Loading…
Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model
With the recent advancements in computer vision and artificial intelligence, traffic conflicts occurring at an intersection and associated traffic characteristics can be obtained at the granular level of a signal cycle in real-time. This capability enables the estimation of the real-time crash risk...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Default Article |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/2134/25112072.v1 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1818165011328008192 |
---|---|
author | Fizza Hussain Yasir Ali Yuefeng Li Md. Mazharul Haque |
author_facet | Fizza Hussain Yasir Ali Yuefeng Li Md. Mazharul Haque |
author_sort | Fizza Hussain (8139471) |
collection | Figshare |
description | With the recent advancements in computer vision and artificial intelligence, traffic conflicts occurring at an intersection and associated traffic characteristics can be obtained at the granular level of a signal cycle in real-time. This capability enables the estimation of the real-time crash risk using sophisticated modelling techniques, e.g., extreme value theory. However, these models are inherently incapable of forecasting the crash risk of future time periods based on the temporal dependency of crash risks. This study proposes a unified framework of extreme value theory and autoregressive integrated moving average models for forecasting crash risks at signalised intersections. At the first level of this framework, a non-stationary generalised extreme value model has been developed to estimate the real-time rear-end crash risk at the signal cycle level using the video data collected from three signalised intersections in Queensland, Australia. To capture the time-varying effect of different traffic conditions on conflict extremes, traffic flow, speed, shockwave area, and platoon ratio covariates are incorporated into the generalised extreme value model. The signal cycle-level crash risks obtained from the first level form a univariate time series, which is modelled using two variants of autoregressive integrated moving average model to forecast the crash risk of future signal cycles. Results reveal that the autoregressive integrated moving average model with exogenous variables outperforms the model without exogenous variables and can forecast the crash risk for the next 30–35 min with reasonable accuracy. Similarly, results also demonstrate that different crash risk patterns within a typical day are accurately predicted. The proposed framework helps identify the spatiotemporal windows where safety gradually deteriorates over time, thus enabling proactive safety assessment. |
format | Default Article |
id | rr-article-25112072 |
institution | Loughborough University |
publishDate | 2023 |
record_format | Figshare |
spelling | rr-article-251120722023-09-09T00:00:00Z Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model Fizza Hussain (8139471) Yasir Ali (13768642) Yuefeng Li (521173) Md. Mazharul Haque (3643810) Transportation, logistics and supply chains Civil engineering Applied mathematics Real-time Crash risk Forecasting Time-series models Signalised intersections With the recent advancements in computer vision and artificial intelligence, traffic conflicts occurring at an intersection and associated traffic characteristics can be obtained at the granular level of a signal cycle in real-time. This capability enables the estimation of the real-time crash risk using sophisticated modelling techniques, e.g., extreme value theory. However, these models are inherently incapable of forecasting the crash risk of future time periods based on the temporal dependency of crash risks. This study proposes a unified framework of extreme value theory and autoregressive integrated moving average models for forecasting crash risks at signalised intersections. At the first level of this framework, a non-stationary generalised extreme value model has been developed to estimate the real-time rear-end crash risk at the signal cycle level using the video data collected from three signalised intersections in Queensland, Australia. To capture the time-varying effect of different traffic conditions on conflict extremes, traffic flow, speed, shockwave area, and platoon ratio covariates are incorporated into the generalised extreme value model. The signal cycle-level crash risks obtained from the first level form a univariate time series, which is modelled using two variants of autoregressive integrated moving average model to forecast the crash risk of future signal cycles. Results reveal that the autoregressive integrated moving average model with exogenous variables outperforms the model without exogenous variables and can forecast the crash risk for the next 30–35 min with reasonable accuracy. Similarly, results also demonstrate that different crash risk patterns within a typical day are accurately predicted. The proposed framework helps identify the spatiotemporal windows where safety gradually deteriorates over time, thus enabling proactive safety assessment.<p></p> 2023-09-09T00:00:00Z Text Journal contribution 2134/25112072.v1 https://figshare.com/articles/journal_contribution/Real-time_crash_risk_forecasting_using_Artificial-Intelligence_based_video_analytics_A_unified_framework_of_generalised_extreme_value_theory_and_autoregressive_integrated_moving_average_model/25112072 CC BY 4.0 |
spellingShingle | Transportation, logistics and supply chains Civil engineering Applied mathematics Real-time Crash risk Forecasting Time-series models Signalised intersections Fizza Hussain Yasir Ali Yuefeng Li Md. Mazharul Haque Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model |
title | Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model |
title_full | Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model |
title_fullStr | Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model |
title_full_unstemmed | Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model |
title_short | Real-time crash risk forecasting using Artificial-Intelligence based video analytics: A unified framework of generalised extreme value theory and autoregressive integrated moving average model |
title_sort | real-time crash risk forecasting using artificial-intelligence based video analytics: a unified framework of generalised extreme value theory and autoregressive integrated moving average model |
topic | Transportation, logistics and supply chains Civil engineering Applied mathematics Real-time Crash risk Forecasting Time-series models Signalised intersections |
url | https://hdl.handle.net/2134/25112072.v1 |