Dynamic Path Flow Estimation Using Automatic Vehicle Identification and Probe Vehicle Trajectory Data: A 3D Convolutional Neural Network Model

Abstract

Dynamic path flows, referring to the number of vehicles that choose each path in a network over time, are generally estimated with the partial observations as the input. The automatic vehicle identification (AVI) system and probe vehicle trajectories are now popular and can provide rich and complementary trip information, but the data fusion was rarely explored. Therefore, in this paper, the dynamic path flow estimation is based on these two data sources and transformed into a feature learning problem. To fuse the two data sources belonging to different detection ways at the data level, the virtual AVI points, analogous to the real AVI points (turning movements at nodes with AVI detectors), are defined and selected to statically observe the dynamic movement of the probe vehicles. The corresponding selection principles and a programming model considering the distribution of real AVI points are first established. The selected virtual AVI points are used to construct the input tensor, and the turning movement-based observations from both the data sources can be extracted and fused. Then, a three-dimensional (3D) convolutional neural network (CNN) model is designed to exploit the hidden patterns from the tensor and establish the high-dimensional correlations with path flows. As the path flow labels commonly with noises, the bootstrapping method is adopted for model training and the corresponding relabeling principle is defined to purify the noisy labels. The entire model is extensively tested based on a realistic road network, and the results show that the designed CNN model with the presented data fusion method can perform well in training time and estimation accuracy. The robustness of a model to noisy labels is also improved through the bootstrapping method. The dynamic path flows estimated by the trained model can be applied to travel information provision, proactive route guidance, and signal control with high real-time requirements.

Review of driving-behaviour simulation: VISSIM and artificial intelligence approach

“… Reversible Lane Control Algorithm Reversible Lane Control After adopting the variable lane control system, the average queue length, the maximum delay time, and the average carbon emission, the average queue length decreased. [ 193 ] Generating a large data sample through Simulation. Convolutional Neural Network (CNN) Using the automatic vehicle identification and probe vehicle trajectory data to estimate Dynamic Path Flow The dynamic path flows estimated by the trained model can be applied to travel information provision, proactive route guidance, and signal control with high real-time requirements.…”

“…[ 182 ] based on a backpropagation neural network (BP-NN) to obtain data containing vehicle to vehicle (V2V) information to predict the velocity of intelligent CVs [ 187 ]. generated data for training the ANN to estimate traffic delays using a VISSIM simulation [ 193 ]. created the necessary data using a microscopic simulation model to estimate the dynamic path flow based on a convolutional neural network [ 178 ].…”

Estimating Link Flows in Road Networks With Synthetic Trajectory Data Generation: Inverse Reinforcement Learning Approach

“…Zhang et al (2019) developed a traffic prediction model using Generative Adversarial Nets (GAN), in which historical traffic flow data are used as input for training such a model [28]. Chen et al (2021) used a convolutional neural network (CNN) model to learn the traffic flow pattern from probe vehicle trajectories and automatic vehicle identification [29]. However, there is a lack of research in generative modelling approaches that consider both vehicle trajectory data and traffic volume data collected by fixed sensors on the road network while making minimal assumptions on the available data.…”

Dynamic Route Flow Estimation in Road Networks Using Data from Automatic Number of Plate Recognition Sensors

“…Their results deduced that with a sampling or observation of 60% of the flows, it is possible to accurately estimate the O-D patterns. Chen et al [48] propose a model for estimating flows on routes from a combination of data collected by probe vehicles and AVI sensors, using a neural network model that despite offering good estimation results can be improved in certain aspects, with one being the dynamic route choice in congested networks.…”