Unexploded ordnance(UXO)poses a threat to soldiers operating in mission areas,but current UXO detection systems do not necessarily provide the required safety and efficiency to protect soldiers from this hazard.Recent...Unexploded ordnance(UXO)poses a threat to soldiers operating in mission areas,but current UXO detection systems do not necessarily provide the required safety and efficiency to protect soldiers from this hazard.Recent technological advancements in artificial intelligence(AI)and small unmanned aerial systems(sUAS)present an opportunity to explore a novel concept for UXO detection.The new UXO detection system proposed in this study takes advantage of employing an AI-trained multi-spectral(MS)sensor on sUAS.This paper explores feasibility of AI-based UXO detection using sUAS equipped with a single(visible)spectrum(SS)or MS digital electro-optical(EO)sensor.Specifically,it describes the design of the Deep Learning Convolutional Neural Network for UXO detection,the development of an AI-based algorithm for reliable UXO detection,and also provides a comparison of performance of the proposed system based on SS and MS sensor imagery.展开更多
This paper aims to provide the reader with the results of the Unexploded Ordnance(UXO)survey of the defensive historical naval minefields launched by the Romanian and German Navies on the Romanian Black Sea coast,duri...This paper aims to provide the reader with the results of the Unexploded Ordnance(UXO)survey of the defensive historical naval minefields launched by the Romanian and German Navies on the Romanian Black Sea coast,during the Second World War.This UXO survey was carried out between 2015-2018 by the Romanian Navy’s hydrographic ship“Commander Alexandru Cătuneanu”and Romanian Mine Warfare Data Center,using towed side-scan sonar technology and oceanographic observations.After explaining the materials and methodology,the results are presented and discussed:mosaics of the minefields,side-scan images of UXO contacts,side-scan images of the wrecks that were sunk in the minefields and some visible natural geological features of the seafloor.It was concluded that most of the objects discovered are sinkers,wreck debris or parts of chains,which does not represent a danger to navigation.展开更多
基金the Office of Naval Research for supporting this effort through the Consortium for Robotics and Unmanned Systems Education and Research。
文摘Unexploded ordnance(UXO)poses a threat to soldiers operating in mission areas,but current UXO detection systems do not necessarily provide the required safety and efficiency to protect soldiers from this hazard.Recent technological advancements in artificial intelligence(AI)and small unmanned aerial systems(sUAS)present an opportunity to explore a novel concept for UXO detection.The new UXO detection system proposed in this study takes advantage of employing an AI-trained multi-spectral(MS)sensor on sUAS.This paper explores feasibility of AI-based UXO detection using sUAS equipped with a single(visible)spectrum(SS)or MS digital electro-optical(EO)sensor.Specifically,it describes the design of the Deep Learning Convolutional Neural Network for UXO detection,the development of an AI-based algorithm for reliable UXO detection,and also provides a comparison of performance of the proposed system based on SS and MS sensor imagery.
文摘This paper aims to provide the reader with the results of the Unexploded Ordnance(UXO)survey of the defensive historical naval minefields launched by the Romanian and German Navies on the Romanian Black Sea coast,during the Second World War.This UXO survey was carried out between 2015-2018 by the Romanian Navy’s hydrographic ship“Commander Alexandru Cătuneanu”and Romanian Mine Warfare Data Center,using towed side-scan sonar technology and oceanographic observations.After explaining the materials and methodology,the results are presented and discussed:mosaics of the minefields,side-scan images of UXO contacts,side-scan images of the wrecks that were sunk in the minefields and some visible natural geological features of the seafloor.It was concluded that most of the objects discovered are sinkers,wreck debris or parts of chains,which does not represent a danger to navigation.
文摘针对常规兵器靶场试验、部队训练及演习过程中非爆弹定位困难的问题,介绍了一种采用低成本声学传感器的终点弹道未爆弹探测技术。根据弹着区范围,布置若干声学传感器,保证其测量范围覆盖整个弹着区。对于每一个声学传感器采集到的气动噪声及落地声信号,执行以下计算步骤:采用快速傅里叶变换与拉普拉斯小波分析技术进行声学信号的降噪与增强;采用短时能量、短时幅度以及短时过零率进行气动噪声与落地声端点检测;采用小波包分析技术提取降噪增强后声学信号的特征;采用基于最小距离的阈值准则进行终点弹道气动噪声及落地声的识别。靶场试验未爆弹落点粗定位结果显示,文中所提技术可用于未爆弹落地点定位,定位精度可达10 m.
