阴影检测新方法。该方法深度融合颜色信息、光学不变性以及纹理特征等因素,通过机器学习,自适应地进行目标阴影检测,在综合分析三种信息检测结果的基础上,实现对阴影的有效确定。该算法能够有效地结合各种方法的优势,在物联网应用中取得了较好的效果和运行效率。

Under the banner of internet of things (IOT),intelligent video surveillance is an emerging re- search direction in the field of computer vision.It focuses on how to describe,analyze and understand the contents of the surveillance video by using image and video processing technology and artificial intelligence techniques.Then it can control the video surveillance system according to the analysis results, making the video surveillance system have a higher level of intelligence.Moving object detection is an important part in intelligent video surveiIlance of IOT.But there are drawbacks on the ilIumination change,complex background and shadow in the traditional methods.Based on the variety of shadow detection methods,we find that only using one feature can not obtain the result of detection accurately. Then we present a new method of shadow detection for moving object based on machine learning,which contains color information,the invariance of optical and texture features.Through machine learning,it can adaptively do shadow detection for moving object.Based on the comprehensive analysis of the detecting results of three kinds of information,the shadow can be effectively determined.The method has combined the advantages of various methods,and it can get ideal effect and efficiency in the application of IOT.