Pedestrian Path Prediction for Autonomous Driving at Un-Signalized Crosswalk Using W/CDM and MSFM

Zhang, Xi; Chen, Hao; Yang, Wenyan; Jin, Wenqiang; Zhu, Wangwang

doi:10.1109/tits.2020.2979231

Cited by 26 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of vision sensors is supposed to make it easier to recognize vehiclepedestrian collisions in advance and warn immediately them of such situations, and to evaluate vehiclepedestrian behavioral interactions that pose a threat to pedestrian at crosswalk [7]- [10]. To date, an extensive variety of studies have reported on deriving a surrogate safety measurement (SSM) [11], [12], estimating collision probability [13], measuring levels of potential risks, analyzing road users' behaviors [14], [15] in order to prevent vehicle-pedestrian collisions proactively.…”

Section: Figure 1 Overall Approaches To Protect Vrus From Traffic Inc...mentioning

confidence: 99%

“…Then, with categorizing pedestrian's behaviors as three stages (show up, show intention, start to cross) and defining "crossing intention" pattern, the crossing intentions were predicted by using LSTM-RNN network. The authors in [15] proposed pedestrian path prediction system at a time horizon of 2s by applying waiting/crossing decision model (W/CDM) and modified social force model (MSFM). This can recognize a possible conflict between straight-going vehicles and pedestrians at unsignalized crosswalk, and guide to decide in advance whether autonomous vehicle continue to move forward or stop.…”

Section: Figure 1 Overall Approaches To Protect Vrus From Traffic Inc...mentioning

confidence: 99%

See 1 more Smart Citation

A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure

Noh

Yeo

2022

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Section: Figure 1 Overall Approaches To Protect Vrus From Traffic Inc...mentioning

confidence: 99%

Section: Figure 1 Overall Approaches To Protect Vrus From Traffic Inc...mentioning

confidence: 99%

A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure

Noh

Yeo

2022

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

“…Tracking and simulating pedestrian movements is part of the solution to protect their safety at intersections [7]. In Reference [32], the reader can also find models for pedestrian path prediction at 2 s time horizon, and this helps to analyze interactions between pedestrians and straight-going vehicle at non-signalized crosswalks. Extensive research studied pedestrian behaviors, while other works focused on the car driver behavior, like the recent patent [33] where the inventor proposed a traffic control system, controller, and method for directing vehicle behavior at a defined spatial location, based on a UAV hovering above a roadway.…”

Section: Related Workmentioning

confidence: 99%

Evaluating the Impact of Drone Signaling in Crosswalk Scenario

et al. 2020

View full text Add to dashboard Cite

The characteristic pillars of a city are its economy, its mobility, its environment, its inhabitants, its way of life, and its organization. Since 1980, the concept of smart city generally consists of optimizing costs, organization, and the well-being of inhabitants. The idea is to develop means and solutions capable of meeting the needs of the population, while preserving resources and the environment. Owing to their little size, their flexibility, and their low cost, Unmanned Aerial Vehicles (UAV) are today used in a huge number of daily life applications. UAV use cases can be classified into three categories: data covering (like surveillance and event covering), data relaying (like delivery and emergency services), and data dissemination (like cartography and precise agriculture). In addition, the interest to Cooperative Intelligent Transportation Systems (C-ITS) has risen in these recent years, especially in the context of smart cities. In such systems, both drivers and traffic managers share the information and cooperate to coordinate their actions to ensure safety, traffic efficiency, and environment preservation. In this work, we aimed at introducing a UAV in a use case that is likely to happen in C-ITS. A conflict is considered involving a car and a pedestrian. A UAV observes from the top of the scene and will play the role of the situation controller, the information collector, and the assignment of the instructions to the car driver in case of a harmful situation to avoid car-pedestrian collision. To this end, we highlight interactions between the UAV and the car vehicle (U2V communication), as well as between the UAV and infrastructure (U2I communication). Hence, the benefit of using UAV is emphasized to reduce accident gravity rate, braking distance, energy consumption, and occasional visibility reduction.

show abstract

“…Achieving higher levels of autonomy requires various types of functionalities, including but not limited to scene understanding, decision-making, and mission planning. While scene understanding and situational awareness may seem an easy task for an attentive human driver based on their intuition or driving experience, fulfilling it for an autonomous vehicle needs further development [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Toward Driver Intention Prediction for Intelligent Vehicles: A Deep Learning Approach

Azadani

Boukerche

2021

2021 IEEE 46th Conference on Local Computer Networks (LCN)

View full text Add to dashboard Cite

High-level scene understanding and situational awareness are fundamental for autonomous vehicles before being widely used on public roads in a thoroughly efficient and safe manner. These tasks involve not only perceiving the current surrounding states but also predicting the future behavior of nearby human-driven vehicles. A large amount of vehicular sensing data can be collected using sensors and networking systems in vehicles. Moreover, with the advent of Dedicated Short Range Communication, vehicles can further transfer intention information to surrounding vehicles. However, real-time intention inference of nearby drivers is still challenging. Our primary focus is to present a novel deep learning-based approach to predict drivers driving behavior at unsignalized T-junctions. We use temporal convolutional networks to analyze sequences of trajectory data for a vehicle approaching the T-junction and classify the maneuver seconds before actual maneuver occurrence. The cross-validation results demonstrate the efficiency of the proposed methodology.

show abstract

Pedestrian Path Prediction for Autonomous Driving at Un-Signalized Crosswalk Using W/CDM and MSFM

Cited by 26 publications

References 31 publications

A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure

A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure

Evaluating the Impact of Drone Signaling in Crosswalk Scenario

Toward Driver Intention Prediction for Intelligent Vehicles: A Deep Learning Approach

Contact Info

Product

Resources

About