Advance Search
Display Method:
Intelligent Vehicles Localization Based on Semantic Map Representation from 3D Point Clouds
ZHU Yuntao, LI Fei, HU Zhaozheng, WU Huawei
Abstract(7328) PDF(6425)
Abstract:
In order to improve the accuracy of node localization for intelligent vehicles,an intelligent vehicles localization method based on three-dimensional point clouds semantic map representation is proposed. The method is divided into three parts. Semantic segmentation based on 3D laser point clouds includes ground segmentation,traffic signs segmentation and pole-shaped target segmentation. Semantic map representation for intelligent vehicles uses segmented targets to project. Finally directional projections with weight,semantic roads and semantic codeing are generated. The codeing and global location from high-precision GPS make up representation model. Localization based on semantic representation model includes coarse localization from GPS matching and node localization from semantic coding matching. The experiments are carried out in three road scenes with different length and complexity,and the localization accuracy is 98.5%,97.6% and 97.8%,respectively. The results show that proposed method has high accuracy and strong robustness, which is suitable for different road scenes.
Companion Relationship Discovering Algorithm for Passengers in the Cruise Based on UWB Positioning
YAN Sixun, WU Bing, SHANG Lei, LYU Jieyin, WANG Yang
Abstract(6684) PDF(2889)
Abstract:
To accurately discover the companion relationship among passengers in the interior space of a cruise, UWB positioning is employed in the cruise to carry out on-board personnel location experiment. An improved Haussdorff-DBSCAN based scheme combined with indoor positional semantics is proposed to realize the trajectory clustering of the passenger trajectories, considering the characteristics of the UWB location data. Afterwards, the LSTM neural network is applied to predict the changing similarity of the suspected companions. Traditional Hausdorff algorithm does not consider the consistency of trajectory timing while calculating the trajectory similarity, and the introduction of positional semantic sequence can solve this problem well. In the first phase, the passenger trajectory data set is input to the improved Hausdorff-DBSCAN algorithm, and the clustering radius is determined according to the overall similarity threshold of trajectories. The outputs are the emerging clusters of passenger trajectories in the same companion group. In the second phase, the LSTM neural network takes the point similarity sequence with a fixed time window as the input to predict the point similarity value at the next time. The sequential change of passengers companion relationship is analyzed by the similarity threshold and prediction results. The validity of the presented algorithm is demonstrated by the trajectory data obtained from the passengers simulation on one deck of the cruise under study, which is modeled in Anylogic. The results indicate that the precision of the proposed algorithm reaches 0.92, the recall value reaches 0.95 and the F1 value is 0.934, which are at least 5.7 percent, 8.0 percent and 6.7 percent higher than the comparing algorithm. The LSTM neural network also shows a promising effect in predicting the changing trend of the similarity, for the loss is at a stable level of 3 to 4 percent.
Data Association Method Based on Descriptor Assisted Optical flow Tracking Matching
XIA Huajia, ZHANG Hongping, CHEN Dezhong, LI Tuan
Abstract(3668) PDF(1182)
Abstract:
in the view of the problem that the positioning accuracy of visual inertial odometer using multi-state constrained Kalman filter(MSCKF) is easily affected by the abnormal value of feature point matching, a data association method based on descriptor assisted optical flow tracking matching is proposed. This method uses pyramid LK optical flow to track and match the feature points in the sequence image, then calculates the rbrief descriptor of each pair of matching points, judges the similarity of the descriptor according to the Hamming distance,and eliminates the abnormal matching points. In the experiment, the effectiveness of the proposed method is evaluated from two aspects:the subjective effect of feature point matching and positioning accuracy. The results show that the proposed method can effectively filter the abnormal values of image feature matching in dynamic scene. The image processed by this method is used for msckf motion solution,and the drift rate of position result is less than 0.38%, compared with the result of msckf algorithm without eliminating abnormal matching values,The improvement is 54.7%, and the single frame image processing time is about 39 ms.
Indoor Sign-based Visual Localization Method
HUANG Gang, CAI Hao, DENG Chao, HE Zhi, XU Ningbo
Abstract(8192) PDF(1459)
Abstract:
To solve the problem of localization calculation of intelligent vehicles and the mobile robot in the indoor traffic environment, by exploiting kinds of signs which existed in the indoor environment, a visual localization method is proposed through using BEBLID (Boosted Efficient Binary Local Image Descriptor) algorithm. The proposed method enforces the ability to characterize the whole image by improving the classic BEBLID. In this paper, the localization method consists of an offline stage and an online stage. In the offline stage, a scene sign map is created. In the online stage, the calculation progress is divided into 3 parts, which include holistic and local BEBLID method from current image and image in the scene sign map, closet sign site and closet image calculation by using KNN method, metric calculation by using coordinate information which is stored in the scene sign map. The experiment is conducted in three kinds of indoor scenes, including a teaching building, an office building, and an indoor parking lot. The experiment shows the scene sign recognition rate reached 90%, and the average localization error is less than 1 meter. Compared with the traditional method, the proposed method improves about 10% relative recognition rate with the same test set, which verified the effectiveness of the proposed method.
A Cooperative Map Matching Algorithm Applied in Intelligent and Connected Vehicle Positioning
CHEN Wei, DU Luyao, KONG Haiyang, FU Shuaizhi, ZHENG Hongjiang
Abstract(8392) PDF(1276)
Abstract:
In order to achieve low-cost and high-precision vehicle positioning in the intelligent and connected environment,a cooperative map matching algorithm based on adaptive genetic Rao-Blackwellized particle filter is studied in this paper,improving the accuracy of vehicle positioning by using the real-time location data and road constraints of other connected vehicles. The adaptive genetic algorithm is introduced into the re-sampling process of the particle filter to increase the diversity of particles,so as to solve the problems of "particle degradation" and "particle exhaustion" that are prone to appear in traditional particle filter algorithms. Model of the algorithm is established and simulated. The positioning results under the traditional particle filter and Kalman smooth particle filter are compared,and the influence of the number of different connected vehicles on the positioning accuracy is analyzed. The experiment is completed in real-world and the performance of the algorithm is verified. The experimental results show that taking a typical intersection with four connected vehicles as an example,the range of position error of cooperative map matching is 1.67 m. It is only 41.03% and 56.80% of the traditional GNSS and the single map matching positioning results. At the same time,the circular error probable(CEP) of this algorithm is 1.06 m, which is 2.52 m higher than raw GNSS positioning result.
MORE>
Display Method:
2024, 42(3): .  
Abstract(0) HTML(0) PDF(0)
Abstract:
A Risk Assessment Method of Multi-aircraft Interaction for Complex Airspace
AI Yi, WAN Qifeng, HAN Xun, LI Yueyang, YU Yingxue, CONG Wei
2024, 42(3): 1-10.   doi: 10.3963/j.jssn.1674-4861.2024.03.001
Abstract(0) HTML(0) PDF(0)
Abstract:
To assess the interaction risks among multiple aircraft in complex traffic scenarios, a concept of "interac-tion potential fields of multiple aircraft and airspace environment" is developed, which is based on the similarity be-tween traffic risk and potential field theory. The interaction potential fields (IPF) generated by aircraft, critical air-space points (CAPs) and air routes (ARs) are defined, respectively, and the generation functions of IPFs are formu-lated. Considering the short-term effects of historical trajectories on the aircraft, a time-varying historical trajectory IPF is added to the real-time aircraft IPFs; considering the requirement of safety intervals in horizontal and vertical dimensions for aircraft, the parameters of rule-compliant IPFs are found; then, a fusion method is developed to integrate IPFs generated by aircraft, CAPs and ARs. Inspired by the relationship between potential field force and poten-tial energy, a potential energy-based risk index is introduced, denoted as RPE, showing the changes of risk over time in multi-aircraft scenarios from the perspective of energy. To validate the effectiveness of the proposed method, a simulation based on a real airspace section is introduced, and the results show that: ① RPE is much closer to the precepted risk by the air traffic operators (RSE) compared with traditional risk indicators; ② RPE is more sensitive at certain intervals than the conflict time-based index RATSR, with a mean absolute error of 0.077. In brief, the pro-posed risk assessment method could offer more precise decision support for risk management in complex air traffic scenarios in the future.
An Analysis of Safety Influencing Factors for Longitudinal Interaction Between Vehicles in Human-machine Mixed Traffic Driving Conditions
WANG Yiyun, YU Rongjie
2024, 42(3): 11-19.   doi: 10.3963/j.jssn.1674-4861.2024.03.002
Abstract(0) HTML(0) PDF(0)
Abstract:
Autonomous vehicles are gradually introduced to the existing traffic environment, leading to a mixed flow of both autonomous vehicles and human-driven vehicles. Studies show that the crash rate per-kilometer for autonomous vehicles is 9.1, which is more than twice that of human-driven vehicles (4.1). The ratio of the rear-end crash pattern between autonomous vehicles and human-driven vehicles is 57.5%, which exceeds 27.9% of among human-driven vehicles. Therefore, there is an urgent need to investigate the safety mechanisms of longitudinal interactions of autonomous vehicles and human-driven vehicles. Existing studies typically employ driving simulation experiments to analyze the longitudinal interaction and safety between human-driven and autonomous vehicles in virtual environments. However, the differences between simulated environments and real-world road scenarios make it challenging to accurately capture the interaction behavior between vehicles in mixed human-autonomous traffic flows. In this study, public road-testing dataset of autonomous vehicles are utilized to extract longitudinal interacting scenarios, and the influencing factors and the impact mechanisms of longitudinal interaction behavior and safety are investigated. Specifically, scenarios of human-driven vehicles following the other human-driven vehicle, and following an autonomous vehicle are studied, Structural equation model is applied to construct a chained relationship among driving behavior of leading vehicle, type of leading vehicle (whether it is an autonomous vehicle or not), speed level of vehicles on the roadway, and the safety surrogate measure. The modelling results revealed the type of leading vehicle is identified as an influencing factor in longitudinal interaction safety. When other variables remain constant, the safety of interactions between human drivers and autonomous vehicles as leading vehicles decreased compared to interactions with other human-driven vehicles as leading vehicles.
An Analysis and Adjustment of the Abrupt Change of Vehicle Trajectories in the Entrance area of Freeway Tunnels
YU Liang, BEI Runzhao, DU Zhigang, ZHANG Xing, YANG Yongzheng
2024, 42(3): 20-30.   doi: 10.3963/j.jssn.1674-4861.2024.03.003
Abstract(0) HTML(0) PDF(0)
Abstract:
Vehicle trajectories would undergo abrupt changes at the entrance area of freeway tunnels. To analyze the reasons behind this phenomenon and quantitatively evaluate the regulating effect of different visual guiding schemes, four simulation scenarios are developed. Scenario 1, based on the guidelines outlined in Specifications for Design of Highway Tunnels Section 2 Traffic Engineering and Affiliated Facilities (JTG D70/2—2014), serves as the control group, while other scenarios incorporate visual guiding schemes on the basis of Scenario 1. Specifically, Scenario 2 introduces a low-position scheme consisting of flexible posts and crash cushions, Scenario 3 introduces a high-position scheme comprising retroreflective arches and warning alignment signs, and Scenario 4 combines both the low and high schemes. Through a simulated driving platform, data such as driving distance, steering wheel angle, and lateral offset are obtained, and an evaluation index system is established considering the occurrence, evolution, and fading of the abrupt change trajectories. The study results indicate that changes of the visual reference system can prompt abrupt changes of driving trajectories, but a continuous and consistent visual guiding scheme can regulate this phenomenon. Specifically, compared to the control group, the low-position scheme significantly reduced the average steering wheel angle before the tunnel entrance (SWAav) by 82%, helping drivers avoid abrupt maneuvers. High-position scheme increased the gradient coefficient (G) by 3.7 times, reduced the expected lateral deviation during the transient stability phase (O1) by 31%, and decreased the difference between O1 and the expected lateral deviation during the stable phase (O1-O2) by 75%. This improved the gradual change in trajectory, reduced avoidance of the tunnel portal and wall, and enhanced adaptation to the tunnel environment. The combined guiding scheme, which integrates both low and high-position scheme, yielded the best results: it increased G by 4.4 times, reduced SWAav by 83%, decreased O1 by 41%, and minimized O1-O2 by 98%. This scheme effectively improved the gradual nature of trajectory changes, reduced avoidance of the tunnel entrance and walls, and enhanced environmental adaptation. Consequently, it is recommended to implement the combined scheme in the entrance areas of highway tunnels, with the exception of special cases where only the high scheme should be applied.
Characteristics of Driving Behavior and Performance Caused by Plateau Environment of Young and Middle-aged Drivers
GUO Weiwei, HU Yuqin, TAN Jiyuan, XUE Qingwan
2024, 42(3): 31-41.   doi: 10.3963/j.jssn.1674-4861.2024.03.004
Abstract(0) HTML(0) PDF(0)
Abstract:
To analyze effects of a hypoxic environment on driving performance, a driving simulator experiment is conducted in this study. Both drivers' behavioral data and physiological data are collected by simulating a plateau scenario (3 900 m). The driver behavior characteristics in the plateau scenario and plain scenario are analyzed using a radar map, a numerical ranking map, and one-way ANOVA. The probability density fitting distribution differences between the two scenarios for road offset, steering velocity, lateral acceleration, and speed are quantified using the Jensen-Shannon divergence. The difference method is employed to identify time windows when driving performance decreased in the plateau area. The validity of the simulated hypoxic driving environment is verified by comparing the heart rate trend of the pilot test data in the plateau. The results indicated that: ① the standard deviation of road offset, lateral acceleration, steering velocity, and speed in the plateau scenario increase by 0.094 3 m, 0.119 0 m/s2, 0.000 9 °/s, and 0.651 3 km/h, respectively, compared to the plain scenario; ② the fitted probability density distribution differences between the plateau and plain scenarios for road offset, lateral acceleration, steering velocity, and speed are 0.23, 0.11, 0.01, and 0.02, respectively (thus, it could be inferred that vehicle lateral movement is more affected by the high-altitude factor); ③ driving performance decrease significantly after 6 minutes upon entering the plateau area at 3 900 m altitude.
Multi-LiDAR Roadside Intelligent Perception Method Fusing High-Definition Map
HU Zhaozheng, CHEN Qili, MENG Jie, HU Huahua, ZHANG Jianan
2024, 42(3): 42-52.   doi: 10.3963/j.jssn.1674-4861.2024.03.005
Abstract(0) HTML(0) PDF(0)
Abstract:
In the research of vehicle-road collaborative roadside perception, challenges such as low detection efficiency, unstable target trajectories, and inaccurate tracking arise due to the sheer volume of point cloud data and the inevitable obstruction of targets. To tackle these issues, a method of intelligent roadside perception utilizing multi-LiDAR fused with High-Definition (HD) maps is proposed. The goal is to enhance the accuracy and reliability of perception outcomes by incorporating detailed map information. Leveraging the calibration results of multi-LiDAR, the extraction of the region of interest (ROI) within the three-dimensional point cloud is achieved through HD maps, effectively reducing the quantity of point clouds for processing and enhancing computational efficiency. Employing the polar-image Gaussian mixture model (P-GMM) for background modeling, moving targets are swiftly identified using polar-images to circumvent direct processing of extensive LiDAR point clouds, thereby boosting detection efficiency. By enforcing the alignment between vehicle heading and lane line direction, the lane orientation in the HD map is translated into a linear constraint of vehicle state within the Kalman filter framework, thereby enhancing the efficacy of vehicle detection and trajectory tracking. Experimental validation is conducted using simulated crossroads and real-world roads with double T-shaped intersections. Compared to other methods, the method proposed yielded a 55% reduction in data volume, a 12% increase in target detection accuracy, and a 56% decrease in processing time. The improvements in extreme error, mean error, and root mean square error are also achieved in target tracking. The experimental results show that the method proposed can fuse HD map information effectively, achieving rapid detection and tracking of road-moving targets in a wide range of road scenarios.
An Active Tracking Method for Small Ships in Open Water Based on Fixed/PTZ Camera System
YOU Ji'an, HU Zhaozheng, XIAO Hanbiao, MENG Jie
2024, 42(3): 53-61.   doi: 10.3963/j.jssn.1674-4861.2024.03.006
Abstract(0) HTML(0) PDF(0)
Abstract:
It is difficult to actively track and capture clear images of inland river ships with the current Closed Circuit Television (CCTV) system. To fill the gap, an active tracking method for small ships in open waters based on the fixed/pan-tilt-zoom (PTZ) camera system is proposed. A three-layer joint calibration model based on a virtual quadrilateral (VQ) is introduced to jointly calibrate the fixed camera and the PTZ camera, which matches the image coordinate with the pan and tilt angle of the PTZ camera one by one; The introduced VQ filters out the targets outside the quadrilateral, eliminating inference and improving the accuracy of detection. The mapping relationship between the image coordinates and the world coordinates can be obtained by using the Perspective-n-Point (PnP) algorithm and the vertices of the VQ; Fourthly, the world coordinates of the points in the VQ are transformed into the Pan-Tilt-Hight (PTH) coordinates via PTH model. Then, by calculating the coordinate of the ship (the centroid of the ship) in the VQ, the pan and tilt angle of the PTZ camera can be derived, achieving real-time active tracking and keeping the target at the center of the PTZ camera image. To validate the proposed method, two real scenes are introduced, namely Chunhui Lake in Xiaogan City and the Sino-French Bridge section of the Han River in Wuhan City, Hubei Province. The results indicate that, ① the F1 -Scores of the proposed method on the fixed camera are 96.82% and 97.62%, respectively; ② when the proposed method is applied to the PTZ camera for tracking the moving ships, the failure rate is 4.63%. In summary, the proposed active tracking method performs reasonably in practice with a high tracking rate of 18.55 fps.
A Layout Method of Guide Signs for Inner and Outer Lanes Integrated Composite Expressway
HU Xinchao, DAI Zhe, XI Kun
2024, 42(3): 62-73.   doi: 10.3963/j.jssn.1674-4861.2024.03.007
Abstract(0) HTML(0) PDF(0)
Abstract:
The integrated composite expressway has a special road structure and traffic organization mode, which requires the transmission of a large amount of information. In order to enhance the efficiency of guide signs, prevent information overload, and improve safety, research is conducted to optimize the layout of guide signs for this type of expressway. Using the Guangshen expressway as a case study, the research analyzes its characteristics of the inner and outer lanes to clarify layout principles for guide signs. It proposes information guidance methods based on the functions of inner and outer lanes and develops a grading method for guidance information. Through driving simulation technology, experiments are carried out to determine information threshold and layout design for guide signs. Drivers'target search time for different information quantities of guide signs is measured, as well as the lateral offset, speed, acceleration, and sign fixation time during interchange exits. In the information threshold experiment, robust estimation theory is applied to process the target information search time, concluding that the information threshold for guide signs on an integrated composite expressway is 8. In the layout design experiment, two sets of interchange exit guide signs are tested based on the proposed information guidance and grading methods. Both sets can correctly guide vehicles to their destinations. However, the guidance method based on the inner and outer functions proves more efficiency, leading to an earlier lane changes about 250 m, a 5.88% increase in driving speed, a 45.77% reduction in acceleration standard deviation, and a shortened sign fixation time. The research indicates that the proposed information guidance method effectively enhances sign visibility, guides traffic flow, and alleviates driver stress on integrated composite expressways. It is recommended to adopt the information guidance method based on the inner and outer functions for integrated composite expressways.
MORE>
Intelligent Vehicles Localization Based on Semantic Map Representation from 3D Point Clouds
ZHU Yuntao, LI Fei, HU Zhaozheng, WU Huawei
[Abstract](7328) [PDF 4082KB](364)
Abstract:
In order to improve the accuracy of node localization for intelligent vehicles,an intelligent vehicles localization method based on three-dimensional point clouds semantic map representation is proposed. The method is divided into three parts. Semantic segmentation based on 3D laser point clouds includes ground segmentation,traffic signs segmentation and pole-shaped target segmentation. Semantic map representation for intelligent vehicles uses segmented targets to project. Finally directional projections with weight,semantic roads and semantic codeing are generated. The codeing and global location from high-precision GPS make up representation model. Localization based on semantic representation model includes coarse localization from GPS matching and node localization from semantic coding matching. The experiments are carried out in three road scenes with different length and complexity,and the localization accuracy is 98.5%,97.6% and 97.8%,respectively. The results show that proposed method has high accuracy and strong robustness, which is suitable for different road scenes.
Companion Relationship Discovering Algorithm for Passengers in the Cruise Based on UWB Positioning
YAN Sixun, WU Bing, SHANG Lei, LYU Jieyin, WANG Yang
[Abstract](6684) [PDF 1759KB](274)
Abstract:
To accurately discover the companion relationship among passengers in the interior space of a cruise, UWB positioning is employed in the cruise to carry out on-board personnel location experiment. An improved Haussdorff-DBSCAN based scheme combined with indoor positional semantics is proposed to realize the trajectory clustering of the passenger trajectories, considering the characteristics of the UWB location data. Afterwards, the LSTM neural network is applied to predict the changing similarity of the suspected companions. Traditional Hausdorff algorithm does not consider the consistency of trajectory timing while calculating the trajectory similarity, and the introduction of positional semantic sequence can solve this problem well. In the first phase, the passenger trajectory data set is input to the improved Hausdorff-DBSCAN algorithm, and the clustering radius is determined according to the overall similarity threshold of trajectories. The outputs are the emerging clusters of passenger trajectories in the same companion group. In the second phase, the LSTM neural network takes the point similarity sequence with a fixed time window as the input to predict the point similarity value at the next time. The sequential change of passengers companion relationship is analyzed by the similarity threshold and prediction results. The validity of the presented algorithm is demonstrated by the trajectory data obtained from the passengers simulation on one deck of the cruise under study, which is modeled in Anylogic. The results indicate that the precision of the proposed algorithm reaches 0.92, the recall value reaches 0.95 and the F1 value is 0.934, which are at least 5.7 percent, 8.0 percent and 6.7 percent higher than the comparing algorithm. The LSTM neural network also shows a promising effect in predicting the changing trend of the similarity, for the loss is at a stable level of 3 to 4 percent.

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)