Floating Car and Camera Data Fusion for Non-parametric Route Travel Time Estimation

Abstract

Traffic management centers take advantage of various data collection systems ranging from stationary sensors e.g. automated vehicle identification systems to mobile sensors e.g. fleet management systems. Each type of data collection system has its own advantages and disadvantages. Stationary sensors has less measurement noise than mobile sensors but their network coverage is limited. On the other hand, mobile sensors cover expand areas of road networks but they have less penetration rate and frequency of reports. Traffic state estimation can benefit from fusion of data from various sources as they complement each other. This paper introduces a route travel time estimation method that aggregates data from two traffic data sources, automated number plate recognition system and floating car data.