Information Systems Department, University of Minho, 4800-058 Guimarães, Portugal.
Sensors (Basel). 2018 Jun 21;18(7):1984. doi: 10.3390/s18071984.
Anomalies on road pavement cause discomfort to drivers and passengers, and may cause mechanical failure or even accidents. Governments spend millions of Euros every year on road maintenance, often causing traffic jams and congestion on urban roads on a daily basis. This paper analyses the difference between the deployment of a road anomalies detection and identification system in a “conditioned” and a real world setup, where the system performed worse compared to the “conditioned” setup. It also presents a system performance analysis based on the analysis of the training data sets; on the analysis of the attributes complexity, through the application of PCA techniques; and on the analysis of the attributes in the context of each anomaly type, using acceleration standard deviation attributes to observe how different anomalies classes are distributed in the Cartesian coordinates system. Overall, in this paper, we describe the main insights on road anomalies detection challenges to support the design and deployment of a new iteration of our system towards the deployment of a road anomaly detection service to provide information about roads condition to drivers and government entities.
道路路面异常会给驾驶员和乘客带来不适，还可能导致机械故障甚至事故。政府每年花费数百万欧元用于道路维护，这常常导致城市道路每天都出现交通拥堵。本文分析了在“有条件”和真实环境设置中部署道路异常检测和识别系统之间的区别，结果表明系统在真实环境设置中的性能要比“有条件”设置中的性能差。它还根据对训练数据集的分析、通过应用 PCA 技术对属性复杂性的分析、以及在每个异常类型的上下文中对属性的分析，展示了一个系统性能分析；通过加速度标准差属性来观察不同异常类型在笛卡尔坐标系中的分布情况，以此来分析属性。总的来说，在本文中，我们描述了道路异常检测挑战的主要见解，以支持我们的系统的新迭代的设计和部署，从而为驾驶员和政府实体提供有关道路状况的信息，实现道路异常检测服务的部署。
