Automatic incident detection in smart city using multiple traffic flow parameters via V2X communication
Automatic incident detection in smart city using multiple traffic flow parameters via V2X communication
复制标题
DOI：
10.1177/1550147718815845
复制
发表时间：
2018-11-29
影响因子：
2.3
通讯作者：
Khan, Majid Iqbal
中科院分区：
文献类型：
--
作者：
Iqbal, Zafar;Khan, Majid Iqbal
智能交通系统的近期研究趋势侧重于开发自动事件检测系统，以应对包括事故、交通拥堵和堵塞在内的道路事件，这些事件对宝贵的生命造成伤害并导致经济损失。大多数现有的自动事件检测系统使用固定探测器来检测交通参数，如占有率、速度和车道变换信息。由于视线和短距离通信、天气条件、道路维修以及驾驶员的驾驶模式等原因，这些系统在数据收集和处理过程中容易出现延迟、不准确和误报的情况。此外，这些系统是为高速公路设计的，由于城市交通密度因素变化很大，它们与城市环境的兼容性较差。为了克服这些缺陷，利用智能道路以及分别用于数据收集和数据处理的路侧单元，开发了一种用于智能城市自动事件检测的有效且稳健的方法。该算法的事件置信因子不仅基于速度和车道变换参数，还基于加速度、方向和偏差等因素，这些因素被整合以应对高峰/非高峰交通时段。多个参数的整合提高了事件置信度，从而提高了事件检测的准确性。使用集合论的概念对整个算法进行了数学描述，然后通过形式分析确保该算法在模拟过程中不太容易出现运行时和逻辑错误。
Recent research trends in intelligent transportation system are focused toward developing automatic incident detection systems to deal with on-road incidents including accidents, traffic congestion, and jamming which cause damage to precious human lives and financial losses. Most of the existing automatic incident detection systems use fixed detectors to detect traffic parameters like occupancy, speed, and lane change information. These systems are prone to delay, inaccuracy, and false alarms during data collection and processing due to line of sight and short-range communication, weather conditions, road repairing, and driver's driving patterns. Moreover, these systems are designed for freeways/highways and are less compatible with city scenario due to its highly variable traffic density factor. To overcome these deficiencies, an effective and robust approach for automatic incident detection for smart city is developed using smart roads in association with roadside units for data collection and data processing, respectively. The incident confidence factor of the algorithm is based not only on speed and lane change parameters but also on acceleration, orientation, and deviation factors that are integrated to cope with peak/non-peak traffic hours. The integration of multiple parameters increases the incident belief factor and hence the accuracy of incident detection. The complete algorithm is mathematically described using the notions of set theory and then formal analysis assures that the algorithm would be less susceptible to runtime and logical errors during simulations.