基于智能感知的城市环境车辆测速研究

发布时间：2019-01-21 20:24

【摘要】：随着智能手机的推广，基于智能手机的车载应用越来越多的被使用在如分析复杂的城市交通和提升智能化的驾驶体验等方面。具体来讲，智能化的车辆定位、提升驾驶安全性、分析驾驶员行为和建立智能化交通系统等方向成为了近些年的研究热点。作为一个重要输入，准确的车辆的行驶速度测定对于提升车载应用的可用性与精确性来说至关重要。传统的车速测量手段包括视频采集、铺设线圈及使用超声波雷达等技术都有着投资成本大、维护成本高、覆盖范围窄等缺点。智能手机的出现给车辆测速方法注入了新鲜血液。通过利用行车过程中基站信号强度的变化或是借助GPS定位测速等手段都可以实现对车辆行驶速度的测量。然而，其在实时度和精确度上的缺陷以及受到环境因素的制约等都使其难以满足车载应用提出的越来越丰富的需求。考虑到现有车辆测速方法在可用性以及精确度上收到的制约，本文提出了一种依赖于智能手机运动传感器的车速测定系统。该系统可以借助手机加速度传感器来测算车速，并进一步通过感知车辆在城市环境中的一些行驶特性，包括停车、转弯和驶过颠簸路面的信息来消除测算误差，，进而产生高精度的车速估计。在此基础上，本论文进一步探讨了智能手机传感器的能耗特性，并设计出了一套基于车辆行驶速度及城市环境行驶特性的采样率自适应策略。该策略可以在不影响系统测速精度的前提下实现了对系统运行时能耗的显著降低。此外，大量的上路实验验证了系统的有效性，鲁棒性以及精确性。
[Abstract]:With the promotion of smart phones, more and more applications based on smart phones are used in analyzing complex urban traffic and improving intelligent driving experience. Specifically, intelligent vehicle positioning, improve driving safety, analysis of driver behavior and the establishment of intelligent traffic system have become the focus of research in recent years. As an important input, accurate vehicle speed measurement is very important to improve the usability and accuracy of vehicle applications. Traditional speed measurement methods including video acquisition, coil laying and ultrasonic radar have many disadvantages, such as high investment cost, high maintenance cost, narrow coverage and so on. The advent of smartphones has injected fresh blood into vehicle velocimetry. The vehicle speed can be measured by using the change of the signal intensity of the base station in the course of driving or by means of GPS positioning and velocity measurement. However, its defects in real-time degree and accuracy, as well as the constraints of environmental factors, make it difficult to meet the increasing needs of vehicle applications. Considering the limitations of the existing vehicle speed measurement methods in terms of availability and accuracy, a speed measurement system based on smart phone motion sensor is proposed in this paper. The system can use mobile acceleration sensors to measure vehicle speed and further eliminate measurement errors by sensing some of the vehicle's driving characteristics in urban environments, including parking, turning, and driving across bumpy roads. Furthermore, high precision speed estimation is generated. On this basis, this paper further discusses the energy consumption characteristics of smart phone sensor, and designs a set of sampling rate adaptive strategy based on vehicle driving speed and urban environment driving characteristics. The strategy can significantly reduce the energy consumption of the system without affecting the accuracy of the system speed measurement. In addition, a large number of experiments on the road verify the effectiveness, robustness and accuracy of the system.
【学位授予单位】：上海交通大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：U495;TP212

【共引文献】