Probabilistic Prediction of Pedestrian Crossing Intention Using Roadside LiDAR Data

Abstract

Pedestrians are vulnerable road users that need proactive protection. While both autonomous and connected vehicle technologies aim to deliver greater safety benefits, current designs heavily rely on vehicle-based or on-board sensors and lack strategic real-time interactions with pedestrians who do not have any communication means. As pedestrians are passively protected by the system, they might be put into hazardous situations when vehicle-mounted sensors fail to detect their presence. This paper is part of ongoing research that uses roadside light detection and ranging (LiDAR) sensors to develop a human-inthe-loop system that brings pedestrians into the connected environment. To proactively protect pedestrians, accurate prediction of their intention for crossings at locations, such as unsignalized intersections and street mid-blocks is critical, and this paper presents a modified Naïve Bayes approach for this purpose. It features a probabilistic approach to overcoming the common deficiencies in deterministic methods and provides valuable comparisons between feature-based data processing methods, such as artificial neural network (ANN) and model-based Naïve Bayes approach. A case study was conducted by using a low-cost 16-line LiDAR sensor installed at the roadside. Pedestrians' crossing intention was predicted at a range of 0.5-3 s before actual crossings. The results satisfactorily demonstrated the properties of the modified Naïve Bayes model, as well as its higher flexibility, compared with the ANN approaches in practice.INDEX TERMS Confidence level, Naïve Bayes, pedestrian crossing intention, roadside LiDAR.

Comparison of the Pedestrian Crossing Intention Parameters and Research on Intention Recognition Model Under Different Road Conditions

“…The results demonstrated that the model had high recognition accuracy; however, the set of representative parameters was not sufficiently comprehensive, and advance recognition was not discussed. Zhao et al [23] extracted the parameters of the trajectory of a pedestrian crossing at an intersection and established an improved naive Bayesian intention recognition model. The verification results revealed that the model had good recognition accuracy 0.5 s in advance.…”

An Automatic Trigged Rectangular Rapid Flashing Beacons (RRFB) System Using the Roadside LiDAR Sensor

“…The Naïve Bayes (NB) classifier was applied for pedestrian crossing intention prediction [21]. The intention can be simply classified into two types: Yes (Crossing), No (Non-Crossing).…”

“…Based on the authors' best knowledge, the only study related to pedestrian crossing road detection is the method developed by Zhao et al [21]. In their study, they used a NB method to predict the pedestrian's crossing intention.…”

An Online Semisupervised Learning Model for Pedestrians’ Crossing Intention Recognition of Connected Autonomous Vehicle Based on Mobile Edge Computing Applications

“…It showed that context-based data are good indicators for crossing prediction. Zhao et al [13] proposed a pedestrian crossing intention model based on improved naive Bayesian networks. The input feature data source is Lidar.…”