节点文献

城市轨道交通中闸机智能识别系统及其识别技术的研究

The Research on Intelligent Recognition System of Gate and Its Recognition Technology in Urban Railway Traffic

【作者】 曲日

【导师】 何丕廉; 任长明;

【作者基本信息】 天津大学 , 计算机应用技术, 2005, 博士

【摘要】 随着城市轨道交通的快速发展,自动售检票系统的作用变得越来越重要。闸机是城市轨道交通的自动售检票系统中的关键设备之一,它利用其内部的智能识别系统对乘客的行为进行识别,从而实现自动检票。因此,智能识别系统是轨道交通中闸机的“大脑”,是整个闸机设计和开发的核心,已成为城市轨道交通的研究热点。由于乘客通行情况相当复杂,闸机的智能识别系统如何快速、准确的识别出乘客面临着艰巨的挑战,本文对此进行了深入研究,主要内容如下:首先,本文开发了适合于城市轨道交通中闸机的仿真软件GS。该仿真软件具有模拟各种乘客通行情况、模拟闸机的硬件、分析仿真试验结果等功能。因此,闸机的设计者可以使用仿真软件GS进行仿真试验,以便验证各种识别方案的正确性。其次,依据运动过程包含动作、事件和行为的思想,本文提出了一种新的适合于闸机的基于事件识别的方法。在人体步态识别的XYT模型的基础上,本文使用红外传感器代替摄像机,对XYT模型进行了改进,进而提出了一种新的适合于闸机的基于人体步态识别的方法。综合图像处理和图像识别技术,本文提出了一种新的适合于闸机的基于人体轮廓识别的方法。最后,根据系统论和控制论的方法,综合上述3种识别技术,本文提出了一种新的适合于闸机的基于事件驱动的乘客通行算法。此外,本文还设计和开发了一套闸机智能识别系统,并将乘客通行算法应用于该识别系统。

【Abstract】 With the rapid development of urban railway traffic, Automatic Fare Colletion(AFC) System has become more important. In urban railway traffic, gate is one of keyapparatus and used to automatically examine tickets by means of its intelligentrecognition system. The recognition system is the “brain” and core of gate in urbanrailway traffic. Therefore it has been a hot issue in recent study on urban railwaytraffic. We are facing with the tremendous challenges in the aspects of how thepassengers are recognized quickly and correctly using the recognition system of thegate, owing to complicated transits. This paper has made a further study on this issue,and the main content is as follows:Firstly, the emulation software called GS has been developed in this paper. GS isable to simulate passengers’ transits, emulate gate’s hardware and analyze test results,etc. So GS is used for emulation experiment in order to check whether somerecognition scheme is valid during the beginning of the design of the recognitionsystem.Secondly, according to action, event and behavior of motion, this paper presentsa new method based on event recognition. In this paper, XYT model in recognizingwalking is enhanced by using infrared sensors instead video device. On basis of theenhanced XYT model, we put forward a new method based on gait recognition. Inaddition, this paper presents a new method based on human outline recognition usingimage processing and recognition.At last, this paper makes a study on passenger transit algorithm and presents anew algorithm based on event drive with the above-mentioned recognition methods.An intelligent recognition system has been designed and developed by means of thenew algorithm.

  • 【网络出版投稿人】 天津大学
  • 【网络出版年期】2006年 07期
节点文献中: 

本文链接的文献网络图示:

本文的引文网络