Shuyun Niu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shuyun Niu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Fan Zhang
Research Institute of Highway, MOT
4 shared publications - Jian Gao
National ITS Research Center, Research Institute of Highway Ministry of Transport
4 shared publications - Xiaojing Wang
National ITS Research Center, Research Institute of Highway Ministry of Transport, 8 Xi Tucheng Rd., Haidian Dist., Beijing 100088, China
2 shared publications - Honghai Li
Research Institute of Highway Ministry of Transport, Beijing, China
1 shared publication Jian-Ping Liu
Research Institute of Highway Ministry of Transport
1 shared publicationJianping Liu
National ITS Research Center, Research Institute of Highway Ministry of Transport, 8 Xi Tucheng Rd., Haidian Dist., Beijing 100088, China
1 shared publication
Latest Publications
- Open Access
- 24 May 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (11) , 8505
A Traffic Parameter Extraction Model Using Small Vehicle Detection and Tracking in Low-Brightness Aerial Images
It is still a challenge to detect small-size vehicles from a drone perspective, particularly under low-brightness conditions. In this context, a YOLOX-IM-DeepSort model was proposed, which improved the object detection performance in low-brightness conditions accurately and efficiently. At the stage of object detection, this model incorporates the data enhancement algorithm as well as an ultra-lightweight subspace attention module, and optimizes the number of detection heads and the loss function. Then, the ablation experiment was conducted and the analysis results showed that the YOLOX-IM model has better mAP than the baseline model YOLOX-s for multi-scale object detection. At the stage of object tracking, the DeepSort object-tracking algorithm is connected to the YOLOX-IM model, which can extract vehicle classification data, vehicle trajectory, and vehicle speed. Then, the VisDrone2021 dataset was adopted to verify the object-detection and tracking performance of the proposed model, and comparison experiment results showed that the average vehicle detection accuracy is 85.00% and the average vehicle tracking accuracy is 71.30% at various brightness levels, both of which are better than those of CenterNet, YOLOv3, FasterR-CNN, and CascadeR-CNN. Next, a field experiment using an in-vehicle global navigation satellite system and a DJI Phantom 4 RTK drone was conducted in Tianjin, China, and 12 control experimental scenarios with different drone flight heights and vehicle speeds were designed to analyze the effect of drone flight altitude on speed extraction accuracy. Finally, the conclusions and discussions were presented.
- 24 May 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (11) , 8505
Open AccessA Traffic Parameter Extraction Model Using Small Vehicle Detection and Tracking in Low-Brightness Aerial Images
It is still a challenge to detect small-size vehicles from a drone perspective, particularly under low-brightness conditions. In this context, a YOLOX-IM-DeepSort model was proposed, which improved the object detection performance in low-brightness conditions accurately and efficiently. At the stage of object detection, this model incorporates the data enhancement algorithm as well as an ultra-lightweight subspace attention module, and optimizes the number of detection heads and the loss function. Then, the ablation experiment was conducted and the analysis results showed that the YOLOX-IM model has better mAP than the baseline model YOLOX-s for multi-scale object detection. At the stage of object tracking, the DeepSort object-tracking algorithm is connected to the YOLOX-IM model, which can extract vehicle classification data, vehicle trajectory, and vehicle speed. Then, the VisDrone2021 dataset was adopted to verify the object-detection and tracking performance of the proposed model, and comparison experiment results showed that the average vehicle detection accuracy is 85.00% and the average vehicle tracking accuracy is 71.30% at various brightness levels, both of which are better than those of CenterNet, YOLOv3, FasterR-CNN, and CascadeR-CNN. Next, a field experiment using an in-vehicle global navigation satellite system and a DJI Phantom 4 RTK drone was conducted in Tianjin, China, and 12 control experimental scenarios with different drone flight heights and vehicle speeds were designed to analyze the effect of drone flight altitude on speed extraction accuracy. Finally, the conclusions and discussions were presented.
- 18 January 2018
- Published by American Society of Civil Engineers (ASCE)
- p. 2712-2724
A Study on Highway Corridor Traffic State Identification Based on Data Fusion of DSRC Data and ETC Data
Traffic state identification is an important part in real-time traffic management and intelligent transportation systems (ITS) applications, which is conventionally based on the available single dataset from traffic sensors such as loop detector, microwave detector, video camera, Bluetooth detector, etc. An accurate profile of the traffic state on highway corridor in terms of speed and density is expected to be a critical factor for supporting traffic management measures. Data fusion techniques are nowadays applied to ITS to improve efficiency and safety of highways. As more and more ETC and DSRC data can be obtained, a method of analyzing traffic status with the datasets gained from ETC via DSRC is expected. In this paper, the DSRC was firstly large scaled installed and applied as a traffic detector along Jingcheng Highway, and the data from DSRC based detector and tolling data were used to identify the traffic state along this corridor. A data fusion method was developed in order to consider both space and time effects was proposed. The results indicated that the DSRC detector could be a promising way to collect traffic data and represent the traffic state on the network with ETC data.
- 18 January 2018
- Published by American Society of Civil Engineers (ASCE)
- p. 2712-2724
A Study on Highway Corridor Traffic State Identification Based on Data Fusion of DSRC Data and ETC Data
Traffic state identification is an important part in real-time traffic management and intelligent transportation systems (ITS) applications, which is conventionally based on the available single dataset from traffic sensors such as loop detector, microwave detector, video camera, Bluetooth detector, etc. An accurate profile of the traffic state on highway corridor in terms of speed and density is expected to be a critical factor for supporting traffic management measures. Data fusion techniques are nowadays applied to ITS to improve efficiency and safety of highways. As more and more ETC and DSRC data can be obtained, a method of analyzing traffic status with the datasets gained from ETC via DSRC is expected. In this paper, the DSRC was firstly large scaled installed and applied as a traffic detector along Jingcheng Highway, and the data from DSRC based detector and tolling data were used to identify the traffic state along this corridor. A data fusion method was developed in order to consider both space and time effects was proposed. The results indicated that the DSRC detector could be a promising way to collect traffic data and represent the traffic state on the network with ETC data.
- 29 June 2016
- Published by American Society of Civil Engineers (ASCE)
- p. 1204-1216
Evaluating the Operational Status of Freeway Networks Based on DSRC Data
In this paper, the feasibility of evaluating traffic operation status at freeway networks by utilizing dedicated short range communications (DSRC) data is discussed. The method of data processing as well as the data analysis algorithm are proposed. The data analysis and processing method is done based on the DSRC data and the toll dataset of an operational freeway network from 1st to 15th of July 2015. This includes some fundamental pieces of information, such as the penetration rate of electronic toll collection (ETC) vehicle, the ETC vehicle flow analysis, the proportion of missing data, the speed calculation, and the freeway corridor traffic operation index. The analysis shows that it is feasible to evaluate the traffic operation status of freeway networks by DSRC data when the ETC penetration is big enough, and that the outputs of DSRC data can be used for real-time traffic information service.
- 29 June 2016
- Published by American Society of Civil Engineers (ASCE)
- p. 1204-1216
Evaluating the Operational Status of Freeway Networks Based on DSRC Data
In this paper, the feasibility of evaluating traffic operation status at freeway networks by utilizing dedicated short range communications (DSRC) data is discussed. The method of data processing as well as the data analysis algorithm are proposed. The data analysis and processing method is done based on the DSRC data and the toll dataset of an operational freeway network from 1st to 15th of July 2015. This includes some fundamental pieces of information, such as the penetration rate of electronic toll collection (ETC) vehicle, the ETC vehicle flow analysis, the proportion of missing data, the speed calculation, and the freeway corridor traffic operation index. The analysis shows that it is feasible to evaluate the traffic operation status of freeway networks by DSRC data when the ETC penetration is big enough, and that the outputs of DSRC data can be used for real-time traffic information service.
- 13 July 2015
- Published by American Society of Civil Engineers (ASCE)
- p. 2204-2212
Highway Network Critical Segments Identifying Method with Network Dynamic Traffic Characteristics: A Simulation Based Study
The methods on identifying the highway network critical segments associate with the physical structure have been extensively studied in the last decade. Most of them are based on graph theory and network theory and few of them have considered the dynamic traffic characteristics of the network. These method based on static critical segments may not be sufficient under the real traffic condition. It is meaningful to study the network key segments identifying method with dynamic traffic flows. In this paper, a flow based method will be proposed to identify the critical segments, then the results from the simulation study will be compared with the results from the static network characteristics analysis. After that, we will searching the relations of the critical segments from the static network and the dynamic network. Finally, a verification of the new method was conducted with Anhui highway network simulation.
- 13 July 2015
- Published by American Society of Civil Engineers (ASCE)
- p. 2204-2212
Highway Network Critical Segments Identifying Method with Network Dynamic Traffic Characteristics: A Simulation Based Study
The methods on identifying the highway network critical segments associate with the physical structure have been extensively studied in the last decade. Most of them are based on graph theory and network theory and few of them have considered the dynamic traffic characteristics of the network. These method based on static critical segments may not be sufficient under the real traffic condition. It is meaningful to study the network key segments identifying method with dynamic traffic flows. In this paper, a flow based method will be proposed to identify the critical segments, then the results from the simulation study will be compared with the results from the static network characteristics analysis. After that, we will searching the relations of the critical segments from the static network and the dynamic network. Finally, a verification of the new method was conducted with Anhui highway network simulation.
- Open Access
A Space-Time Network-Based Modeling Framework for Dynamic Unmanned Aerial Vehicle Routing in Traffic Incident Monitoring Applications
It is essential for transportation management centers to equip and manage a network of fixed and mobile sensors in order to quickly detect traffic incidents and further monitor the related impact areas, especially for high-impact accidents with dramatic traffic congestion propagation. As emerging small Unmanned Aerial Vehicles (UAVs) start to have a more flexible regulation environment, it is critically important to fully explore the potential for of using UAVs for monitoring recurring and non-recurring traffic conditions and special events on transportation networks. This paper presents a space-time network- based modeling framework for integrated fixed and mobile sensor networks, in order to provide a rapid and systematic road traffic monitoring mechanism. By constructing a discretized space-time network to characterize not only the speed for UAVs but also the time-sensitive impact areas of traffic congestion, we formulate the problem as a linear integer programming model to minimize the detection delay cost and operational cost, subject to feasible flying route constraints. A Lagrangian relaxation solution framework is developed to decompose the original complex problem into a series of computationally efficient time-dependent and least cost path finding sub-problems. Several examples are used to demonstrate the results of proposed models in UAVs’ route planning for small and medium-scale networks.
Open AccessA Space-Time Network-Based Modeling Framework for Dynamic Unmanned Aerial Vehicle Routing in Traffic Incident Monitoring Applications
It is essential for transportation management centers to equip and manage a network of fixed and mobile sensors in order to quickly detect traffic incidents and further monitor the related impact areas, especially for high-impact accidents with dramatic traffic congestion propagation. As emerging small Unmanned Aerial Vehicles (UAVs) start to have a more flexible regulation environment, it is critically important to fully explore the potential for of using UAVs for monitoring recurring and non-recurring traffic conditions and special events on transportation networks. This paper presents a space-time network- based modeling framework for integrated fixed and mobile sensor networks, in order to provide a rapid and systematic road traffic monitoring mechanism. By constructing a discretized space-time network to characterize not only the speed for UAVs but also the time-sensitive impact areas of traffic congestion, we formulate the problem as a linear integer programming model to minimize the detection delay cost and operational cost, subject to feasible flying route constraints. A Lagrangian relaxation solution framework is developed to decompose the original complex problem into a series of computationally efficient time-dependent and least cost path finding sub-problems. Several examples are used to demonstrate the results of proposed models in UAVs’ route planning for small and medium-scale networks.
- 24 June 2014
- Published by American Society of Civil Engineers (ASCE)
- p. 2096-2106
Structural Characteristics Comparisons between the Provincial Expressway Network and the Trunk Highway Network in China
Using the Network Theory, comparisons were made with node degree distributions, betweennesses, shortest path lengths, and clustering coefficients of the provincial Expressway network and Trunk Highway network consisting partly of the Expressway System and the National Highway System in the same province. Based on structural characteristics of networks, this paper focused on comparing vulnerabilities between the provincial Expressway and Trunk Highway network. In addition, destructive experiments focusing on edge betweenness were conducted, while reactions and reliabilities from the Expressway Network and Trunk Highway Network were observed. Results showed that when 15% of all segments were damaged or blocked, the general efficiency of the Expressway System reduced to half of normal, which meant the whole system almost stopped running. On the other hand, this situation would occur when 25% of segments were damaged or blocked in the Trunk Highway Network, and this indicated the Trunk Highway Network had higher reliability than the Expressway System.
- 24 June 2014
- Published by American Society of Civil Engineers (ASCE)
- p. 2096-2106
Structural Characteristics Comparisons between the Provincial Expressway Network and the Trunk Highway Network in China
Using the Network Theory, comparisons were made with node degree distributions, betweennesses, shortest path lengths, and clustering coefficients of the provincial Expressway network and Trunk Highway network consisting partly of the Expressway System and the National Highway System in the same province. Based on structural characteristics of networks, this paper focused on comparing vulnerabilities between the provincial Expressway and Trunk Highway network. In addition, destructive experiments focusing on edge betweenness were conducted, while reactions and reliabilities from the Expressway Network and Trunk Highway Network were observed. Results showed that when 15% of all segments were damaged or blocked, the general efficiency of the Expressway System reduced to half of normal, which meant the whole system almost stopped running. On the other hand, this situation would occur when 25% of segments were damaged or blocked in the Trunk Highway Network, and this indicated the Trunk Highway Network had higher reliability than the Expressway System.
- 24 June 2014
- Published by American Society of Civil Engineers (ASCE)
- p. 1819-1829
A Study on the Highway Network Key Segments Identifying Method Based on the Structural Characteristics
Within the physical structure of the highway network, the key segments are significant for both the resistance against emergency and operational efficiency. Based on the Graph Theory and Network Theory, this paper proposes a new method for identifying key nodes in highway networks. First, a benefit function was estimated for each node with weights of GDP, mileage, and capacity. A benefit indicator was calculated, which represented the partial importance of each node. Second, weighted betweenness was estimated for describing the general importance throughout the whole network. After that, the overall importance for each node was calculated by finding weighted averages for both partial and general importance. Finally, a verification of the new method was conducted with a highway network among five eastern provinces and cities in China. The results indicated that the overall importance estimated by this method matched with the reality.
- 24 June 2014
- Published by American Society of Civil Engineers (ASCE)
- p. 1819-1829
A Study on the Highway Network Key Segments Identifying Method Based on the Structural Characteristics
Within the physical structure of the highway network, the key segments are significant for both the resistance against emergency and operational efficiency. Based on the Graph Theory and Network Theory, this paper proposes a new method for identifying key nodes in highway networks. First, a benefit function was estimated for each node with weights of GDP, mileage, and capacity. A benefit indicator was calculated, which represented the partial importance of each node. Second, weighted betweenness was estimated for describing the general importance throughout the whole network. After that, the overall importance for each node was calculated by finding weighted averages for both partial and general importance. Finally, a verification of the new method was conducted with a highway network among five eastern provinces and cities in China. The results indicated that the overall importance estimated by this method matched with the reality.