Users Login
Column
MORE+
01 Intelligent Vehicles Localization Based on Semantic Map Representation from 3D Point Clouds
02 An Overview of Traffic Management in "Automatic+Manual" Driving Environment
04 A Cooperative Map Matching Algorithm Applied in Intelligent and Connected Vehicle Positioning
05 Indoor Sign-based Visual Localization Method
06 An Analysis of Highway-traffic Safety Based on Dynamic Risk Saturation
07 An Image Generation Method for Automated Driving Based on Improved GAN
08 Companion Relationship Discovering Algorithm for Passengers in the Cruise Based on UWB Positioning
09 An Analysis of Injury Severities in School Bus Accidents Based on Random Parameter Logit Models
Display Method:
, Available online
Abstract:
, Available online
Abstract:
, Available online
Abstract:
, Available online
Abstract:
Display Method:
2022, 40(1): 1-9.
doi: 10.3963/j.jssn.1674-4861.2022.01.001
Abstract:
It is of great importance to study the safety risk of amphibious seaplanes during their take-off and landing, since accidents occur frequently in these two phases. Based on the SEIRS model for disease transmission, considering the propagation and delay mechanism on safety risk of amphibious seaplane during take-off and landing, a risk propagation delay(D-SEIRS)model based on a scale-free network is developed to study the propagation mechanism of safety risk during the take-off and landing of amphibious seaplanes. The Routh-Hurwitz Criterion is used to analyze the stability of the equilibrium in the proposed model and solve for the steady-state density(SSD)and basic regeneration number of the proposed model. A numeric simulation based on the MATLAB software is performed using the proposed model, which discloses the dynamic propagation law of the safety risk during the take-off and landing of amphibious seaplanes. Study results show that both the effective propagation rate(EPR) and the propagation delay time(PDT)can lead to the increase of the steady-state density of the infected nodes of the network; the propagation delay can reduce the risk propagation threshold in the network and accelerate the emerging of risk outbreak state; the propagation rates of both latent nodes and infected nodes will lead to an increase in the steady-state density of infected nodes and latent nodes, and the effective propagation rate of latent nodes has a more prominent impact on risk propagation over the network than that of the infected nodes.
It is of great importance to study the safety risk of amphibious seaplanes during their take-off and landing, since accidents occur frequently in these two phases. Based on the SEIRS model for disease transmission, considering the propagation and delay mechanism on safety risk of amphibious seaplane during take-off and landing, a risk propagation delay(D-SEIRS)model based on a scale-free network is developed to study the propagation mechanism of safety risk during the take-off and landing of amphibious seaplanes. The Routh-Hurwitz Criterion is used to analyze the stability of the equilibrium in the proposed model and solve for the steady-state density(SSD)and basic regeneration number of the proposed model. A numeric simulation based on the MATLAB software is performed using the proposed model, which discloses the dynamic propagation law of the safety risk during the take-off and landing of amphibious seaplanes. Study results show that both the effective propagation rate(EPR) and the propagation delay time(PDT)can lead to the increase of the steady-state density of the infected nodes of the network; the propagation delay can reduce the risk propagation threshold in the network and accelerate the emerging of risk outbreak state; the propagation rates of both latent nodes and infected nodes will lead to an increase in the steady-state density of infected nodes and latent nodes, and the effective propagation rate of latent nodes has a more prominent impact on risk propagation over the network than that of the infected nodes.
2022, 40(1): 10-18.
doi: 10.3963/j.jssn.1674-4861.2022.01.002
Abstract:
Based on the analyses of driving behavior of manually operated, adaptive cruise control(ACC), and cooperative adaptive cruise control(CACC)vehicles, this paper investigates the impact of proportion of CACC vehicles on the safety of mixed-traffic-flow at off-ramp diverging areas in a simulated environment, which is established based on a car-following model and a lane-changing model. Specifically, a full velocity difference model, an ACC car-following model and a CACC car-following model are used as the longitudinal car-following models for manually operated, ACC, and CACC vehicles, respectively. A discretionary lane-changing model and a mandatory lane-changing model are customized to develop the lateral lane-changing model for all types of vehicles at the main and end sections of off-ramp diverging areas, respectively. Next, a set of evaluation indices for traffic safety are proposed based on the following parameters such as time-to-collision(TTC), time exposed time-to-collision(TET) and time integrated time-to-collision(TIT). The MATLAB software is used to analyze the safety for mixed traffic flows under the scenarios with different proportions of CACC vehicles. The results show that: when the proportion of CACC vehicles ranges between 40% and 50%, the safety of mixed traffic flow deteriorates most, TET and TIT increase by about 68% and 89%, respectively, and the speed dispersion coefficient is as large as more than 0.9. Study results also indicate that the risk of rear-end collision for mixed traffic flow can be effectively reduced by adding the mandatory lane-changing area(≤ 1 000 m)at the far-end of off-ramp diverging area.
Based on the analyses of driving behavior of manually operated, adaptive cruise control(ACC), and cooperative adaptive cruise control(CACC)vehicles, this paper investigates the impact of proportion of CACC vehicles on the safety of mixed-traffic-flow at off-ramp diverging areas in a simulated environment, which is established based on a car-following model and a lane-changing model. Specifically, a full velocity difference model, an ACC car-following model and a CACC car-following model are used as the longitudinal car-following models for manually operated, ACC, and CACC vehicles, respectively. A discretionary lane-changing model and a mandatory lane-changing model are customized to develop the lateral lane-changing model for all types of vehicles at the main and end sections of off-ramp diverging areas, respectively. Next, a set of evaluation indices for traffic safety are proposed based on the following parameters such as time-to-collision(TTC), time exposed time-to-collision(TET) and time integrated time-to-collision(TIT). The MATLAB software is used to analyze the safety for mixed traffic flows under the scenarios with different proportions of CACC vehicles. The results show that: when the proportion of CACC vehicles ranges between 40% and 50%, the safety of mixed traffic flow deteriorates most, TET and TIT increase by about 68% and 89%, respectively, and the speed dispersion coefficient is as large as more than 0.9. Study results also indicate that the risk of rear-end collision for mixed traffic flow can be effectively reduced by adding the mandatory lane-changing area(≤ 1 000 m)at the far-end of off-ramp diverging area.
2022, 40(1): 19-27.
doi: 10.3963/j.jssn.1674-4861.2022.01.003
Abstract:
In order to analyze the characteristics of vehicle control behaviors and study its relationship with rear-end collision risk under foggy conditions, a driving simulationexperiment is conducted, and corresponding behaviors under foggy weather is compared with that under good visibility using ANONA and mixed-effect regression model. Further, the relationship between vehicle control behavior and rear-end collision risk is investigated by correlation analysis and a binary logistic regression model. The results show that the standard deviations of lane departure under foggy conditions are 20.8% higher than that under good visibility conditions, indicates poor vehicle control of drivers under foggy conditions. Besides, drivers prefer to keep shorter time headway, in order to maintain a good vision to the vehicles in front under foggy weather. It is also found that, during the process of avoiding rear-end collision, average deceleration underfoggy weather is 1.1 times of that under good weather. Moreover, study results show that the average minimum time headway under foggy conditions is 0.475 s shorter than that undergood visibility conditions, which results in the rear-end collision risk increases by 4.93 times.
In order to analyze the characteristics of vehicle control behaviors and study its relationship with rear-end collision risk under foggy conditions, a driving simulationexperiment is conducted, and corresponding behaviors under foggy weather is compared with that under good visibility using ANONA and mixed-effect regression model. Further, the relationship between vehicle control behavior and rear-end collision risk is investigated by correlation analysis and a binary logistic regression model. The results show that the standard deviations of lane departure under foggy conditions are 20.8% higher than that under good visibility conditions, indicates poor vehicle control of drivers under foggy conditions. Besides, drivers prefer to keep shorter time headway, in order to maintain a good vision to the vehicles in front under foggy weather. It is also found that, during the process of avoiding rear-end collision, average deceleration underfoggy weather is 1.1 times of that under good weather. Moreover, study results show that the average minimum time headway under foggy conditions is 0.475 s shorter than that undergood visibility conditions, which results in the rear-end collision risk increases by 4.93 times.
2022, 40(1): 28-35.
doi: 10.3963/j.jssn.1674-4861.2022.01.004
Abstract:
In this study, a negative binomial model is developed to investigate factors influencing crashes on freeways such as traffic flow, freeway alignment and pavement conditions. Since traditional fixed-effects models are incapable of capturing the heterogeneous effects of these factors on crash risk, a random-effects modeling method is introduced. Results indicate that the proposed random-effects negative binomial model has a better goodness-of-fit compared with its fixed-effects counterpart. In addition, the model explains the impact of the related factors on road safety in a more reasonable way. The interactions of the impact factors used in the model can be further studied by setting up the mean of a random parameter to be a functional form of other variables. It is found that traffic volume, length of road section, proportion of truck traffic, curvature, longitudinal grade and rutting depth are all positively correlated with crash frequency and 1% of increase in aforementioned variables increases the expected crash risk by 0.299%, 1.029%, 0.093%, 0.079%, 0.068%, and 0.054%, respectively. The pavement structural strength index is negatively correlated with crashes, and one percent of increase of the index will reduce the expected crash risk by 0.064%. Increasing the width of marginal strip is found to be beneficial to enhance safety. Three- or four-lane one-way freeway sections are found to experience more crashes than two-lane one-way freeway sections. It is also found that a segment with the combined alignment of curves and slopes is significantly more dangerous than a flat curved segment and the crash risk is considerably higher for downhill segments with a high proportion of truck flow.
In this study, a negative binomial model is developed to investigate factors influencing crashes on freeways such as traffic flow, freeway alignment and pavement conditions. Since traditional fixed-effects models are incapable of capturing the heterogeneous effects of these factors on crash risk, a random-effects modeling method is introduced. Results indicate that the proposed random-effects negative binomial model has a better goodness-of-fit compared with its fixed-effects counterpart. In addition, the model explains the impact of the related factors on road safety in a more reasonable way. The interactions of the impact factors used in the model can be further studied by setting up the mean of a random parameter to be a functional form of other variables. It is found that traffic volume, length of road section, proportion of truck traffic, curvature, longitudinal grade and rutting depth are all positively correlated with crash frequency and 1% of increase in aforementioned variables increases the expected crash risk by 0.299%, 1.029%, 0.093%, 0.079%, 0.068%, and 0.054%, respectively. The pavement structural strength index is negatively correlated with crashes, and one percent of increase of the index will reduce the expected crash risk by 0.064%. Increasing the width of marginal strip is found to be beneficial to enhance safety. Three- or four-lane one-way freeway sections are found to experience more crashes than two-lane one-way freeway sections. It is also found that a segment with the combined alignment of curves and slopes is significantly more dangerous than a flat curved segment and the crash risk is considerably higher for downhill segments with a high proportion of truck flow.
2022, 40(1): 36-44.
doi: 10.3963/j.jssn.1674-4861.2022.01.005
Abstract:
With continuous improvement of laws and regulations related to road safety in China, traffic police departments are required to issue different penalties for specific traffic violations. In response to the call and to improve the capacity of"intelligent governance", this article proposes to develop a knowledge base for traffic violations and accidents with event evolutionary graph, which can be used to reason appropriate penalty for traffic violations& accidents quickly and efficiently. This paper uses open-source data to develop the knowledge base required for processing traffic violations/accidents and creates an event evolutionary graph through extracting traffic events and their relationship. Moreover, a knowledge base system for traffic violations/accidents is developed. The experimental results show that the proposed system offers a F1 score of 0.832 when classifying traffic violations and accidents, which indicates that the event evolutionary graph is a good tool for reasoning the penalty of traffic violations and accidents.
With continuous improvement of laws and regulations related to road safety in China, traffic police departments are required to issue different penalties for specific traffic violations. In response to the call and to improve the capacity of"intelligent governance", this article proposes to develop a knowledge base for traffic violations and accidents with event evolutionary graph, which can be used to reason appropriate penalty for traffic violations& accidents quickly and efficiently. This paper uses open-source data to develop the knowledge base required for processing traffic violations/accidents and creates an event evolutionary graph through extracting traffic events and their relationship. Moreover, a knowledge base system for traffic violations/accidents is developed. The experimental results show that the proposed system offers a F1 score of 0.832 when classifying traffic violations and accidents, which indicates that the event evolutionary graph is a good tool for reasoning the penalty of traffic violations and accidents.
2022, 40(1): 45-53.
doi: 10.3963/j.jssn.1674-4861.2022.01.006
Abstract:
In order to improve the efficiency of signalized intersections under the consideration of the courtesy rules from vehicles to pedestrians, a timing optimization method based on superposition-phase is proposed. A typical intersection from Xi'an is taken as a case study. The conflicts between vehicles and pedestrians are analyzed. Based on Webster's timing model, a timing optimization model is developed, which combines superposition phase design and space-time separation strategy for reducing the conflicts between vehicles and pedestrians. In addition, the calculation methods for starting time of pedestrian phase and the threshold for adopting vehicle-pedestrian phase separation strategy are proposed. Then VISSIM simulation software is used to verify the effectiveness of the proposed signal timing optimization schemes. The simulation results show that compared to the current scheme, the scheme from the proposed timing optimization method can reduce the average vehicle delay, delay per capita, total vehicle delay, total pedestrian delay and total intersection delay by 27.11%, 22.41%, 27.08%, 22.49%, and 26.15%, respectively. In addition, it can also reduce the emissions of VOC, CO, NOx, and fuel consumption by 3.76%, 3.76%, 3.76%, and 3.78%, respectively. The proposed method can effectively reduce the vehicle-pedestrian conflicts and improve the efficiency of traffic operation at signalized intersections.
In order to improve the efficiency of signalized intersections under the consideration of the courtesy rules from vehicles to pedestrians, a timing optimization method based on superposition-phase is proposed. A typical intersection from Xi'an is taken as a case study. The conflicts between vehicles and pedestrians are analyzed. Based on Webster's timing model, a timing optimization model is developed, which combines superposition phase design and space-time separation strategy for reducing the conflicts between vehicles and pedestrians. In addition, the calculation methods for starting time of pedestrian phase and the threshold for adopting vehicle-pedestrian phase separation strategy are proposed. Then VISSIM simulation software is used to verify the effectiveness of the proposed signal timing optimization schemes. The simulation results show that compared to the current scheme, the scheme from the proposed timing optimization method can reduce the average vehicle delay, delay per capita, total vehicle delay, total pedestrian delay and total intersection delay by 27.11%, 22.41%, 27.08%, 22.49%, and 26.15%, respectively. In addition, it can also reduce the emissions of VOC, CO, NOx, and fuel consumption by 3.76%, 3.76%, 3.76%, and 3.78%, respectively. The proposed method can effectively reduce the vehicle-pedestrian conflicts and improve the efficiency of traffic operation at signalized intersections.
2022, 40(1): 54-62.
doi: 10.3963/j.jssn.1674-4861.2022.01.007
Abstract:
In order to improve traffic safety of highway segments with continuous tunnels, visual characteristics of drivers are analyzed. An experimentfor collecting characteristics of drivers'eye movement is designed in actual highway scenes. Eye movement data of 20 drivers, such as fixation, scanning, and pupil area change is collected with TobiiGlass2 and ErgoLAB data analytics tool. The visual characteristics of drivers inside different tunnels and at different sections are compared and analyzed. Study results show that the average view angle is higher in the first tunnel than that in the second tunnel in the horizontal direction, but it is opposite in the vertical direction. Average saccade time of the second tunnel is 47.75% shorter than that of the first tunnel. Average pupil diameter of the first tunnel is 7.89% larger than that of the second tunnel. Mean and variance of change rate of the pupil area at the entrance segment of the first tunnel are larger than that of the second tunnel. It can be concluded that when driving through the second tunnel over continuous highway tunnels, drivers' visual load isreduced, and visual stability is improved, when compared to those observed over the first tunnel.
In order to improve traffic safety of highway segments with continuous tunnels, visual characteristics of drivers are analyzed. An experimentfor collecting characteristics of drivers'eye movement is designed in actual highway scenes. Eye movement data of 20 drivers, such as fixation, scanning, and pupil area change is collected with TobiiGlass2 and ErgoLAB data analytics tool. The visual characteristics of drivers inside different tunnels and at different sections are compared and analyzed. Study results show that the average view angle is higher in the first tunnel than that in the second tunnel in the horizontal direction, but it is opposite in the vertical direction. Average saccade time of the second tunnel is 47.75% shorter than that of the first tunnel. Average pupil diameter of the first tunnel is 7.89% larger than that of the second tunnel. Mean and variance of change rate of the pupil area at the entrance segment of the first tunnel are larger than that of the second tunnel. It can be concluded that when driving through the second tunnel over continuous highway tunnels, drivers' visual load isreduced, and visual stability is improved, when compared to those observed over the first tunnel.
2022, 40(1): 63-71.
doi: 10.3963/j.jssn.1674-4861.2022.01.008
Abstract:
Aiming at preventing Officers on Watch (OOW) from fatigue driving, a fatigue detection and alert algorithm based on deep learning technique is developed. Considering the large space and complex background of the ship bridge, the RetinaFace model is improved by using Depthwise Separable Convolution to optimize the detection speed. An upgraded ShuffleNetV2 network is then developed by adopting the concepts of Channel Split, Channel Shuffle, and other techniques such as batch normalization and global average pooling. The proposed algorithm can extract image features and automatically identify the opening and closing of the eyes and mouth of the OOW. According to the PERCLOS criteria, the two features of the eyes and mouth are integrated to determine whether the OOW is fatigued. Experimental results show that the detection speed of the improved RetinaFace model improves from 9.33 to 22.60 frames/s. The detection accuracy and speed for the face detection are superior to the multi-task convolutional neural network. The upgraded ShuffleNetV2 network achieves over 99.50% accuracy in recognizing the states of eyes and mouth. The algorithm has an accuracy of 95.70% and a recall rate of 96.73% in identifying the fatigue state in a simulated ship bridge scenario, which are higher than Haar-like+Adaboost and MTCNN+CNN fatigue detection algorithmsused in practice. It only takes 0.083 s for the algorithm to complete the process, which indicates that the algorithm is capable of carrying out real-time detection.
Aiming at preventing Officers on Watch (OOW) from fatigue driving, a fatigue detection and alert algorithm based on deep learning technique is developed. Considering the large space and complex background of the ship bridge, the RetinaFace model is improved by using Depthwise Separable Convolution to optimize the detection speed. An upgraded ShuffleNetV2 network is then developed by adopting the concepts of Channel Split, Channel Shuffle, and other techniques such as batch normalization and global average pooling. The proposed algorithm can extract image features and automatically identify the opening and closing of the eyes and mouth of the OOW. According to the PERCLOS criteria, the two features of the eyes and mouth are integrated to determine whether the OOW is fatigued. Experimental results show that the detection speed of the improved RetinaFace model improves from 9.33 to 22.60 frames/s. The detection accuracy and speed for the face detection are superior to the multi-task convolutional neural network. The upgraded ShuffleNetV2 network achieves over 99.50% accuracy in recognizing the states of eyes and mouth. The algorithm has an accuracy of 95.70% and a recall rate of 96.73% in identifying the fatigue state in a simulated ship bridge scenario, which are higher than Haar-like+Adaboost and MTCNN+CNN fatigue detection algorithmsused in practice. It only takes 0.083 s for the algorithm to complete the process, which indicates that the algorithm is capable of carrying out real-time detection.
2021, 39(5): 1-11.
doi: 10.3963/j.jssn.1674-4861.2021.05.001
Abstract:
Journal of Transport Information and Safety
(Founded in 1983 bimonthly )
Former Name：Computer and Communications
Supervised by：Ministry of Education of P. R. CHINA
Sponsored by：Wuhan University of Technology
Network of Computer Application Information in Transportation
In Association With：Intelligent Transportation Committee of China Association of Artificial Intelligence
Editor-in-Chief：ZHONG Ming
Edited and Published by：Editorial Office of Transport Information and Safety
Address：No. 1178，Heping Avenue, Wuchang, Wuhan, CHINA
Postcode：430063
Tel：027-86580355
E-mail：jtjsj@vip.163.com
Website：http://www.jtxa.net/
Postal Code：38-94
Domestic Issue：
CN 42-1781/U
Publication No.：ISSN 1674-4861
Indexed In
- Chinese Core Journal in “Integrated Transportation” category
- Chinese Science Citation Database (CSCD)
- Core Science and Technology Journals
- Chinese Scientific and Technological Papers and Citations (CSTPCD)
- Class A of Research Center for Chinese Science Evaluation (RCCSE)
- Chinese Academic Journal Comprehensive Evaluation Database (CAJ-CED)
- Chinese Core Journals (Selection) Database
- Chinese Scientific and Technological Periodicals Database
- China National Knowledge Infrastructure (CNKI)
- Chinese Academic Journals (CAJ-CD)
- Chinese Lifelong Education Academic Research Database
- Japan Science and Technology Agency (JST)
- World Journal Clout Index Report (2020 STM)