The accuracy of center height detection for corrugated beam guardrails is significantly affected by robot posture in the mobile highway guardrail detection systems based on structured light vision.To address the probl...The accuracy of center height detection for corrugated beam guardrails is significantly affected by robot posture in the mobile highway guardrail detection systems based on structured light vision.To address the problem,this paper proposes an integrated calibration method for structured light vision sensors.In the proposed system,the sensor is mounted on a crawler-type mobile robot,which scans and measures the center height of guardrails while in motion.However,due to external disturbances such as uneven road surfaces and vehicle vibrations,the posture of the robot may deviate,causing displacement of the sensor platform and resulting in spatial 3D measurement errors.To overcome this issue,the system integrates inertial measurement unit(IMU)data into the sensor calibration process,enabling realtime correction of posture deviations through sensor fusion.This approach achieves a unified calibration of the structured light vision system,effectively compensates for posture-induced errors,and enhances detection accuracy.A prototype was developed and tested in both laboratory and real highway environments.Experimental results demonstrate that the proposed method enables accurate center height detection of guardrails under complex road conditions,significantly reduces posture-related measurement errors,and greatly improves the efficiency and reliability of traditional detection methods.展开更多
We introduce a novel stretchable photodetector with enhanced multi-light source detection,capable of discriminating light sources using artificial intelligence(AI).These features highlight the application potential of...We introduce a novel stretchable photodetector with enhanced multi-light source detection,capable of discriminating light sources using artificial intelligence(AI).These features highlight the application potential of deep learning enhanced photodetectors in applications that require accurate for visual light communication(VLC).Experimental results showcased its excellent potential in real-world traffic system.This photodetector,fabricated using a composite structure of silver nanowires(AgNWs)/zinc sulfide(ZnS)-polyurethane acrylate(PUA)/AgNWs,maintained stable performance under 25%tensile strain and 2 mm bending radius.It shows high sensitivity at both 448 and 505 nm wavelengths,detecting light sources under mechanical deformations,different wavelengths and frequencies.By integrating a one-dimensional convolutional neural network(1D-CNN)model,we classified the light source power level with 96.52%accuracy even the light of two wavelengths is mixed.The model’s performance remains consistent across flat,bent,and stretched states,setting a precedent for flexible electronics combined with AI in dynamic environments.展开更多
Visible light communication(VLC)is a promising research field in modern wireless communication.VLC has its irreplaceable strength including rich spectrum resources,no electromagnetic disturbance,and high-security guar...Visible light communication(VLC)is a promising research field in modern wireless communication.VLC has its irreplaceable strength including rich spectrum resources,no electromagnetic disturbance,and high-security guarantee.However,VLC systems suffer from the non-linear effects that exist in almost every part of the system.As a part of artificial intelligence,machine learning(ML)is showing its potential in non-linear mitigating for its natural ability to fit all kinds of transfer functions,which may dramatically push the research in VLC.This paper introduces the application of ML in VLC,describes five recent research of deep learning applications in VLC,and analyses the performance.展开更多
基金Supported by the Special Fund for Basic Scientific Research of Central-Level Public Welfare Scientific Research Institutes(2024-9007)。
文摘The accuracy of center height detection for corrugated beam guardrails is significantly affected by robot posture in the mobile highway guardrail detection systems based on structured light vision.To address the problem,this paper proposes an integrated calibration method for structured light vision sensors.In the proposed system,the sensor is mounted on a crawler-type mobile robot,which scans and measures the center height of guardrails while in motion.However,due to external disturbances such as uneven road surfaces and vehicle vibrations,the posture of the robot may deviate,causing displacement of the sensor platform and resulting in spatial 3D measurement errors.To overcome this issue,the system integrates inertial measurement unit(IMU)data into the sensor calibration process,enabling realtime correction of posture deviations through sensor fusion.This approach achieves a unified calibration of the structured light vision system,effectively compensates for posture-induced errors,and enhances detection accuracy.A prototype was developed and tested in both laboratory and real highway environments.Experimental results demonstrate that the proposed method enables accurate center height detection of guardrails under complex road conditions,significantly reduces posture-related measurement errors,and greatly improves the efficiency and reliability of traditional detection methods.
基金supported by National Research Foundation of Korea(NRF)grants(Number RS-2023-00247545)funded by the Korean government(MSIP)funded and conducted under the Competency Development Program for Industry Specialists of the Korean Ministry of Trade,Industry and Energy(MOTIE),operated by Korea Institute for Advancement of Technology(KIAT)(No.P0023704,SemiconductorTrack Graduate School(SKKU)).
文摘We introduce a novel stretchable photodetector with enhanced multi-light source detection,capable of discriminating light sources using artificial intelligence(AI).These features highlight the application potential of deep learning enhanced photodetectors in applications that require accurate for visual light communication(VLC).Experimental results showcased its excellent potential in real-world traffic system.This photodetector,fabricated using a composite structure of silver nanowires(AgNWs)/zinc sulfide(ZnS)-polyurethane acrylate(PUA)/AgNWs,maintained stable performance under 25%tensile strain and 2 mm bending radius.It shows high sensitivity at both 448 and 505 nm wavelengths,detecting light sources under mechanical deformations,different wavelengths and frequencies.By integrating a one-dimensional convolutional neural network(1D-CNN)model,we classified the light source power level with 96.52%accuracy even the light of two wavelengths is mixed.The model’s performance remains consistent across flat,bent,and stretched states,setting a precedent for flexible electronics combined with AI in dynamic environments.
基金This work was partially supported by National Key Research and Development Program of China(2017YFB0403603)the NSFC project(No.61925104)。
文摘Visible light communication(VLC)is a promising research field in modern wireless communication.VLC has its irreplaceable strength including rich spectrum resources,no electromagnetic disturbance,and high-security guarantee.However,VLC systems suffer from the non-linear effects that exist in almost every part of the system.As a part of artificial intelligence,machine learning(ML)is showing its potential in non-linear mitigating for its natural ability to fit all kinds of transfer functions,which may dramatically push the research in VLC.This paper introduces the application of ML in VLC,describes five recent research of deep learning applications in VLC,and analyses the performance.
