Road transport safety policies have emphasized road infrastructure safety design and engineering as a core function.However,in developing countries like Vietnam,this approach has been slower to adopt,resulting in subs...Road transport safety policies have emphasized road infrastructure safety design and engineering as a core function.However,in developing countries like Vietnam,this approach has been slower to adopt,resulting in substandard roads.In-depth studies of accident locations indicate that road environment factors contribute significantly to road accidents in Vietnam and road design features are associated with specific accident types and hazards.Proactive and reactive approaches,such as road safety audit,inspection,assessment,and treatment of hazardous locations,are necessary to ensure that the road and its environment are safe.This paper provides an overview of road safety in Vietnam in general,and Ho Chi Minh in particular,including its factors and characteristics,as well as road infrastructure safety improvements.The iRap tool for road safety inspection and assessment is highlighted as a potential method for systematically analyzing road infrastructure deficiencies and providing targeted countermeasures to improve road safety under mixed traffic conditions.展开更多
In order to analyze and learn the difference in car-following behavior between normal and rainy days, we first collect car-following trajectory data of an urban elevated road on normal and rainy days by microwave rada...In order to analyze and learn the difference in car-following behavior between normal and rainy days, we first collect car-following trajectory data of an urban elevated road on normal and rainy days by microwave radar and analyze the differences in speed, relative speed, acceleration, space headway, and time headway among data through statistics. Secondly, owing to the time-series characteristics of car-following data, we use the long short-term memory(LSTM) neural network optimized by attention mechanism(AM) and sparrow search algorithm(SSA) to learn the different car-following behaviors under different weather conditions and build corresponding models(ASL-Normal, ASL-Rain, where ASL stands for AM-SSA-LSTM), respectively. Finally, the simulation test shows that the mean square error(MSE) and reciprocal of time-to-collision(RTTC) of the ASL model are better than those of LSTM and intelligent diver model(IDM), which is closer to the real data. The ASL model can better learn different driving behaviors on normal and rainy days. However,it has a higher sensitivity to weather conditions from cross test on normal and rainy data-sets which need classification training or sample diversification processing. In the car-following platoon simulation, the stability performances of two models are excellent, which can describe the basic characteristics of traffic flow on normal and rainy days. Comparing with ASL-Rain model, the convergence time of ASL-Normal is shorter, reflecting that cautious driving behavior on rainy days will reduce traffic efficiency to a certain extent. However, ASL-Normal model produces a more severe and frequent traffic oscillation within a shorter period because of aggressive driving behavior on normal days.展开更多
A pre-selection space time model was proposed to estimate the traffic condition at poor-data-detector,especially non-detector locations.The space time model is better to integrate the spatial and temporal information ...A pre-selection space time model was proposed to estimate the traffic condition at poor-data-detector,especially non-detector locations.The space time model is better to integrate the spatial and temporal information comprehensibly.Firstly,the influencing factors of the "cause nodes" were studied,and then the pre-selection "cause nodes" procedure which utilizes the Pearson correlation coefficient to evaluate the relevancy of the traffic data was introduced.Finally,only the most relevant data were collected to compose the space time model.The experimental results with the actual data demonstrate that the model performs better than other three models.展开更多
In order to investigate enhancements to cell transmission model (CTM) as a tool for traffic signal timing in oversaturated conditions, randomly distributed saturation flow rates and arrival rates were used instead of ...In order to investigate enhancements to cell transmission model (CTM) as a tool for traffic signal timing in oversaturated conditions, randomly distributed saturation flow rates and arrival rates were used instead of constant values to simulate traffic flow movement, estimate the average delay of the network and search for an optimal traffic signal timing plan. A case study was given to demonstrate that the proposed methodology can capture unique phenomena in oversaturated conditions such as forward wave, spillback and lane entrance blockage. The results show that CTM underestimates travel time by 25% when compared to Simtraffic, while the enhanced CTM underestimates by only 3%. A second case study shows that a dynamic signal timing plan is superior to a fixed signal timing plan in the term of average delay.展开更多
The paper promotes the implementation of a neural network approach to improve one of the most transcendent traffic conditions: the mobility of the cars in any particular junction. Neural networks have proven to be an ...The paper promotes the implementation of a neural network approach to improve one of the most transcendent traffic conditions: the mobility of the cars in any particular junction. Neural networks have proven to be an effective paradigm of modern computing, providing extensive benefits in a wide range of applications. In this sense, the paper uses a BPNN (backpropagation neural network) model. The three input nodes are related to: n1: the amount of cars in the road; n2: the green light interval; and n3:the distance (taking into account the quantity of cars) between the first car in the intersection and the last car in the longest line in front of it. In particular, the paper promotes that each traffic light signal will be capable of offering a new green light interval according to the requirement and constrains of the vitality, ensuring a vehicular mobility level greater than 65%. To assess this idea, the paper presents two experiments confronting the real world data versus experimental results. For example, in the first experiment, the BPNN improves the performance of the real data about vehicular mobility in almost 30%. Finally, some conclusions and future work are presented.展开更多
In developing countries, the numbers of traffic accidents, injuries and fatalities are very high and tend to increase atsignalized intersections. For example, in Ho Chi Minh City (HCMC) of Vietnam, the number of acc...In developing countries, the numbers of traffic accidents, injuries and fatalities are very high and tend to increase atsignalized intersections. For example, in Ho Chi Minh City (HCMC) of Vietnam, the number of accidents at signalized intersectionsaccounted for 45% of the total accidents at all the intersections. This fact leads to strong necessity for analyzing traffic safety atsignalized intersections. Nevertheless, the historical accident data in HCMC is not available for deep analysis, this study uses videocameras to capture and analyze conflicts that potentially lead to accidents using TCT (traffic conflict technique). Conflict severityidentification is one of the most significant steps to evaluate traffic safety at signalized intersections using TCT. Six zones (seriousconflict, common conflict, non-conflict, highest potential serious conflict, potential serious conflict, and potential common conflict) areexplored in this study to clarify conflict severity. This result is based on being the cut off value between serious conflicts and commonconflicts, according to 85% cumulative frequency of TTC (time to collision) and CS (conflict speed) under 3,050 samples size whichwere observed at 10 signalized intersections during August-November, 2014. Such a deep understanding is a scientific basis to studyhow to apply TCT to evaluate traffic safety at signalized intersections under mixed traffic conditions.展开更多
Regarding the postulate of traffic infrastructure and vehicles, much attention should be given to the effect of road conditions on accidents. With large numbers of traffic accidents on Shenda Freeway, Liaoning Provinc...Regarding the postulate of traffic infrastructure and vehicles, much attention should be given to the effect of road conditions on accidents. With large numbers of traffic accidents on Shenda Freeway, Liaoning Province, Harbin City and others in P. R. China, parameters and the effect of accidents caused by horizontal alignment, vertical alignment, cross section and intersection are studied systematically The disciplinary analysis of these effects are presented in this paper. The viewpoint is acknowledged that high sub grade and steep slopes are against traffic safety, which is common and ignored in high-usage highways in China. Design parameters of the current design criteria and the corresponding countermeasures are suggested for safety on our highways.展开更多
The objective of this work is to develop a novel feature for traffic flow models,when traffic queues on two-way arterials periodically extend until then they block an upstream signal in oversaturated conditions.The ne...The objective of this work is to develop a novel feature for traffic flow models,when traffic queues on two-way arterials periodically extend until then they block an upstream signal in oversaturated conditions.The new model,proposed as conditional cell transmission model(CCTM) has been developed with two improvements.First,cell transmission model(CTM) is expanded for two-way arterials by taking account of all diverging and merging activities at intersections.Second,a conditional cell is added to simulate periodic spillback and blockages at an intersection.The results of experiments for a multilane,two-way,three-signal sample network demonstrate that CCTM can accommodate various traffic demands and accurate representation of blockages at intersections.The delay of left turns is underestimated by 40 % in moderate conditions and by 58% in oversaturated condition when using the CTM rather than CCTM.Finally,the consistency between HCS 2000 and CCTM shows that CCTM is a reliable methodology of modeling traffic flow in oversaturated condition.展开更多
To reduce the computation cost of a combined probabilistic graphical model and a deep neural network in semantic segmentation, the local region condition random field (LRCRF) model is investigated which selectively ap...To reduce the computation cost of a combined probabilistic graphical model and a deep neural network in semantic segmentation, the local region condition random field (LRCRF) model is investigated which selectively applies the condition random field (CRF) to the most active region in the image. The full convolutional network structure is optimized with the ResNet-18 structure and dilated convolution to expand the receptive field. The tracking networks are also improved based on SiameseFC by considering the frame relations in consecutive-frame traffic scene maps. Moreover, the segmentation results of the greyscale input data sets are more stable and effective than using the RGB images for deep neural network feature extraction. The experimental results show that the proposed method takes advantage of the image features directly and achieves good real-time performance and high segmentation accuracy.展开更多
文摘Road transport safety policies have emphasized road infrastructure safety design and engineering as a core function.However,in developing countries like Vietnam,this approach has been slower to adopt,resulting in substandard roads.In-depth studies of accident locations indicate that road environment factors contribute significantly to road accidents in Vietnam and road design features are associated with specific accident types and hazards.Proactive and reactive approaches,such as road safety audit,inspection,assessment,and treatment of hazardous locations,are necessary to ensure that the road and its environment are safe.This paper provides an overview of road safety in Vietnam in general,and Ho Chi Minh in particular,including its factors and characteristics,as well as road infrastructure safety improvements.The iRap tool for road safety inspection and assessment is highlighted as a potential method for systematically analyzing road infrastructure deficiencies and providing targeted countermeasures to improve road safety under mixed traffic conditions.
基金Project supported by the National Natural Science Foundation of China (Grant No. 52072108)the Natural Science Foundation of Anhui Province, China (Grant No. 2208085ME148)the Open Fund for State Key Laboratory of Cognitive Intelligence, China (Grant No. W2022JSKF0504)。
文摘In order to analyze and learn the difference in car-following behavior between normal and rainy days, we first collect car-following trajectory data of an urban elevated road on normal and rainy days by microwave radar and analyze the differences in speed, relative speed, acceleration, space headway, and time headway among data through statistics. Secondly, owing to the time-series characteristics of car-following data, we use the long short-term memory(LSTM) neural network optimized by attention mechanism(AM) and sparrow search algorithm(SSA) to learn the different car-following behaviors under different weather conditions and build corresponding models(ASL-Normal, ASL-Rain, where ASL stands for AM-SSA-LSTM), respectively. Finally, the simulation test shows that the mean square error(MSE) and reciprocal of time-to-collision(RTTC) of the ASL model are better than those of LSTM and intelligent diver model(IDM), which is closer to the real data. The ASL model can better learn different driving behaviors on normal and rainy days. However,it has a higher sensitivity to weather conditions from cross test on normal and rainy data-sets which need classification training or sample diversification processing. In the car-following platoon simulation, the stability performances of two models are excellent, which can describe the basic characteristics of traffic flow on normal and rainy days. Comparing with ASL-Rain model, the convergence time of ASL-Normal is shorter, reflecting that cautious driving behavior on rainy days will reduce traffic efficiency to a certain extent. However, ASL-Normal model produces a more severe and frequent traffic oscillation within a shorter period because of aggressive driving behavior on normal days.
基金Project(D101106049710005) supported by the Beijing Science Foundation Program,ChinaProject(61104164) supported by the National Natural Science Foundation,China
文摘A pre-selection space time model was proposed to estimate the traffic condition at poor-data-detector,especially non-detector locations.The space time model is better to integrate the spatial and temporal information comprehensibly.Firstly,the influencing factors of the "cause nodes" were studied,and then the pre-selection "cause nodes" procedure which utilizes the Pearson correlation coefficient to evaluate the relevancy of the traffic data was introduced.Finally,only the most relevant data were collected to compose the space time model.The experimental results with the actual data demonstrate that the model performs better than other three models.
基金Project(51108343) supported by the National Natural Science Foundation of ChinaProject(06121) supported by University of Transportation Center for Alabama, USA
文摘In order to investigate enhancements to cell transmission model (CTM) as a tool for traffic signal timing in oversaturated conditions, randomly distributed saturation flow rates and arrival rates were used instead of constant values to simulate traffic flow movement, estimate the average delay of the network and search for an optimal traffic signal timing plan. A case study was given to demonstrate that the proposed methodology can capture unique phenomena in oversaturated conditions such as forward wave, spillback and lane entrance blockage. The results show that CTM underestimates travel time by 25% when compared to Simtraffic, while the enhanced CTM underestimates by only 3%. A second case study shows that a dynamic signal timing plan is superior to a fixed signal timing plan in the term of average delay.
文摘The paper promotes the implementation of a neural network approach to improve one of the most transcendent traffic conditions: the mobility of the cars in any particular junction. Neural networks have proven to be an effective paradigm of modern computing, providing extensive benefits in a wide range of applications. In this sense, the paper uses a BPNN (backpropagation neural network) model. The three input nodes are related to: n1: the amount of cars in the road; n2: the green light interval; and n3:the distance (taking into account the quantity of cars) between the first car in the intersection and the last car in the longest line in front of it. In particular, the paper promotes that each traffic light signal will be capable of offering a new green light interval according to the requirement and constrains of the vitality, ensuring a vehicular mobility level greater than 65%. To assess this idea, the paper presents two experiments confronting the real world data versus experimental results. For example, in the first experiment, the BPNN improves the performance of the real data about vehicular mobility in almost 30%. Finally, some conclusions and future work are presented.
文摘In developing countries, the numbers of traffic accidents, injuries and fatalities are very high and tend to increase atsignalized intersections. For example, in Ho Chi Minh City (HCMC) of Vietnam, the number of accidents at signalized intersectionsaccounted for 45% of the total accidents at all the intersections. This fact leads to strong necessity for analyzing traffic safety atsignalized intersections. Nevertheless, the historical accident data in HCMC is not available for deep analysis, this study uses videocameras to capture and analyze conflicts that potentially lead to accidents using TCT (traffic conflict technique). Conflict severityidentification is one of the most significant steps to evaluate traffic safety at signalized intersections using TCT. Six zones (seriousconflict, common conflict, non-conflict, highest potential serious conflict, potential serious conflict, and potential common conflict) areexplored in this study to clarify conflict severity. This result is based on being the cut off value between serious conflicts and commonconflicts, according to 85% cumulative frequency of TTC (time to collision) and CS (conflict speed) under 3,050 samples size whichwere observed at 10 signalized intersections during August-November, 2014. Such a deep understanding is a scientific basis to studyhow to apply TCT to evaluate traffic safety at signalized intersections under mixed traffic conditions.
文摘Regarding the postulate of traffic infrastructure and vehicles, much attention should be given to the effect of road conditions on accidents. With large numbers of traffic accidents on Shenda Freeway, Liaoning Province, Harbin City and others in P. R. China, parameters and the effect of accidents caused by horizontal alignment, vertical alignment, cross section and intersection are studied systematically The disciplinary analysis of these effects are presented in this paper. The viewpoint is acknowledged that high sub grade and steep slopes are against traffic safety, which is common and ignored in high-usage highways in China. Design parameters of the current design criteria and the corresponding countermeasures are suggested for safety on our highways.
基金Supported by the Programs for the New Century Excellent Talents in University under Grant No. NCET-08-0038the National Natural Science Foundation of China under Grant Nos. 70701002, 70971007 and 70521001the State Key Basic Research Program of China under Grant No. 2006CB705503
基金Project(51108343) supported by the National Natural Science Foundation of ChinaProject(06121) supported by University of Transportation Center for Alabama,USA
文摘The objective of this work is to develop a novel feature for traffic flow models,when traffic queues on two-way arterials periodically extend until then they block an upstream signal in oversaturated conditions.The new model,proposed as conditional cell transmission model(CCTM) has been developed with two improvements.First,cell transmission model(CTM) is expanded for two-way arterials by taking account of all diverging and merging activities at intersections.Second,a conditional cell is added to simulate periodic spillback and blockages at an intersection.The results of experiments for a multilane,two-way,three-signal sample network demonstrate that CCTM can accommodate various traffic demands and accurate representation of blockages at intersections.The delay of left turns is underestimated by 40 % in moderate conditions and by 58% in oversaturated condition when using the CTM rather than CCTM.Finally,the consistency between HCS 2000 and CCTM shows that CCTM is a reliable methodology of modeling traffic flow in oversaturated condition.
文摘To reduce the computation cost of a combined probabilistic graphical model and a deep neural network in semantic segmentation, the local region condition random field (LRCRF) model is investigated which selectively applies the condition random field (CRF) to the most active region in the image. The full convolutional network structure is optimized with the ResNet-18 structure and dilated convolution to expand the receptive field. The tracking networks are also improved based on SiameseFC by considering the frame relations in consecutive-frame traffic scene maps. Moreover, the segmentation results of the greyscale input data sets are more stable and effective than using the RGB images for deep neural network feature extraction. The experimental results show that the proposed method takes advantage of the image features directly and achieves good real-time performance and high segmentation accuracy.