本文为英国雷丁大学（作者：Nils T. Siebel）的博士论文，共139页。

本文描述了欧盟资助的Framework V project ADVISOR中的一种综合视频监控系统的人体跟踪模块的设计与实现。从利兹和雷丁大学（Universities of Leeds）开发的早期人体跟踪系统开始，经过10年的积累，已经进行了多次的改进，以满足视频监视系统中存在的特殊需求。这就是雷丁追踪系统。

本文的工作重点是完成整个任务：从图像处理和跟踪算法到系统设计和集成。Reading People Tracker使用四个协同检测和跟踪模块的组合来跟踪摄像机图像中的人。每个模块都具有中等到较低的复杂性，以确保实时性能。模块包括运动检测器、区域跟踪器、头部检测器和主动形状跟踪器。组合不同的模块并交换它们之间的结果，克服了单个模块的局限性，提高了系统的可靠性。为了降低跟踪器的复杂度，所有四个模块都直接与图像一起工作，避免了复杂的三维模型。实验表明，在存在遮挡和低图像质量的情况下，雷丁跟踪器能够可靠地跟踪人体。Reading People Tracker的一个重要方面是它的可维护性。通过重新设计软件，使其能够轻松地适应、扩展和改进。

本文以人体跟踪器为例，分析了这一改造过程及其对人体跟踪器维护性的影响。案例研究中研究的第二个方面是软件过程，这些过程在软件的10年生命周期中被用来进行维护。研究结果表明，软件过程的多样性对软件质量有着重要的影响。过程多样性可分为两大类：横向过程多样性和纵向过程多样性。研究了两类过程多样性对软件质量的影响。

This thesis describes the design andimplementation of a people tracking module for an integrated visualsurveillance system developed as part of the Framework V project ADVISOR,funded by the European Union. Starting from an earlier people tracker developedat the Universities of Leeds and Reading over the past 10 years, appropriatemethods have been included and adapted to meet the special needs which exist invisual surveillance systems. The result is the Reading People Tracker. Theemphasis in this work lies on the completion of the whole task: from imageprocessing and tracking algorithms through to system design and integration.The Reading People Tracker uses a combination of four co-operating detectionand tracking modules to track people in camera images. Each of the modules isof medium to low complexity to ensure realtime performance. The modules are aMotion Detector, a Region Tracker, a Head Detector and an Active Shape Tracker.Combining different modules and letting them exchange their results overcomesthe limitations which individual modules have and results in a greaterreliability. All four modules work directly with the image in order to reducethe complexity of the tracker. Complicated 3D models are avoided. Experimentsshow that the Reading People Tracker tracks individuals robustly in thepresence of occlusion and low image quality. An important aspect of the ReadingPeople Tracker is its maintainability. The software was re-engineered, makingit possible to adapt, extend and improve the software with ease. Thisre-engineering process and its influence on the maintainability of the peopletracker is analysed as a case study. A second aspect examined in the case studyis the software processes which have been used to maintain the software overits lifetime of 10 years. It is shown that the diversity of software processeshas a significant impact on the quality of the software. Process diversity isdivided into two broad classes, latitudinal and longitudinal process diversity.The influence of both classes of process diversity on software quality isexamined.

1. 引言

2. 人体跟踪

3. 稳健图像处理中的彩色图像滤波

4. Reading People Tracker

5. Reading People Tracker可维护性

6. 过程多样性及其对人体跟踪的影响

7. 新一代人体跟踪器验证

8. 结论

更多精彩文章请关注公众号：