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
With high-frequency,low power dissipation and high-efficiency characteristics,Gallium nitride(GaN)power devices are of significant benefit in designing high-speed motor drives,as they improve performance and reduce we...With high-frequency,low power dissipation and high-efficiency characteristics,Gallium nitride(GaN)power devices are of significant benefit in designing high-speed motor drives,as they improve performance and reduce weight.However,due to the cascode structure,coupling with the parasitics in gate driver and power circuits,power converters based on cascode GaN are prone to overshoot and oscillate on switching waveforms,which may lead to serious EMC problems,or even device breakdown.The complicated structure of cascode GaN device makes the gate driver design comparatively complex.An analytical model of the switching process considering gate driver parameters is proposed in this article.The influence of gate driver parameters on switching behavior is investigated from the perspective of switching speed,waveform overshoot,and power loss.Trade-offs among overshoot,switching speed,and power loss are discussed;guidelines to design gate driver parameters are given.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 in part by the National Natural Science Foundation of China(51707161).
文摘With high-frequency,low power dissipation and high-efficiency characteristics,Gallium nitride(GaN)power devices are of significant benefit in designing high-speed motor drives,as they improve performance and reduce weight.However,due to the cascode structure,coupling with the parasitics in gate driver and power circuits,power converters based on cascode GaN are prone to overshoot and oscillate on switching waveforms,which may lead to serious EMC problems,or even device breakdown.The complicated structure of cascode GaN device makes the gate driver design comparatively complex.An analytical model of the switching process considering gate driver parameters is proposed in this article.The influence of gate driver parameters on switching behavior is investigated from the perspective of switching speed,waveform overshoot,and power loss.Trade-offs among overshoot,switching speed,and power loss are discussed;guidelines to design gate driver parameters are given.
