Pedestrian detection is a critical challenge in the field of general object detection,the performance of object detection has advanced with the development of deep learning.However,considerable improvement is still re...Pedestrian detection is a critical challenge in the field of general object detection,the performance of object detection has advanced with the development of deep learning.However,considerable improvement is still required for pedestrian detection,considering the differences in pedestrian wears,action,and posture.In the driver assistance system,it is necessary to further improve the intelligent pedestrian detection ability.We present a method based on the combination of SSD and GAN to improve the performance of pedestrian detection.Firstly,we assess the impact of different kinds of methods which can detect pedestrians based on SSD and optimize the detection for pedestrian characteristics.Secondly,we propose a novel network architecture,namely data synthesis PS-GAN to generate diverse pedestrian data for verifying the effectiveness of massive training data to SSD detector.Experimental results show that the proposed manners can improve the performance of pedestrian detection to some extent.At last,we use the pedestrian detector to simulate a specific application of motor vehicle assisted driving which would make the detector focus on specific pedestrians according to the velocity of the vehicle.The results establish the validity of the approach.展开更多
As a promising imaging technology,the low sensitivity of fluorine-19 magnetic resonance imaging(^(19)F MRI)severely hinders its biomedical applications.Herein,we have developed an unprecedented rotaxanebased strategy ...As a promising imaging technology,the low sensitivity of fluorine-19 magnetic resonance imaging(^(19)F MRI)severely hinders its biomedical applications.Herein,we have developed an unprecedented rotaxanebased strategy to improve the sensitivity of^(19)F MRI agents.By threading the fluorinated macrocycle into2-blade pinwheel[2]rotaxanes,the^(19)F longitudinal relaxation rate R1was dramatically increased,resulting in a significant^(19)F MRI signal intensity enhancement of up to 79%.Through comparative molecular dynamics studies using a series of solution and solid-state^(1)H/^(19)F nuclear magnetic resonance(^(1)H/^(19)F NMR)and molecular dynamics simulations,it was found that the formation of mechanical bonds dramatically restricts the motion of the wheel fluorines and thus increasing the R1for higher^(19)F MRI sensitivity.Besides a novel strategy for improving^(19)F MRI sensitivity,this study has established^(19)F NMR/MRI as a valuable technology for monitoring the molecular dynamics of rotaxanes,which may shed new light on high-performance^(19)F MRI agents and molecular devices.展开更多
文摘Pedestrian detection is a critical challenge in the field of general object detection,the performance of object detection has advanced with the development of deep learning.However,considerable improvement is still required for pedestrian detection,considering the differences in pedestrian wears,action,and posture.In the driver assistance system,it is necessary to further improve the intelligent pedestrian detection ability.We present a method based on the combination of SSD and GAN to improve the performance of pedestrian detection.Firstly,we assess the impact of different kinds of methods which can detect pedestrians based on SSD and optimize the detection for pedestrian characteristics.Secondly,we propose a novel network architecture,namely data synthesis PS-GAN to generate diverse pedestrian data for verifying the effectiveness of massive training data to SSD detector.Experimental results show that the proposed manners can improve the performance of pedestrian detection to some extent.At last,we use the pedestrian detector to simulate a specific application of motor vehicle assisted driving which would make the detector focus on specific pedestrians according to the velocity of the vehicle.The results establish the validity of the approach.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDB0540000)the National Key R&D Program of China(No.2018YFA0704000)+2 种基金the National Natural Science Foundation of China(Nos.22327901,22077098,U21A20392,21921004,and 82127802)the Knowledge Innovation Program of WuhanBasic Research(No.2022020801010137)support from the Youth Innovation Promotion Association and the Young Top-notch Talent Cultivation Program。
文摘As a promising imaging technology,the low sensitivity of fluorine-19 magnetic resonance imaging(^(19)F MRI)severely hinders its biomedical applications.Herein,we have developed an unprecedented rotaxanebased strategy to improve the sensitivity of^(19)F MRI agents.By threading the fluorinated macrocycle into2-blade pinwheel[2]rotaxanes,the^(19)F longitudinal relaxation rate R1was dramatically increased,resulting in a significant^(19)F MRI signal intensity enhancement of up to 79%.Through comparative molecular dynamics studies using a series of solution and solid-state^(1)H/^(19)F nuclear magnetic resonance(^(1)H/^(19)F NMR)and molecular dynamics simulations,it was found that the formation of mechanical bonds dramatically restricts the motion of the wheel fluorines and thus increasing the R1for higher^(19)F MRI sensitivity.Besides a novel strategy for improving^(19)F MRI sensitivity,this study has established^(19)F NMR/MRI as a valuable technology for monitoring the molecular dynamics of rotaxanes,which may shed new light on high-performance^(19)F MRI agents and molecular devices.
