运动目标检测中阴影去除算法的研究与实现毕业设计正文
- 1、下载文档前请自行甄别文档内容的完整性,平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益,请联系客服反馈,我们会尽快为您处理(人工客服工作时间:9:00-18:30)。
JIANGSU UNIVERSITY
本科生毕业论文
运动目标检测中阴影去除算法的研究与实现Research and realization of the shadow removing algorithm for
Moving object detection
学院名称:计算机科学与通信工程学院
专业班级:通信工程0602班
学生姓名:汪雅洁
指导教师姓名:宋雪桦
指导教师职称:副教授
2010年6月
运动目标检测中阴影去除算法的研究与实现
专业班级:通信工程0602班学生姓名:汪雅洁
指导教师:宋雪桦职称:副教授
摘要随着计算机视觉技术、电子技术、通信技术的发展,智能视频监控系统作为安全防卫的一种重要手段正在越来越受到人们的重视。由于智能视频监控系统具有监控能力强、安全隐患少、节省人力物力资源的优点。因此,在交通、银行、宾馆、商场等重要场所的监控中有广泛的应用前景。
本文首先综合介绍了智能监控系统的发展历史和现状,然后对静止摄像机监控下的运动目标检测、阴影的检测和去除等关键技术进行了比较深入的研究。
运动目标检测作为智能视频监控系统中视频处理的第一步,具有非常重要的地位。本文首先对目前运动目标检测方法进行了概括,在详细研究了几种目标检测方法的基础上,确定了目标检测中较好的一种方法,即基于混合高斯模型的方法,用这个算法来提取运动目标。
由于日照和灯光等外来因素的影响,造成了提取的运动前景中往往含有阴影。因此,运动目标的阴影检测与去除对于运动目标跟踪、分类和识别等后期处理都是一个关键性问题。由于阴影的存在,会给上述后期处理带来干扰甚至失败。为了去除目标前景的阴影,本文首先分析了阴影产生的机理,了解阴影的特征和人类的视觉特征,针对这些特征以及总结和分类目前己有的各类阴影检测算法的基础上,提出了一种基于RGB颜色模型的阴影检测算法。通过实验对本文的算法进行了验证,证明了该算法能够很好地检测出运动目标的阴影以及将阴影去除,而且易于实现。
关键词:视频监控;运动目标检测;混合高斯模型;RGB颜色模型;阴影去除
Research and realization of the shadow removing algorithm for
Moving object detection
Abstract Development of the computer vision technology, the electronic and the communication technology, has made the intelligent visual surveillance system an increasingly important safe defense way. Because it has advantages of higher quality and less need of investment. So it has cheerful prospect in the applications of surveillance for traffic, bank, hotel, shopping, etc.
Both its history and current situation is summarized here, then, a research was made for the key technology of the segmentation of moving objects and the detection and removal of shadows.
As the initial stage in the visual data processing, moving object detection is a key point.After carefully study of moving object detection methods used presently, a more reliable algorithm is determined, that is, the mixed Gauss model. It was adopted to detect moving objects.
As external factors such as sunlight and lighting effects,resulting in extraction of moving foreground often contain shadow. So, shadows detection and elimination of moving objects is essential to the post-processing such as objects tracking, classification and recognition. The existence of shadow will allow the above-mentioned post-processing to fail. In order to remove the shadow of object foreground, this paper first analyze the mechanism of the shadow produced, understand the characteristics of the shadow and the human visual characteristics, then, a method of shadow detection based on the RGB color model is proposed on the basis of these characteritics and the summary and analysis for various shadow detection. We have conducted many experiments to verify the proposed approach. The results show that the algorithm can detect moving targets to remove the shadow, and easy to implement.
Key words Visual Surveillance; Moving Object Detection; Mixed Gaussian Model; RGB color model; Shadow Removal