Vehicle Collision Prediction under Reduced Visibility Conditions
Rear-end collisions often cause serious traffic accidents. Conventionally, in intelligent transportation systems (ITS), radar collision warning methods are highly accurate in determining the inter-vehicle distance via detecting the rear-end of a vehicle; however, in poor weather conditions such as f...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/18/9/3026 |
id |
doaj-5c320d12e6ad450c94072ab12de87b84 |
---|---|
record_format |
Article |
spelling |
doaj-5c320d12e6ad450c94072ab12de87b842020-11-24T22:20:17ZengMDPI AGSensors1424-82202018-09-01189302610.3390/s18093026s18093026Vehicle Collision Prediction under Reduced Visibility ConditionsKeng-Pin Chen0Pao-Ann Hsiung1Department of Computer Science & Information Engineering, National Chung Cheng University, Chiayi 62102, TaiwanDepartment of Computer Science & Information Engineering, National Chung Cheng University, Chiayi 62102, TaiwanRear-end collisions often cause serious traffic accidents. Conventionally, in intelligent transportation systems (ITS), radar collision warning methods are highly accurate in determining the inter-vehicle distance via detecting the rear-end of a vehicle; however, in poor weather conditions such as fog, rain, or snow, the accuracy is significantly affected. In recent years, the advent of Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication systems has introduced new methods for solving the rear-end collision problem. Nevertheless, there is still much left for improvement. For instance, weather conditions have an impact on human-related factors such as response time. To address the issue of collision detection under low visibility conditions, we propose a Visibility-based Collision Warning System (ViCoWS) design that includes four models for prediction horizon estimation, velocity prediction, headway distance prediction, and rear-end collision warning. Based on the history of velocity data, future velocity volumes are predicted. Then, the prediction horizon (number of future time slots to consider) is estimated corresponding to different weather conditions. ViCoWs can respond in real-time to weather conditions with correct collision avoidance warnings. Experiment results show that the mean absolute percentage error of our velocity prediction model is less than 11%. For non-congested traffic under heavy fog (very low visibility of 120 m), ViCoWS warns a driver by as much as 4.5 s prior to a possible future collision. If the fog is medium with a low visibility of 160 m, ViCoWs can give warnings by about 2.1 s prior to a possible future collision. In contrast, the Forward Collision Probability Index (FCPI) method gives warnings by only about 0.6 s before a future collision. For congested traffic under low visibility conditions, ViCoWS can warn a driver by about 1.9 s prior to a possible future collision. In this case, the FCPI method gives 1.2 s for the driver to react before collision.http://www.mdpi.com/1424-8220/18/9/3026vehicle collision avoidancedata analyticspredictiontime-to-collisionback-propagation neural networkdata fitting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Keng-Pin Chen Pao-Ann Hsiung |
spellingShingle |
Keng-Pin Chen Pao-Ann Hsiung Vehicle Collision Prediction under Reduced Visibility Conditions Sensors vehicle collision avoidance data analytics prediction time-to-collision back-propagation neural network data fitting |
author_facet |
Keng-Pin Chen Pao-Ann Hsiung |
author_sort |
Keng-Pin Chen |
title |
Vehicle Collision Prediction under Reduced Visibility Conditions |
title_short |
Vehicle Collision Prediction under Reduced Visibility Conditions |
title_full |
Vehicle Collision Prediction under Reduced Visibility Conditions |
title_fullStr |
Vehicle Collision Prediction under Reduced Visibility Conditions |
title_full_unstemmed |
Vehicle Collision Prediction under Reduced Visibility Conditions |
title_sort |
vehicle collision prediction under reduced visibility conditions |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2018-09-01 |
description |
Rear-end collisions often cause serious traffic accidents. Conventionally, in intelligent transportation systems (ITS), radar collision warning methods are highly accurate in determining the inter-vehicle distance via detecting the rear-end of a vehicle; however, in poor weather conditions such as fog, rain, or snow, the accuracy is significantly affected. In recent years, the advent of Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication systems has introduced new methods for solving the rear-end collision problem. Nevertheless, there is still much left for improvement. For instance, weather conditions have an impact on human-related factors such as response time. To address the issue of collision detection under low visibility conditions, we propose a Visibility-based Collision Warning System (ViCoWS) design that includes four models for prediction horizon estimation, velocity prediction, headway distance prediction, and rear-end collision warning. Based on the history of velocity data, future velocity volumes are predicted. Then, the prediction horizon (number of future time slots to consider) is estimated corresponding to different weather conditions. ViCoWs can respond in real-time to weather conditions with correct collision avoidance warnings. Experiment results show that the mean absolute percentage error of our velocity prediction model is less than 11%. For non-congested traffic under heavy fog (very low visibility of 120 m), ViCoWS warns a driver by as much as 4.5 s prior to a possible future collision. If the fog is medium with a low visibility of 160 m, ViCoWs can give warnings by about 2.1 s prior to a possible future collision. In contrast, the Forward Collision Probability Index (FCPI) method gives warnings by only about 0.6 s before a future collision. For congested traffic under low visibility conditions, ViCoWS can warn a driver by about 1.9 s prior to a possible future collision. In this case, the FCPI method gives 1.2 s for the driver to react before collision. |
topic |
vehicle collision avoidance data analytics prediction time-to-collision back-propagation neural network data fitting |
url |
http://www.mdpi.com/1424-8220/18/9/3026 |
work_keys_str_mv |
AT kengpinchen vehiclecollisionpredictionunderreducedvisibilityconditions AT paoannhsiung vehiclecollisionpredictionunderreducedvisibilityconditions |
_version_ |
1725776019847118848 |