基于无人机多光谱图像的土壤水分检测方法研究

以表层土壤为对象,探究土壤的多光谱反射率与土壤水分含量相关性,进行基于无人机多光谱图像的土壤水分含量预测模型方法的探究。选取中国农业大学通州实验站为研究区域,实地采集试验田的土壤样本100组,按照一定梯度配制土壤含水量,配成的土壤含水率为10%~50%之间,土壤含量的真实值采用土壤烘干法进行测定。多光谱相机灵巧便捷,可搭载在无人机上对土壤进行监测。将RedEdged-M型多光谱相机搭载在Phantom 3型无人机上,选择阳光充足的采集环境,实时采集土壤样本的多光谱图像,建立土壤多光谱信息与水分含量之间的模型。利用处理光谱数据的ENVI5.3软件提取土壤样本多光谱信息,以多光谱相机自带的标准白板反射率为100%,计算出土壤样本在蓝、绿、红、红边、近红外五个波段的光谱反射率。采用BP神经网络算法、支持向量机算法、偏最小二乘算法分别建立基于无人机多光谱图像的土壤水分含量的预测模型。以80组土壤样本数据作为训练集,建立基于多光谱图像的土壤水分含量预测模型。采用莱文贝格-马夸特算法对BPNN进行改进,提高了其训练速度,当网络结构为5-10-1时,训练效果最好,本文选择该网络结构;SVM采取高斯核函数,当参数为0.56时,模型效果最好。本研究采用归一化均方根误差(NRMSE)和决策系数(R 2)对三种土壤水分含量的预测模型进行定量对比。以20组土壤样本数据作为测试集,结果可知,基于BP神经网络土壤水分含量预测模型的NRMSE为0.268,R 2为0.872;基于支持向量机的土壤水分含量预测模型的NRMSE为0.298,R 2为0.821;基于偏最小二乘土壤水分含量预测模型的NRMSE为0.316,R 2为0.789。对三种模型分析可知,基于BPNN的土壤水分含量预测模型效果均较好。结果可知,土壤的光谱反射率与含水率间存在较密切的相关性,将多光谱相机搭载在无人机上可以对土壤水分含量进行有效的实时监测,对监测土壤墒情提供技术支持和理论支撑。     

新型大面阵彩色CCD航测相机光学系统设计

介绍了一种有别于传统彩色航测相机的新型大面阵彩色CCD航测相机设计方案,该相机光学系统由Dalsa公司最新生产的6K×8K大面阵彩色CCD作为接收器.通过理论计算和ZEMAX光学设计软件的优化,给出了工作波长适应范围为0.46～0.70μm、焦距为360mm、视场角为10°、相对孔径为1∶4.3的设计实例.设计结果表明...     

一种Ku波段行波管发射机的设计

介绍了一种Ku波段行波管发射机的技术参数及其设计方法。主要叙述了系统中高压电源、监控电路和调制器的设计,并针对发射机在无人机载SAR方面的应用,就如何解决体积小、重量轻情况下的电磁兼容问题,低气压条件下的高压绝缘与散热矛盾作了较详细说明。     

融合多种特征的路面车辆检测方法

提出一种融合多种目标特征的单目视觉车辆检测方法。首先,利用车辆尾部的结构对称性提取出感兴趣区域(ROI),减少搜索范围;然后,利用车辆底部的阴影特征,在ROI中搜寻车辆可能出现的位置,找出假设目标;最后,利用亮度和轮廓信息对假设目标进行对称性验证,排除虚假目标,同时对车辆在图像中的位置实现精确定位。通过实验,验证了提出方法的有效性和鲁棒性。     

Efficient data management and control over WSNs using SDN‐enabled aerial networks

The recent developments in collaborative search, acquisition, and tracking have hoisted the geographical barrier. The network between unmanned aerial vehicles (UAVs) and wireless sensor networks (WSNs) is one such collaboration, which comprises battery‐powered static sensor nodes that act as sources and sinks and UAVs that act as relays. This collaborative network presents with opportunities and advantages, but at the same time, configuration of such networks is an arduous task. The WSN nodes are characterized by constant depleting power. Their network itself requires constant management and reconfiguration. These requisites can be slaked through the formation of an efficient data dissemination algorithm, which acclimates according to the network state. Considering this, a data dissemination approach is presented in this paper, which constructs a virtual topology predicated on the charge of WSN nodes utilizing software‐defined networks (SDNs) through UAVs. The topology is constantly monitored and reconfigured when required. The aerial nodes are equipped with multiple‐input multiple‐output (MIMO) antennas in order to facilitate simultaneous communication with the ground nodes, the base station, and the SDN controller. An efficient sleep timer and backoff counter strategies are also utilized by the proposed approach. The SDN controller facilitates the topology formation and maintenance of a sleep timer and a backoff counter. The proposed model is compared with clustered hierarchical layouts and hexagonal cell layouts through the network simulations. The results suggest significant improvements in the proposed model for various metrics, such as lifetime, delay, latency, delivery ratio, and throughput in comparison with the existing solutions.     

基于倾斜摄影技术的无人机电力巡检设计

随着电力输电线路的长度的不断增长,为了保证电力系统的运行安全,文中设计了一种基于倾斜摄影技术的无人机电力巡检系统。使用无人机搭载倾斜摄影相机采集输电线路及周边设备的图像信息,通过无人机无线传输将图像数据信息传输至地面站,再进行数据解析、分析及三维模型构建。从而完成输电线路故障的排查、安全隐患的排除,保障电力传输安全。此外,使用该倾斜摄影技术可以有效提高电力巡检判断的准确性。     

车辆高海拔环境起步性能试验研究

对于全域机动车辆而言,高海拔环境起步性能是评价其高原环境适应性和机动性的重要指标。针对多个型号车辆存在的高海拔环境起步困难问题,在系统开展车辆起步过程动力学分析的基础上,从车辆本身所具有的动力和所受外界阻力两个方面对高海拔环境车辆起步性能影响因素进行了深入分析,通过对某军用履带车辆高海拔起步性能的实车试验验证,确定了发动机低速扭矩特性、传动油温、行驶坡度、使用工况是高海拔环境影响车辆起步性能的关键因素,为车辆论证、研制、试验和使用工作的改进和发展提供了依据。     

An intelligent task offloading algorithm (iTOA) for UAV edge computing network

Unmanned Aerial Vehicle (UAV) has emerged as a promising technology for the support of human activities, such as target tracking, disaster rescue, and surveillance. However, these tasks require a large computation load of image or video processing, which imposes enormous pressure on the UAV computation platform. To solve this issue, in this work, we propose an intelligent Task Offloading Algorithm (iTOA) for UAV edge computing network. Compared with existing methods, iTOA is able to perceive the network’s environment intelligently to decide the offloading action based on deep Monte Calor Tree Search (MCTS), the core algorithm of Alpha Go. MCTS will simulate the offloading decision trajectories to acquire the best decision by maximizing the reward, such as lowest latency or power consumption. To accelerate the search convergence of MCTS, we also proposed a splitting Deep Neural Network (sDNN) to supply the prior probability for MCTS. The sDNN is trained by a self-supervised learning manager. Here, the training data set is obtained from iTOA itself as its own teacher. Compared with game theory and greedy search-based methods, the proposed iTOA improves service latency performance by 33% and 60%, respectively.     

无人机集群协同态势觉察一致性评估

无人机集群协同态势感知一致性是影响集群协同决策控制的重要因素,已有集群态势感知研究集中在多传感器态势数据融合,对态势感知一致性的讨论不充分,本文对集群协同态势觉察一致性评估方法进行设计.结合集群协同作战特点,分析集群协同态势感知一致性;建立集群协同态势觉察一致性评估模型,指出态势觉察一致性的可用情况;考虑战场信息的不确定性、指标的相关性等因素,提出基于非线性处理和指标变权的区间数形式下的态势觉察一致性计算方法.分析表明,与基于组合赋权的方法相比,本文方法在表示精度、差异度等方面有较好表现,可用于集群协同作战仿真和集群系统优化设计等研究.     

同频段混合信号中的无人机信号盲检测识别

无人机信号的探测识别技术是应对无人机黑飞滥用的关键技术之一。在实际信号监测环境中，经常会接收到多个信号的混合信号，它们在时域和频域上混叠且各信号分量调制样式相同。为解决在同频段混合信号中检测识别出无人机信号的问题，提出了一种通过谱特征分析判断无人机信号存在性的方法。分别采用基于二次方谱特征的无人机图传和WiFi混合信号检测识别算法以及基于频谱带宽特征的多无人机混合信号检测识别算法，通过对射频电路采集的信号进行仿真验证，实现了从同频段混合信号中检测识别出无人机信号分量。理论分析和实验测试结果证实了所提检测识别算法的有效性。