The essential requirement for precise localization of a self-driving car is a lane-level map which includes road markings(RMs).Obviously,we can build the lane-level map by running a mobile mapping system(MMS)which is ...The essential requirement for precise localization of a self-driving car is a lane-level map which includes road markings(RMs).Obviously,we can build the lane-level map by running a mobile mapping system(MMS)which is equipped with a high-end 3D LiDAR and a number of high-cost sensors.This approach,however,is highly expensive and ineffective since a single high-end MMS must visit every place for mapping.In this paper,a lane-level RM mapping system using a monocular camera is developed.The developed system can be considered as an alternative to expensive high-end MMS.The developed RM map includes the information of road lanes(RLs)and symbolic road markings(SRMs).First,to build a lane-level RM map,the RMs are segmented at pixel level through the deep learning network.The network is named RMNet.The segmented RMs are then gathered to build a lane-level RM map.Second,the lane-level map is improved through loop-closure detection and graph optimization.To train the RMNet and build a lane-level RM map,a new dataset named SeRM set is developed.The set is a large dataset for lane-level RM mapping and it includes a total of 25157 pixel-wise annotated images and 21000 position labeled images.Finally,the proposed lane-level map building method is applied to SeRM set and its validity is demonstrated through experimentation.展开更多
Objective To confirm previous effort to identify type 2 diabetes susceptibility genes in a Northern Chinese population by conducting a new genome scan with both an increased number of type 2 diabetes families and a n...Objective To confirm previous effort to identify type 2 diabetes susceptibility genes in a Northern Chinese population by conducting a new genome scan with both an increased number of type 2 diabetes families and a new set of microsatellite markers within the previously localized regions.Methods A genome scan method was applied. After multiplexed PCR, electrophoreses, genescan and genotyping analysis, we obtained size information for all loci , and then a further study was done by both parametric and non-parametric linkage analysis to investigate the P values and Z values of these loci.Results We surveyed 34 microsatellite markers which distributed within 5 regions along chromosome 1, and a total of 12?000 genotypes were screened. Evidence of linkage with diabetes was identified for 8 of the 34 loci. All P values of the 8 loci were lower than 0.05, and the highest Z value was 2.17. A very interesting finding is that all 5 markers at the p- terminal 1p36.3-1p36.23 region, spanning a long range of 16.9?cM, were identified to have a low P value of less than 0.05, which suggests that this region may contain multiple susceptibility genes. Regions 4 and 5 also confirmed the previous findings, and we narrowed these two regions to a 2.7?cM and 2.5?cM regions, respectively.Conclusions We further confirmed the results gained in the previous genome-wide scan using an increased number of NIDDM families and a new set of microsatellite markers lying within the initially localized regions. The fact that all 5 loci at the p- terminal region displayed a low P value of less than 0.05 suggests that more than 1 susceptibility gene may reside in this region.展开更多
基金This work was supported by the Industry Core Technology Development Project,20005062Development of Artificial Intelligence Robot Autonomous Navigation Technology for Agile Movement in Crowded Space,funded by the Ministry of Trade,industry&Energy(MOTIE,Republic of Korea).
文摘The essential requirement for precise localization of a self-driving car is a lane-level map which includes road markings(RMs).Obviously,we can build the lane-level map by running a mobile mapping system(MMS)which is equipped with a high-end 3D LiDAR and a number of high-cost sensors.This approach,however,is highly expensive and ineffective since a single high-end MMS must visit every place for mapping.In this paper,a lane-level RM mapping system using a monocular camera is developed.The developed system can be considered as an alternative to expensive high-end MMS.The developed RM map includes the information of road lanes(RLs)and symbolic road markings(SRMs).First,to build a lane-level RM map,the RMs are segmented at pixel level through the deep learning network.The network is named RMNet.The segmented RMs are then gathered to build a lane-level RM map.Second,the lane-level map is improved through loop-closure detection and graph optimization.To train the RMNet and build a lane-level RM map,a new dataset named SeRM set is developed.The set is a large dataset for lane-level RM mapping and it includes a total of 25157 pixel-wise annotated images and 21000 position labeled images.Finally,the proposed lane-level map building method is applied to SeRM set and its validity is demonstrated through experimentation.
基金ThisworkwassupportedbytheNationalNaturalSciencesFoundationofChina (No .398962 0 0 ) theNationalHighTechnologyResearchandDevelopmentProgram (No .10 2 10 0 2 0 2 ) theNationalProgramforKeyBasicResearchProject (No .G19980 5 10 16)
文摘Objective To confirm previous effort to identify type 2 diabetes susceptibility genes in a Northern Chinese population by conducting a new genome scan with both an increased number of type 2 diabetes families and a new set of microsatellite markers within the previously localized regions.Methods A genome scan method was applied. After multiplexed PCR, electrophoreses, genescan and genotyping analysis, we obtained size information for all loci , and then a further study was done by both parametric and non-parametric linkage analysis to investigate the P values and Z values of these loci.Results We surveyed 34 microsatellite markers which distributed within 5 regions along chromosome 1, and a total of 12?000 genotypes were screened. Evidence of linkage with diabetes was identified for 8 of the 34 loci. All P values of the 8 loci were lower than 0.05, and the highest Z value was 2.17. A very interesting finding is that all 5 markers at the p- terminal 1p36.3-1p36.23 region, spanning a long range of 16.9?cM, were identified to have a low P value of less than 0.05, which suggests that this region may contain multiple susceptibility genes. Regions 4 and 5 also confirmed the previous findings, and we narrowed these two regions to a 2.7?cM and 2.5?cM regions, respectively.Conclusions We further confirmed the results gained in the previous genome-wide scan using an increased number of NIDDM families and a new set of microsatellite markers lying within the initially localized regions. The fact that all 5 loci at the p- terminal region displayed a low P value of less than 0.05 suggests that more than 1 susceptibility gene may reside in this region.
