To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transfo...To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transformation. Then, the colors of traffic lights are detected with color space transformation. Finally, self-associative memory is used to recognize the countdown characters of the traffic lights. Test results at 20 real intersections show that the ratio of correct stabling siding recognition reaches up to 90%;and the ratios of recognition of traffic lights and divided characters are 85% and 97%, respectively. The research proves that the method is efficient for the detection of stabling siding and is robust enough to recognize the characters from images with noise and broken edges.展开更多
To improve the traffic efficiency at signalized intersections, a compact passing algorithm is proposed based on a vehicular network. Its basic principle is that several waiting vehicles after the stop line of the cons...To improve the traffic efficiency at signalized intersections, a compact passing algorithm is proposed based on a vehicular network. Its basic principle is that several waiting vehicles after the stop line of the considered intersection should simultaneously start in green periods. Thus, more vehicles can pass the intersection in a green period. Then, the having passed vehicles should follow the planned trajectories to enlarge their longitudinal clearances. Phase timing is not considered in the compact passing algorithm, and therefore, the proposed compact passing algorithm can be combined with other algorithms on phase timing to further improve their performances. Several simulations were designed and performed to verify the performance of the proposed algorithm. The simulation results show that the proposed algorithm can increase the number of completed vehicles and decrease the travel time in the signalized intersections managed by fixed-time and vehicle actuated algorithms, which indicates that the proposed algorithm is effective for improving the traffic efficiency at common signalized intersections.展开更多
Long-term kinematic research of slow- moving debris slide is rare despite of the widespread global distribution of this kind. This paper presents a study of the kinematics and mechanism of the Jinpingzi debris slide l...Long-term kinematic research of slow- moving debris slide is rare despite of the widespread global distribution of this kind. This paper presents a study of the kinematics and mechanism of the Jinpingzi debris slide located on the Jinsha river bank in southwest China. This debris slide is known to have a volume of 27×106 ms in active state for at least one century. Field survey and geotechnical investigation were carried out to define the structure of the landslide. The physical and mechanical properties of the landslide materials were obtained by in-situ and laboratory tests. Additionally, surface and subsurface displacements, as well as groundwater level fluctuations, were monitored since 2005. Movement features, especially the response of the landslide movement to rainfall, were analysed. Relationships between resisting forces and driving forces were analysed by using the limit equilibrium method assuming rigid-plastic frictional slip. The results confirmed a viscous comoonent in the long-term continuous movement resulting in the quasioverconsolidated state of the slip zone with higher strength parameters than some other types of slowmoving landslides. Both surface and subsurface displacements showed an advancing pattern by the straight outwardly inclined (rather than gently or reversely inclined) slip zone, which resulted in low resistance to the entire sliding mass. The average surface displacement rate from 2005 to 2016 was estimated to be 0.19-0.87 mm/d. Basal sliding on the silty clay seam accounted for most of the deformation with different degrees of internal deformation in different parts. Rainfall was the predominant factor affecting the kinematics of Jinpingzi landslide while the role of groundwater level, though positive, was not significant. The response of the groundwater level to rainfall infiltration was not apparent. Unlike some shallow slow-moving earth flows or mudslides, whose behaviors are directly related to the phreatic groundwater level, the mechanism for Jinpingzi landslide kinematics is more likely related to the changing weight of the sliding mass and the downslope seepage pressure in the shallow soil mass resulting from rainfall events.展开更多
Intelligent vehicle needs the turn light information of front vehicles to make decisions in autonomous navigation. A recognition algorithm was designed to get information of turn light. Approximated center segmentatio...Intelligent vehicle needs the turn light information of front vehicles to make decisions in autonomous navigation. A recognition algorithm was designed to get information of turn light. Approximated center segmentation method was designed to divide the front vehicle image into two parts by using geometry information. The number of remained pixels of vehicle image which was filtered by the morphologic feaatres was got by adaptive threshold method, and it was applied to recognizing the lights flashing. The experimental results show that the algorithm can not only distinguish the two turn lights of vehicle but also recognize the information of them. The algorithm is quiet effective, robust and satisfactory in real-time performance.展开更多
We examine the traffic lights regime to enable the fastest overall approach to a city for a specific case. The case involves a traffic light where one continues on the main road, into which additional cars are enterin...We examine the traffic lights regime to enable the fastest overall approach to a city for a specific case. The case involves a traffic light where one continues on the main road, into which additional cars are entering at the light. At this intersection an alternative route begins, which is longer but into which no additional cars are entering. To keep the total number of vehicles constant, we subtract on the main road far from the intersection, the same number of cars as were added at the intersection. In addition to checking different densities we check also the influence of changes in the number of cars which were added. We calculate the Fourier transform of the average on each traffic light cycles of the velocity on the main road and bypass. We obtained different results for different cases. All the cases can be written as 1/fa .展开更多
基金The Cultivation Fund of the Key Scientific and Technical Innovation Project of Higher Education of Ministry of Education (No.705020)
文摘To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transformation. Then, the colors of traffic lights are detected with color space transformation. Finally, self-associative memory is used to recognize the countdown characters of the traffic lights. Test results at 20 real intersections show that the ratio of correct stabling siding recognition reaches up to 90%;and the ratios of recognition of traffic lights and divided characters are 85% and 97%, respectively. The research proves that the method is efficient for the detection of stabling siding and is robust enough to recognize the characters from images with noise and broken edges.
基金The National Natural Science Foundation of China(No.51575103,U1664258)the National Key Research and Development Program of China(No.2016YFB0100906,2016YFD0700905)+2 种基金Six Talent Peaks Project in Jiangsu Province(No.2014-JXQC-001)Fundamental Research Funds for the Central Universities(No.2242016K41056)the Southeast University Excellent Doctor Degree Thesis Training Fund(No.YBJJ1703)
文摘To improve the traffic efficiency at signalized intersections, a compact passing algorithm is proposed based on a vehicular network. Its basic principle is that several waiting vehicles after the stop line of the considered intersection should simultaneously start in green periods. Thus, more vehicles can pass the intersection in a green period. Then, the having passed vehicles should follow the planned trajectories to enlarge their longitudinal clearances. Phase timing is not considered in the compact passing algorithm, and therefore, the proposed compact passing algorithm can be combined with other algorithms on phase timing to further improve their performances. Several simulations were designed and performed to verify the performance of the proposed algorithm. The simulation results show that the proposed algorithm can increase the number of completed vehicles and decrease the travel time in the signalized intersections managed by fixed-time and vehicle actuated algorithms, which indicates that the proposed algorithm is effective for improving the traffic efficiency at common signalized intersections.
文摘Long-term kinematic research of slow- moving debris slide is rare despite of the widespread global distribution of this kind. This paper presents a study of the kinematics and mechanism of the Jinpingzi debris slide located on the Jinsha river bank in southwest China. This debris slide is known to have a volume of 27×106 ms in active state for at least one century. Field survey and geotechnical investigation were carried out to define the structure of the landslide. The physical and mechanical properties of the landslide materials were obtained by in-situ and laboratory tests. Additionally, surface and subsurface displacements, as well as groundwater level fluctuations, were monitored since 2005. Movement features, especially the response of the landslide movement to rainfall, were analysed. Relationships between resisting forces and driving forces were analysed by using the limit equilibrium method assuming rigid-plastic frictional slip. The results confirmed a viscous comoonent in the long-term continuous movement resulting in the quasioverconsolidated state of the slip zone with higher strength parameters than some other types of slowmoving landslides. Both surface and subsurface displacements showed an advancing pattern by the straight outwardly inclined (rather than gently or reversely inclined) slip zone, which resulted in low resistance to the entire sliding mass. The average surface displacement rate from 2005 to 2016 was estimated to be 0.19-0.87 mm/d. Basal sliding on the silty clay seam accounted for most of the deformation with different degrees of internal deformation in different parts. Rainfall was the predominant factor affecting the kinematics of Jinpingzi landslide while the role of groundwater level, though positive, was not significant. The response of the groundwater level to rainfall infiltration was not apparent. Unlike some shallow slow-moving earth flows or mudslides, whose behaviors are directly related to the phreatic groundwater level, the mechanism for Jinpingzi landslide kinematics is more likely related to the changing weight of the sliding mass and the downslope seepage pressure in the shallow soil mass resulting from rainfall events.
基金Projects(90820302,60805027)supported by the National Natural Science Foundation of ChinaProject(200805330005)supported by the PhD Programs Foundation of Ministry of Education of ChinaProject(20010FJ4030)supported by the Academician Foundation of Hunan Province,China
文摘Intelligent vehicle needs the turn light information of front vehicles to make decisions in autonomous navigation. A recognition algorithm was designed to get information of turn light. Approximated center segmentation method was designed to divide the front vehicle image into two parts by using geometry information. The number of remained pixels of vehicle image which was filtered by the morphologic feaatres was got by adaptive threshold method, and it was applied to recognizing the lights flashing. The experimental results show that the algorithm can not only distinguish the two turn lights of vehicle but also recognize the information of them. The algorithm is quiet effective, robust and satisfactory in real-time performance.
文摘We examine the traffic lights regime to enable the fastest overall approach to a city for a specific case. The case involves a traffic light where one continues on the main road, into which additional cars are entering at the light. At this intersection an alternative route begins, which is longer but into which no additional cars are entering. To keep the total number of vehicles constant, we subtract on the main road far from the intersection, the same number of cars as were added at the intersection. In addition to checking different densities we check also the influence of changes in the number of cars which were added. We calculate the Fourier transform of the average on each traffic light cycles of the velocity on the main road and bypass. We obtained different results for different cases. All the cases can be written as 1/fa .