With the advancement of unmanned aerial vehicle(UAV)technology,the market for drones and the cooperation of many drones are expanding.Drone swarms move together in multiple regions to perform their tasks.A Ground Cont...With the advancement of unmanned aerial vehicle(UAV)technology,the market for drones and the cooperation of many drones are expanding.Drone swarms move together in multiple regions to perform their tasks.A Ground Control Server(GCS)located in each region identifies drone swarmmembers to prevent unauthorized drones from trespassing.Studies on drone identification have been actively conducted,but existing studies did not consider multiple drone identification environments.Thus,developing a secure and effective identification mechanism for drone swarms is necessary.We suggested a novel approach for the remote identification of drone swarms.For an efficient identification process between the drone swarm and the GCS,each Reader drone in the region collects the identification information of the drone swarmand submits it to the GCS for verification.The proposed identification protocol reduces the verification time for a drone swarm by utilizing batch verification to verify numerous drones in a drone swarmsimultaneously.To prove the security and correctness of the proposed protocol,we conducted a formal security verification using ProVerif,an automatic cryptographic protocol verifier.We also implemented a non-flying drone swarmprototype usingmultiple Raspberry Pis to evaluate the proposed protocol’s computational overhead and effectiveness.We showed simulation results regarding various drone simulation scenarios.展开更多
There is an urgent need for the development of a method that can undertake rapid, effective, and accurate monitoring and identification of fog by satellite remote sensing, since heavy fog can cause enormous disasters ...There is an urgent need for the development of a method that can undertake rapid, effective, and accurate monitoring and identification of fog by satellite remote sensing, since heavy fog can cause enormous disasters to China’s national economy and people's lives and property in the urban and coastal areas. In this paper, the correlative relationship between the reflectivity of land surface and clouds in different time phases is found, based on the analysis of the radiative and satellite-based spectral characteristics of fog. Through calculation and analyses of the relative variability of the reflectivity in the images, the threshold to identify quasi-fog areas is generated automatically. Furthermore, using the technique of quick image run-length encoding, and in combination with such practical methods as analyzing texture and shape fractures, smoothness, and template characteristics, the automatic identification of fog and fog-cloud separation using meteorological satellite remote sensing images are studied, with good results in application.展开更多
Tailings ponds are critical facilities in the mining industry,and accurate monitoring and management of these ponds are of paramount importance.However,conventional object detection methodologies,including recent adva...Tailings ponds are critical facilities in the mining industry,and accurate monitoring and management of these ponds are of paramount importance.However,conventional object detection methodologies,including recent advancements,often face significant challenges in addressing the complexities inherent to tailings pond environments.This is particularly due to deficiencies in their loss function design,which can result in protracted convergence times and suboptimal performance when detecting smaller targets.In this study,we introduce an innovative loss function termed the Rapid Intersection over Union(RIoU)loss function,which incorporates a focal weight and is integrated into the YOLOv5 object detection framework to develop the YOLOv5-RF model.This approach aims to enhance both convergence speed and improve convergence accuracy in the tailings pond identification process by comprehensively addressing the specific challenges posed by complex environmental conditions,thereby enhancing the precision and robustness of tailings pond target detection.It integrates the concepts of the central triangle and the aspect ratio of the circumscribed rectangle,assigning specific weights and penalty terms to optimize the model’s performance in object detection tasks.We validated the efficacy of YOLOv5-RF through simulation experiments and high-resolution remote sensing images of tailings ponds.The experimental results indicate that RIoU facilitates faster convergence rates.Specifically,YOLOv5-RF achieves accuracy and recall rates that are 2%and 2.1%higher than those of YOLOv5,respectively.Furthermore,it completes 120 iterations in 1.08 hours less time compared to its predecessor model while exhibiting an inference time that is 11.7 ms shorter than that for YOLOv5.These findings suggest that our model significantly enhances processing speed without compromising accuracy levels.This research offers novel technical approaches as well as theoretical support for monitoring tailings ponds using computer vision and remote sensing technologies.展开更多
基金supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00225201,Development of Control Rights Protection Technology to Prevent Reverse Use of Military Unmanned Vehicles,50)by MSIT under the ITRC(Information Technology Research Center)Supported Program(IITP-2023-2018-0-01417,Industrial 5G Bigdata Based Deep Learning Models Development and Human Resource Cultivation,50)supervised by the IITP.
文摘With the advancement of unmanned aerial vehicle(UAV)technology,the market for drones and the cooperation of many drones are expanding.Drone swarms move together in multiple regions to perform their tasks.A Ground Control Server(GCS)located in each region identifies drone swarmmembers to prevent unauthorized drones from trespassing.Studies on drone identification have been actively conducted,but existing studies did not consider multiple drone identification environments.Thus,developing a secure and effective identification mechanism for drone swarms is necessary.We suggested a novel approach for the remote identification of drone swarms.For an efficient identification process between the drone swarm and the GCS,each Reader drone in the region collects the identification information of the drone swarmand submits it to the GCS for verification.The proposed identification protocol reduces the verification time for a drone swarm by utilizing batch verification to verify numerous drones in a drone swarmsimultaneously.To prove the security and correctness of the proposed protocol,we conducted a formal security verification using ProVerif,an automatic cryptographic protocol verifier.We also implemented a non-flying drone swarmprototype usingmultiple Raspberry Pis to evaluate the proposed protocol’s computational overhead and effectiveness.We showed simulation results regarding various drone simulation scenarios.
基金Key research project "Research of Shanghai City and Costal Heavy Fog Remote Sensing Detecting and Warning System" of Science and Technology Commission of Shanghai Municipality (075115011)
文摘There is an urgent need for the development of a method that can undertake rapid, effective, and accurate monitoring and identification of fog by satellite remote sensing, since heavy fog can cause enormous disasters to China’s national economy and people's lives and property in the urban and coastal areas. In this paper, the correlative relationship between the reflectivity of land surface and clouds in different time phases is found, based on the analysis of the radiative and satellite-based spectral characteristics of fog. Through calculation and analyses of the relative variability of the reflectivity in the images, the threshold to identify quasi-fog areas is generated automatically. Furthermore, using the technique of quick image run-length encoding, and in combination with such practical methods as analyzing texture and shape fractures, smoothness, and template characteristics, the automatic identification of fog and fog-cloud separation using meteorological satellite remote sensing images are studied, with good results in application.
基金supported by the Erdos Major“Leader Recruitment”Technological Project[JBGS-2023-001]Research Grant from the National Institute of Natural Hazards,Ministry of Emergency Management of China[ZDJ2019-17]Civil Aerospace Technology Advance Research Project of China[D040405].
文摘Tailings ponds are critical facilities in the mining industry,and accurate monitoring and management of these ponds are of paramount importance.However,conventional object detection methodologies,including recent advancements,often face significant challenges in addressing the complexities inherent to tailings pond environments.This is particularly due to deficiencies in their loss function design,which can result in protracted convergence times and suboptimal performance when detecting smaller targets.In this study,we introduce an innovative loss function termed the Rapid Intersection over Union(RIoU)loss function,which incorporates a focal weight and is integrated into the YOLOv5 object detection framework to develop the YOLOv5-RF model.This approach aims to enhance both convergence speed and improve convergence accuracy in the tailings pond identification process by comprehensively addressing the specific challenges posed by complex environmental conditions,thereby enhancing the precision and robustness of tailings pond target detection.It integrates the concepts of the central triangle and the aspect ratio of the circumscribed rectangle,assigning specific weights and penalty terms to optimize the model’s performance in object detection tasks.We validated the efficacy of YOLOv5-RF through simulation experiments and high-resolution remote sensing images of tailings ponds.The experimental results indicate that RIoU facilitates faster convergence rates.Specifically,YOLOv5-RF achieves accuracy and recall rates that are 2%and 2.1%higher than those of YOLOv5,respectively.Furthermore,it completes 120 iterations in 1.08 hours less time compared to its predecessor model while exhibiting an inference time that is 11.7 ms shorter than that for YOLOv5.These findings suggest that our model significantly enhances processing speed without compromising accuracy levels.This research offers novel technical approaches as well as theoretical support for monitoring tailings ponds using computer vision and remote sensing technologies.
