【作者】 王忠礼；

【导师】 唐降龙；

【作者基本信息】 哈尔滨工业大学 ， 计算机科学与技术， 2008， 硕士

【摘要】 车辆交通是现代社会的重要标志之一,但随着经济的发展,它在给人们的生活提供便利的同时也产生了一系列社会和环境问题。智能交通系统(IntelligentTransportationSystem,简称ITS)利用通信技术、控制技术、传感器技术、运筹学、人工智能和计算机技术的有效集成,其目的在于充分利用现有道路基础设施资源,改善车、路、人之间的相互作用,提高系统的安全性、高效性与舒适性,从而从整体上提高交通的经济性,正在成为世界各国解决交通拥塞、交通事故频发、土地和能源短缺、交通环境污染以及由此导致的经济损失等的热点研究问题,具有较高的社会效益和巨大的市场应用前景。目前,智能交通系统在理论和应用上都面临着很多难题,国内外大批学者投身于该领域的研究和探索,并且取得了大量的成果,而运动车辆的实时检测作为智能交通系统的核心部分之一,更是成为了研究热点。本文是在这些成果的基础上,对智能交通系统中车辆的精确检测及分割技术进行了研究。主要工作如下:首先,对混合高斯背景建模进行了比较系统的分析,并针对混合高斯背景模型现实应用中的问题,提出一种快速的混合高斯背景建模改进算法,该算法利用场景内光照条件的变化提出了一个自适应背景更新率,根据各像素点颜色值出现的混乱程度不同采取不同的高斯函数参数更新机制,通过对交通监控图像序列进行实验,该算法能在保证背景建模与运动车辆检测效果的同时,使混合高斯模型的背景更新速度及算法处理速度有了较大提高。其次,针对图像后处理去噪,本文介绍了几种常用的滤波方法,着重讨论了形态学中的膨胀、腐蚀运算在去噪中的应用,并取得了很好的效果。最后,提出了一种利用色度畸变和纹理特征进行车辆阴影抑制的方法。该方法分析了场景点在存在阴影前后色度的分布规律以及纹理的互相关性,根据亮度信息和饱和度信息选择不同的阴影消除机制,利用颜色向量夹角和纹理特征进行阴影的消除。更多还原

【Abstract】 The vehicle transportation is one of the important symbols of modern society, but it brings a series of social and environmental problems as well as advantages in our lives. Intelligent Transportation System(ITS) is a system for integrating with communication technology, control technology, sensor technology, operational research, artificial intelligent and computer technology. The aim of ITS is to make full use of the available road facilities, enhancing the security, high efficiency and comfortable of transportation system, and then improve the economical efficiency of the whole system. ITS is one popular research problem of all countries to solve the traffic jam, the traffic accident, the lack of soil and energy resource, the pollution of the environment, and the economic lose by all of them. The application of ITS will bring both economic and social benefit.As to computer Intelligent Transportation System, there are still many problems no matter in theory research or in applications. Large numbers of researchers devoted themselves in the area and have already achieved many progresses. Moving vehicle detection is the most important one of the fundamental tasks for Intelligent Transportation System, which is active topic widely researched in the last decade around the world. Based on the achievements, the dissertation studied the technologies of accurate detection and segmentation of moving vehicles in Intelligent Transportation System. The main work can be summarized as follows:Firstly, we research Gaussian Mixture Model through systematical analysis, and an improved mixture Gaussian background modeling algorithm is presented to reduce the computational cost of traditional mixture Gaussian algorithms. The improved mixture Gaussian-based background model updates the parameters of Gaussian according to the frequency of a pixel value changes. Experimental results show that our algorithm can improve the processing speed greatly and detect moving vehicle accurately.Secondly, as to noise removal of image post-processing, several commonly used methods of removing noise are introduced in the dissertation. Dilation and Erosion in morphology are discussed emphatically in the application of de-noising in the experiments of this dissertation and results are achieved effectively.Thirdly, a shadow suppression method for vehicle detection which combines chrominance distortion and texture feature is proposed. The distribution rule of the chrominance and the cross correlation of texture after and before shadow appears are analyzed, different shadow suppression mechanism is selected according to brightness and saturation information, and chrominance distortion and texture feature are used to eliminate shadow.更多还原