Automatic incident detection in smart city using multiple traffic flow parameters via V2X communication

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.

Sensitivity Analysis Based SVM Application on Automatic Incident Detection of Rural Road in China

Traditional automatic incident detection methods such as artificial neural networks, backpropagation neural network, and Markov chains are not suitable for addressing the incident detection problem of rural roads in China which have a relatively high accident rate and a low reaction speed caused by the character of small traffic volume. This study applies the support vector machine (SVM) and parameter sensitivity analysis methods to build an accident detection algorithm in a rural road condition, based on real-time data collected in a field experiment. The sensitivity of four parameters (speed, front distance, vehicle group time interval, and free driving ratio) is analyzed, and the data sets of two parameters with a significant sensitivity are chosen to form the traffic state feature vector. The SVM and k-fold cross validation (K-CV) methods are used to build the accident detection algorithm, which shows an excellent performance in detection accuracy (98.15% of the training data set and 87.5% of the testing data set). Therefore, the problem of low incident reaction speed of rural roads in China could be solved to some extent.