一种实时多尺度目标检测识别算法

无人机目标检测与识别任务中,目标随着飞行高度的改变尺寸发生显著变化。常规目标检测模型中,获取的小目标细节信息有限,检测精度较低;而适用于小目标的实时检测模型往往容易丢失大目标的背景信息,降低大目标的检测精度。针对以上多尺度目标检测识别任务难点,提出一种基于改进特征金字塔网络(Feature Pyramid Network, FPN)结构的实时多尺度目标检测识别模型。该模型通过增加特征金字塔层级覆盖更广的目标尺度,获取更为丰富的目标信息;同时,利用跨连接增加不同尺度特征融合的多样性,降低特征传导距离,保留更加完整的尺度特征来提高模型检测识别多尺度目标的性能。通过实验发现,相比于原始网络结构和相同特征层级的四层特征金字塔结构,加入改进特征金字塔结构的多尺度目标检测模型识别性能得到了提升。     

基于测量误差不确定性加权的快速相机位姿估计算法

在相机位姿估计任务中,参考点位置的测量容易受测量仪器或者所处环境影响,出现一定程度的测量误差,其中误差较大的点对最终求解精度的影响很大,被称为野值点。文章针对现有算法抗野值点能力较弱的问题,提出一种基于测量误差不确定性加权的快速相机位姿估计算法。该算法以经典的正交迭代算法为基础,引入M估计方法,对目标函数根据参考点的测量误差赋予相应大小的权值,最大程度地将野值点的影响排除,并引入Kronecker积对计算过程进行优化,减少了迭代过程中的冗余计算,提高运算速度。仿真实验结果表明,改进后的算法提升了原算法的抗野值点能力,且计算速度更快。     

无人机载PolInSAR城区散射机制初步分析

极化干涉合成孔径雷达（PolInSAR）在城市遥感领域中扮演着重要角色。它能够提高图像的相干性并提高反演结果的精度,所以对于其散射机制的解释往往受到许多研究人员的关注。相关的研究多从极化分解的角度考虑,却少有人从散射中心高度方面进行分析。本文使用Ku波段无人机载极化干涉SAR系统,实现了使用无人机SAR系统对地面进行成像,比较了极化干涉最优分解与Pauli分解作用在不同人造目标时散射中心的关系。我们初步分析了极化干涉SAR的物理意义,并使用C波段的机载极化干涉SAR系统对结论进行验证。     

Motion detection in moving camera videos using background modeling and FlowNet

Real-time moving object detection is challenging for moving cameras due to the moving background. Many studies use homography matrix to compensate for global motion by warping the background model to the current frame. Then, the pixel difference between the current frame and the background model is used for background subtraction. Moving pixels are extracted by applying adaptive threshold and some post-processing techniques. On the other hand, deep learning-based dense optical flow can be efficient enough to extract the moving pixels, but it increases computational cost. This study proposes a method to enhance a classical background modeling method with deep learning-based dense optical flow. The main contribution of this paper is to propose a fusing algorithm for dense optical flow and background modeling approach. The background modeling methods are error-prone, especially with continuous camera movement, while the optical flow method alone may not always be efficient. Our hybrid method fuses both techniques to improve the detection accuracy. We propose a software architecture to run background modeling and dense optical flow methods in parallel processes. The proposed implementation approach significantly increases the method’s working speed, while the proposed fusion and combining strategy improve detection results. The experimental results show that the proposed method can run at high speed and has satisfying performance against the methods in the literature.     

基于对抗深度学习的无人机航拍违建场地识别

对违建场地的检测方法主要是通过人工对无人机航拍视频进行检查,存在检测精度低、识别性能差、工作效率低的问题。提出一种结合空间变换网络与Fast RCNN的生成对抗网络ASTN-Fast RCNN,通过深度学习与无人机航拍视频相结合自动识别检测处在建设初期的违建场地。将空间变换网络作为生成器,生成Fast RCNN目标检测器难以识别的旋转形变样本,并通过目标检测器与生成器的对抗式训练,提高检测器的鲁棒性。实验结果表明,该方法能够有效提高对无人机航拍违建场地的识别性能。     

Modeling and Analysis of UAV-Assisted Mobile Network with Imperfect Beam Alignment

With the rapid development of emerging 5G and beyond (B5G), Unmanned Aerial Vehicles (UAVs) are increasingly important to improve the performance of dense cellular networks. As a conventional metric, coverage probability has been widely studied in communication systems due to the increasing density of users and complexity of the heterogeneous environment. In recent years, stochastic geometry has attracted more attention as a mathematical tool for modeling mobile network systems. In this paper, an analytical approach to the coverage probability analysis of UAV-assisted cellular networks with imperfect beam alignment has been proposed. An assumption was considered that all users are distributed according to Poisson Cluster Process (PCP) around base stations, in particular, Thomas Cluster Process (TCP). Using this model, the impact of beam alignment errors on the coverage probability was investigated. Initially, the Probability Density Function (PDF) of directional antenna gain between the user and its serving base station was obtained. Then, association probability with each tier was achieved. A tractable expression was derived for coverage probability in both Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) condition links. Numerical results demonstrated that at low UAVs altitude, beam alignment errors significantly degrade coverage performance. Moreover, for a small cluster size, alignment errors do not necessarily affect the coverage performance.     

基于角度不变的线阵推扫式CCD相机几何畸变在轨检校方法

对航天遥感相机进行在轨检校,是提高卫星产品质量,扩大产品应用效果的重要技术内容.文中研究了一种基于角度不变的线阵推扫式CCD相机几何畸变在轨检校方法.该方法利用相机外方元素对于相机视向量夹角角度影响比较小的原理,根据地面控制点和一级产品图像,求解相机视向量夹角,从中提取相机光学部件的畸变模型参数,从而实现相机内外方元素解耦.相机畸变模型采用一维3阶多项式,对焦距和主点等引起的低阶误差能够很好地吸收.该方法用在HJ-1A/B卫星的宽幅盖CCD相机几何畸变校正上,检校误差残留在2—6个像元,和参考数据精度相似,表明取得了很好的校正效果.     

Analysis and evaluation of a general camera model

A versatile General Camera Model, GCM, has been developed, and is described in detail. The model is general in the sense that it can capture both fisheye and conventional as well as catadioptric cameras in a unified framework. The camera model includes efficient handling of non-central cameras as well as compensations for decentring distortion. A novel way of analysing radial distortion functions of camera models leads to a straightforward improvement of conventional models with respect to generality, accuracy and simplicity. Different camera models are experimentally compared for two cameras with conventional and fisheye lenses, and the results show that the overall performance is favourable for the GCM.     

基于ROI的智能交通系统摄像机控制算法

针对城市道路监控的需求,提出了一种基于感兴趣区域的摄像机自适应控制方法。它作为车牌识别系统的一个辅助功能,在固定光圈的情况下,能够根据车牌识别和运动检测的反馈信息自适应地调节摄像机的快门和增益,获取较好质量的图片,从而达到提高车牌识别率的作用,特别是该方法能够大大降低强逆光和强眩光现象对采集图像质量的影响。     

基于人工神经网络的CCD数码相机颜色特征化

阐述了基于BP神经网络的数码相机特征化方法。采用不同的神经网络结构,建立了数码相机记录的RGB信息和原影像C IEXYZ色度信息之间的非线性对应关系。对NIKON D200数码相机进行了研究,通过实验得到了合理的神经网络结构为3—10—10—3。测试不同的训练样本和测试样本,达到的C IELAB平均色差和最大色差分别为1.9~2.2和6.7~7.4个色差单位。讨论了实验设备的重复性,同时,分析了样本数量对实验结果的影响。实验结果表明:对数码相机的特征化,可采用BP神经网络技术实现较高的精度。