改进YOLOv5的无人机影像小目标检测算法

无人机航拍影像具有目标尺度变化大、背景复杂等诸多特性，导致现有的检测器难以检测出航拍影像中的小目标。针对无人机影像中小目标误检漏检的问题，提出了改进YOLOv5的算法模型Drone-YOLO。增加了检测分支以提高模型在多尺度下的检测能力。设计了多层次信息聚合的特征金字塔网络结构，实现跨层次信息的融合。设计了基于多尺度通道注意力机制的特征融合模块，提高对小目标的关注度。将预测头的分类任务与回归任务解耦，使用Alpha-IoU优化损失函数定义，提升模型检测的效果。通过无人机影像数据集VisDrone的实验结果表明，Drone-YOLO模型较YOLOv5模型在AP50指标上提高了4.91个百分点，推理延时仅需16.78 ms。对比其他主流模型对于小目标拥有更好的检测效果，能够有效完成无人机航拍影像的小目标检测任务。     

改进YOLOv5的无人机影像车辆检测方法

针对传统遥感影像车辆目标检测算法易受干扰、鲁棒性较差且在实际应用当中会产生一定的漏检与误检现象等问题,提出了一种基于改进YOLOv5s的轻量级无人机遥感影像车辆目标检测算法。以YOLOv5s为基线模型,根据车辆目标长宽比相对固定的特点,对锚框尺寸进行修正,提高了锚框与车辆目标的契合度;针对无人机影像中车辆密集情况,进行了加权框融合改进,对检测框合并,解决了预测框计数不准确的问题;由于车辆目标具有多变性,通过增加注意力机制网络,提升了模型识别车辆的速度和准确性。研究表明,改进的YOLOv5s模型可以实现实时准确的无人机影像车辆检测。     

基于无人机倾斜摄影技术的多源遥感影像变化检测并行系统设计

为使无人机遥感图像的影像残差值得到有效控制,提升多源遥感影像变化特征的检测精度水平,设计基于无人机倾斜摄影技术的多源遥感影像变化检测并行系统。在C/S框架体系中,设置并行运作电路、像素点检测主机、HBase存储结构与遥感影像显示器,完成对多源遥感影像变化检测并行系统的硬件设计。根据联合平差指标的数值水平,计算密集度指标,联合已知影像数据,求解无人机倾斜摄影过程中的纹理映射条件,实现对多源遥感影像的建模处理。按照影像特征提取结果,完善影像检测金字塔的构型模式,将无人机数字影像与并行检测节点匹配起来,再结合各级硬件应用结构,完成基于无人机倾斜摄影技术的多源遥感影像变化检测并行系统设计。实验结果表明,设计的系统在无人机倾斜摄影技术的作用下,遥感图像在x轴、y轴、z轴方向上的影像残差指标均出现明显下降的数值变化状态,能够有效提升多源遥感影像变化特征的检测精度。     

无人机航拍图像语义分割研究综述

随着无人机技术的快速发展,无人机在研究领域和工业应用方面受到了广泛的关注。图像和视频是无人机感知周围环境的重要途径。图像语义分割是计算机视觉领域的研究热点,在无人驾驶、智能机器人等场景中应用广泛。无人机航拍图像语义分割是在无人机航拍图像的基础上,运用语义分割技术使无人机获得场景目标智能感知能力。介绍了语义分割技术和无人机的应用发展、相关无人机航拍数据集、无人机航拍图像特点和常用语义分割评价指标。针对无人机航拍的特点介绍了相关语义分割方法,包括小目标、模型实时性和多尺度整合等方面。综述无人机语义分割相关应用,包括线检测、农业和建筑物提取等方向,并分析无人机语义分割未来发展趋势和挑战。     

基于图像分割的无人机遥感影像目标提取技术

为全面增强遥感影像上地物波谱的反射特性能力,实现对无人机目标的无误提取,提出基于图像分割的无人机遥感影像目标提取技术;在类哈尔滤波器结构的支持下,按照区域环境中地物目标的颜色特征,完成低层影像特征的量化处理,实现基于图像分割技术的无人机遥感深度图获取;定义与无人机遥感影像相关的基本名词,通过原始特征选择的方式,判定地物波谱的平均反射特性水平,得到准确的特征元素相关性测度数值,完成无人机遥感影像的目标融合处理;在此基础上,分割多分辨率条件下的影像目标,在定义图像纹理与尺度条件的同时,得到最终的地物提取结果,实现基于图像分割无人机遥感影像目标提取技术的应用;对比实验结果表明,在初始采集相位条件及亚像素条件下,目标地物的波谱宽度均超过7.0μm,遥感影像的反射特性能力大幅提升,满足对无人机目标无误提取的实用需求。     

无人机视角下的目标检测研究进展

在人工智能技术的支持下,无人机初步获得智能感知能力,在实际应用中展现出高效灵活的数据收集能力。无人机视角下的目标检测作为关键核心技术,在诸多领域中发挥着不可替代的作用,具有重要的研究意义。为了进一步展现无人机视角下的目标检测研究进展,本文对无人机视角下的目标检测算法进行了全面总结,并对已有算法进行了归类、分析和比较。1）介绍无人机视角下的目标检测概念,并总结无人机视角下目标检测所面临的目标尺度、空间分布、样本数量、类别语义以及优化目标等5大不均衡挑战。在介绍现有研究方法的基础上,特别整理并介绍了无人机视角下目标检测算法在交通监控、电力巡检、作物分析和灾害救援等实际场景中的应用。2）重点阐述从数据增强策略、多尺度特征融合、区域聚焦策略、多任务学习以及模型轻量化等方面提升无人机视角下目标检测性能的方法,总结这些方法的优缺点并分析了其与现存挑战之间的关联性。3）全面介绍基于无人机视角的目标检测数据集,并呈现已有算法在两个较常用公共数据集上的性能评估。4）对无人机视角下目标检测技术的未来发展方向进行了展望。     

基于卷积神经网络的无人机油气管线巡检监察系统

为满足深埋式油气管道巡检监察需求,以及解决常规人工巡检手段效率低、时效性差、安全性低等问题,通过结合无人机飞行平台、卷积神经网络算法及计算机系统集成技术,设计并开发了一套基于卷积神经网络的无人机油气管线巡检监察系统,为油气管线的巡检监察工作提供技术支撑.本文首先介绍了巡检监察系统的总体设计方案、及作业流程进行了介绍;其次对系统组成进行了详细介绍,整个系统由无人机飞行平台、神经网络目标检测系统、无人机巡检监察管理系统以及无人机巡检执法终端四大子系统组成,无人机飞行平台以油动固定翼无人机为飞行载体,搭载高清相机进行数据采集,神经网络目标检测系统对影像数据进行自动检测、识别、搜索沿线工程车辆和管线隐患的目标,无人机巡检监察管理系统实现数据信息的存储管理及分发推送,无人机巡检执法终端接收隐患目标推送信息并进行现场快速执法;最后,对该系统的应用情况及后续的发展方向进行了总结和展望.目前,该系统成功应用于河南、甘肃等省份的油气管线巡检监察作业中,结果表明系统满足油气管线巡检监察的业务需求.     

低空无人机影像处理技术及方法研究

近年来,科学技术的快速发展使得无人机的低空摄影测量技术在三维重建等方面的应用范围不断增加,但是,无人机影像本身的特殊性较为明显,在后续处理,特别是数据处理等方面的困难程度较高.因此,为了更加高效、更加简单地完成低空无人机影像处理,通常需要使用相应的处理技术与方法.将低空无人机影像的主要特点作为入手点,通过低空无人机影像数据获取等分析引出低空无人机影像处理技术及其方法,并进行深入研究.     

基于四旋翼无人机平台的实时多目标检测算法

随着无人机技术和深度学习技术的发展,基于深度学习的多目标检测算法在工业无人机中得到了广泛的应用。针对目前基于深度学习的多目标检测算法占用大量计算量资源,难以在算力有限的中小型无人机平台上实时运行的问题,分析了深度学习算法在低功耗CPU上的耗时,提出一种卷积神经网络计算优化方法。在机载计算机中进行仿真,结果表明在检测效果基本不变的条件下,算法帧率达到了56FPS,实现了无人机平台上的实时多目标检测。     

基于深度学习的无人机多目标检测算法研究

无人机多目标检测技术广泛应用于交通、航空等重要领域，发展前景广阔，市场需求空间巨大。传统的目标检测算法已无法满足无人机进行多目标检测过程中可能遇到的目标数量多、目标种类多、拍摄目标小等需求，因此提升无人机多目标检测能力成为了急需解决的难题，也是重要的研究方向。针对无人机对目标检测实时性要求较高，同时考虑到提高多目标和小目标的检测精度以及推理速度，选用YOLO目标检测算法为模型，分析YOLO系列算法的优缺点，并对各算法进行总结归纳。     

基于SIFT和TPS算法的四旋翼无人机图像自动配准

针对四旋翼无人机图像姿态倾角大、图像变形明显等特点,采用尺度不变特征变换(SIFT)算法和薄板样条模型(TPS)对四旋翼无人机图像进行特征点匹配和配准实验研究,从拼接图像的目视效果和配准均方差方面比较分析了TPS模型与常用的仿射变换及多项式变换模型的图像配准效果。结果表明:在SIFT算法精确的同名点匹配下,TPS变换模型能够兼顾四旋翼无人机图像的整体刚性变形及局部的非刚性变形,无论是目视效果还是均方差定量分析,TPS变换的图像配准精度最高\,效果最好,能够满足四旋翼无人机图像的快速配准、拼接要求。     

UAV imagery based potential safety hazard evaluation for high-speed railroad using Real-time instance segmentation

Potential safety hazards (PSHs) along the track needs to be inspected and evaluated regularly to ensure a safe environment for high-speed railroad operations. Other than track inspection, evaluating potential safety hazards in the nearby areas often requires inspectors to patrol along the track and visually identify potential threads to the train operation. The current visual inspection approach is very time-consuming and may raise safety concerns for the inspectors, especially in remote areas. Using the unmanned aerial vehicle (UAV) has great potential to complement the visual inspection by providing a better view from the top and ease the safety concerns in many cases. This study develops an automatic PSH detection framework named YOLARC (You Only Look at Railroad Coefficients) using UAV imagery for high-speed railroad monitoring. First, YOLARC is equipped with a new backbone having multiple available receptive fields to strengthen the multi-scale representation capability at a granular level and enrich the semantic information in the feature space. Then, the system integrates the abundant semantic features at different high-level layers by a light weighted feature pyramid network (FPN) with multi-scale pyramidal architecture and a Protonet with residual structure to precisely predict the track areas and PSHs. A hazard level evaluation (HLE) method, which calculates the distance between identified PSH and the track, is also developed and integrated for quantifying the hazard level. Experiments conducted on the UAV imagery of high-speed railroad dataset show the proposed system can quickly and effectively turn UAV images into useful information with a high detection rate and processing speed.     

Timely autonomous identification of UAV safe landing zones

For many applications such as environmental monitoring in the aftermath of a natural disaster and mountain search-and-rescue, swarms of autonomous Unmanned Aerial Vehicles (UAVs) have the potential to provide a highly versatile and often relatively inexpensive sensing platform. Their ability to operate as an ‘eye-in-the-sky’, processing and relaying real-time colour imagery and other sensor readings facilitate the removal of humans from situations which may be considered dull, dangerous or dirty. However, as with manned aircraft they are likely to encounter errors, the most serious of which may require the UAV to land as quickly and safely as possible. Within this paper we therefore present novel work on autonomously identifying Safe Landing Zones (SLZs) which can be utilised upon occurrence of a safety critical event. Safe Landing Zones are detected and subsequently assigned a safety score either solely using multichannel aerial imagery or, whenever practicable by fusing knowledge in the form of Ordnance Survey (OS) map data with such imagery. Given the real-time nature of the problem we subsequently model two SLZ detection options one of which utilises knowledge enabling the UAV to choose an optimal, viable solution. Results are presented based on colour aerial imagery captured during manned flight demonstrating practical potential in the methods discussed.     

入河排污口遥感排查进展评述

入河排污口是人为污染物流入河流的最后一道关卡,对其进行精确排查在水资源保护、水污染防治等工作中具有重要作用.首先回顾了近30 a来国内大型入河排污口排查工作情况,分别从人工实地调查、GIS台账系统建设、卫星遥感监测和无人机排查4个方面进行介绍;其次,在分析了直接目视解译、基于水环境参数反演以及基于地物分类等常用入河排污...     

Environmental condition in British moorlands: quantifying the life cycle of Calluna vulgaris using UAV aerial imagery

ABSTRACT

As the dominant vegetation species of most British moorlands, Calluna vulgarisis the focus of much scientific interest. While multiple approaches for quantifying the life cycle of the species have been tested, few, if any, have been successful. Given that British moorland environments are internationally valuable in terms of biogeography and carbon storage, but also inherently vulnerable to change, robust long-term monitoring is urgently needed. This study aimed to develop an original methodology, using UAV (Unmanned Aerial Vehicle) aerial imagery to quantify both flowering and vegetation height at different C. vulgaris growth phases. The former has been previously investigated, although not using low-altitude UAV imagery. The latter has not been tested before. Flower coverage was successfully quantified using supervised pixel-based classification, with statistically significant differences found between percentage flower coverage at each growth phase. Findings from height analysis, using structure-from-motion point clouds, suggest that modelled vegetation height can also be used to distinguish between growth phases. These findings demonstrate that UAV imagery can improve data acquisition in field ecology. The novel approach developed here, based on flower coverage and vegetation height, has potential for use beyond the moorland environment, to improve understadning of spatial characteristics of ecological systems and processes.     

自卫干扰对无人机敏感性的影响研究

研究了单架无人机在突防地空导弹系统的过程中,自卫干扰对无人机敏感性的影响,分析了自卫干扰在敏感性各个环节的作用,仿真分析了平均干扰功率对无人机最小暴露半径、被探测到的概率、脱靶距离及被击中概率的影响。仿真结果表明,使用自卫干扰技术能有效地降低无人机的敏感性,从而提高其作战生存力。研究结果可为无人机敏感性评估、生存力增强措施的研究及雷达探测系统的效能评估提供一定的依据。     

基于无人机图像的输电线检测方法

在无人机应用于输电线巡检背景下,为了方便后续的输电线故障检测与分析,提出一种新的基于无人机图像的输电线检测方法.首先,通过Otsu获取高低阈值的方法改进Canny边缘检测算法,用于提取输电线图像边缘;然后,通过数学形态学方法处理边缘检测得到的二值图像,并用分式查表法改进的Hough变换对数学形态学处理后的图像进行直线段检测;最后,提出线-线空间信息分析的方法,对检测出来的直线段进行筛选和拟合.通过在无人机图像上的实验结果表明,本文提出的输电线检测方法是一种性能良好的基于无人机图像的输电线检测方法.     

Unmanned Aerial Vehicle Security Using Recursive Parameter Estimation

The proliferation of Unmanned Aerial Vehicles (UAVs) brings about many new security concerns. A common concern with UAV security is for an intruder to take control of a UAV, which leads for a need for a real time anomaly detection system. This research resulted in a prototype UAV monitoring system that captures flight data, and then performs real time estimation and tracking of the airframe and controller parameters. The aforementioned is done by utilizing the Recursive Least Squares Method (RLSM). Using statistical validation and trend analysis, parameter estimates are critical for the detection of cyber attacks and incipient hardware failures that can invariably jeopardize mission success. The results demonstrate that achieving efficient anomaly detection during flight is possible through the application of statistical methods to profile system behavior. The anomaly detection system that was designed can be performed in real time while the UAV is in flight, constantly verifying its parameters.