In order to reduce the number of surface mining accidents related to low visibility conditions and blind spots of trucks and to provide 3D information for truck drivers and real time monitored truck information for th...In order to reduce the number of surface mining accidents related to low visibility conditions and blind spots of trucks and to provide 3D information for truck drivers and real time monitored truck information for the remote dispatcher, a 3D assisted driving system (3D-ADS) based on the GPS, mesh-wireless networks and the Google-Earth engine as the graphic interface and mine-mapping server, was developed at Virginia Tech. The research results indicate that this 3D-ADS system has the potential to increase reliability and reduce uncertainty in open pit mining operations by customizing the local 3D digital mining map, con-structing 3D truck models, tracking vehicles in real time using a 3D interface and indicating available escape routes for driver safety.展开更多
The Assisted Driving System (ADS) for haul trucks operating in surface mining and construction sites is to reduce accidents related to low visibility conditions. This system is based on the GPS, Zigbee, and the Google...The Assisted Driving System (ADS) for haul trucks operating in surface mining and construction sites is to reduce accidents related to low visibility conditions. This system is based on the GPS, Zigbee, and the Google-Earth engine as the graphic interface and mine-mapping server. The system has the capability to pin-point and track vehicles in real time using a 3D interface, which is based on user-based AutoCAD mine maps using the Google-Earth graphics interface. All equipped vehicles are shown in a 3D mine map stored in a local server through a wireless network. When low visibility conditions are present, the system indicates available exit/escape routes for driver safety. The ADS potentially increases reliability and reduces uncertainty in open pit mining operations.展开更多
In our recent work we showed, by investigating the initialization of some unusual forms of assisted driving Hamiltonians, that the addition of an assisted driving Hamiltonian is not always useful in quantum adiabatic ...In our recent work we showed, by investigating the initialization of some unusual forms of assisted driving Hamiltonians, that the addition of an assisted driving Hamiltonian is not always useful in quantum adiabatic evolution. These unusual forms are those that are not the relatively fixed ones that are widely used in the literature. In this paper, we continue this study, providing further evidence for the validity of the conclusion above by researching some relatively more complex forms of assisted driving scheme, which generalize the ones studied in our previous work.展开更多
The multiple tasks involved in real-time driving are challenging tasks for any new learner of driving. The proposed Low Cost Driving Trainer Assistance System (DTAS) helps the amateur drivers to learn the basic skills...The multiple tasks involved in real-time driving are challenging tasks for any new learner of driving. The proposed Low Cost Driving Trainer Assistance System (DTAS) helps the amateur drivers to learn the basic skills involved while driving a vehicle, in particular a 4 wheeler like a car. The proposed system not only helps the novice drivers to gain confidence but also saves money spent on fuels while learning. The proposed DTAS system uses a steering wheel, an accelerator pedal, a brake pedal, gear mechanism and virtual (simulated) road environment. We also monitor and record the vital system parameters during the training period and analyze the same. The proposed DTAS involves operations like taking a turn, braking, accelerating, using dashboard functions and changing gears.展开更多
Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted vid...Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted videos can assist drivers in making decisions.However,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time detection.We proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary shapes.Our model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD model.The enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text regions.Additionally,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s performance.We further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection speed.This model holds potential for practical applications in real-world scenarios.展开更多
Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recogn...Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recognition System(TSRS)is one of themost important components ofADAS.Among the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing time.Accordingly,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed modules.Firstly,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured frames.Secondly,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise recognition.In addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting technique.Through rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,respectively.Furthermore,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.展开更多
基金Financial support for this work, provided by the Key Programs of the National Science and Technology Foundation during the 11th Five-Year Plan Period (No.2006BAK04B04) the State Scholarship Fund (No.2007104096), is gratefully acknowledged
文摘In order to reduce the number of surface mining accidents related to low visibility conditions and blind spots of trucks and to provide 3D information for truck drivers and real time monitored truck information for the remote dispatcher, a 3D assisted driving system (3D-ADS) based on the GPS, mesh-wireless networks and the Google-Earth engine as the graphic interface and mine-mapping server, was developed at Virginia Tech. The research results indicate that this 3D-ADS system has the potential to increase reliability and reduce uncertainty in open pit mining operations by customizing the local 3D digital mining map, con-structing 3D truck models, tracking vehicles in real time using a 3D interface and indicating available escape routes for driver safety.
文摘The Assisted Driving System (ADS) for haul trucks operating in surface mining and construction sites is to reduce accidents related to low visibility conditions. This system is based on the GPS, Zigbee, and the Google-Earth engine as the graphic interface and mine-mapping server. The system has the capability to pin-point and track vehicles in real time using a 3D interface, which is based on user-based AutoCAD mine maps using the Google-Earth graphics interface. All equipped vehicles are shown in a 3D mine map stored in a local server through a wireless network. When low visibility conditions are present, the system indicates available exit/escape routes for driver safety. The ADS potentially increases reliability and reduces uncertainty in open pit mining operations.
基金Project supported by the China Postdoctoral Science Foundation(Grant No.2017M620322)the National Natural Science Foundation of China(Grant No.61402188)+1 种基金Priority for the Postdoctoral Scientific and Technological Program of Hubei Province,China in 2017the Science and Technology Program of Shenzhen of China(Grant Nos.JCYJ 20170818160208570 and JCYJ 20170307160458368)
文摘In our recent work we showed, by investigating the initialization of some unusual forms of assisted driving Hamiltonians, that the addition of an assisted driving Hamiltonian is not always useful in quantum adiabatic evolution. These unusual forms are those that are not the relatively fixed ones that are widely used in the literature. In this paper, we continue this study, providing further evidence for the validity of the conclusion above by researching some relatively more complex forms of assisted driving scheme, which generalize the ones studied in our previous work.
文摘The multiple tasks involved in real-time driving are challenging tasks for any new learner of driving. The proposed Low Cost Driving Trainer Assistance System (DTAS) helps the amateur drivers to learn the basic skills involved while driving a vehicle, in particular a 4 wheeler like a car. The proposed system not only helps the novice drivers to gain confidence but also saves money spent on fuels while learning. The proposed DTAS system uses a steering wheel, an accelerator pedal, a brake pedal, gear mechanism and virtual (simulated) road environment. We also monitor and record the vital system parameters during the training period and analyze the same. The proposed DTAS involves operations like taking a turn, braking, accelerating, using dashboard functions and changing gears.
基金This work is supported in part by the National Natural Science Foundation of China(Grant Number 61971078)which provided domain expertise and computational power that greatly assisted the activity+1 种基金This work was financially supported by Chongqing Municipal Education Commission Grants forMajor Science and Technology Project(KJZD-M202301901)the Science and Technology Research Project of Jiangxi Department of Education(GJJ2201049).
文摘Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted videos can assist drivers in making decisions.However,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time detection.We proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary shapes.Our model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD model.The enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text regions.Additionally,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s performance.We further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection speed.This model holds potential for practical applications in real-world scenarios.
文摘Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recognition System(TSRS)is one of themost important components ofADAS.Among the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing time.Accordingly,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed modules.Firstly,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured frames.Secondly,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise recognition.In addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting technique.Through rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,respectively.Furthermore,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.
