Shadow detection for mobile robots: Features,evaluation, and datasets

ABSTRACT

Shadows have long been a challenging topic for computer vision. This challenge is made even harder when we assume that the camera is moving, as many existing shadow detection techniques require the creation and maintenance of a background model. This article explores the problem of shadow modelling from a moving viewpoint (assumed to be a robotic platform) through comparing shadow-variant and shadow-invariant image features — primarily color, texture and edge-based features. These features are then embedded in a segmentation pipeline that provides predictions on shadow status, using minimal temporal context. We also release a public dataset of shadow-related image sequences, to help other researchers further develop shadow detection methods and to enable benchmarking of techniques.     

一种新的导航星选取算法研究

在导航星表的建立过程中，由于恒星的数量太多，往往要进行筛选，通常这种选择复杂费时，而结果往往并不是最优的。本文引入了动态星等阈值分布函数，将传统星等阈值过滤算法中的静态阈值用动态星等阈值代替，建立了一种新的动态星等阈值过滤选择模式。而基于统计学习理论的支持向量机方法为求解高维非线性动态星等阈值分布函数提供了新的途径。本文讨论了这种基于支持向量机的导航星自动选择算法——回归选取算法。实验表明，用该算法所选取的导航星表，导航星数量少、分布均匀性好。同时它还能适应多种任务的导航星选取要求，具有很强的通用性。     

海上雾霾天气下基于能见度的舰载机目视着舰风险评估方法研究

针对雾霾天气对舰载机目视着舰安全性的影响难以量化的问题,利用激光雷达在近海的能见度观测数据,反演海上雾霾天气下飞行员目视着舰的斜程能见度的状况,提出 1种基于能见度指标的目视着舰风险评估方法,将舰载机着舰过程中飞行员频繁的目测压力,转变为舰上数据测量、风险评估和应对措施等程序化工作,将定性的安全分析转变为定量的风险评估和安全指导,谋求在现有着舰控制模式下有效降低飞行员着舰压力,提升指挥引导效率,为低能见度下舰载机目视着舰训练提供理论依据和实践指导。     

基于ANP数据库的飞机起飞仿真研究

以可视化的方式全面直观的反应其航迹,来检验或者分析飞机起飞过程,为解决飞机噪声问题提供技术理论支持,利用ANP数据库,从中获取各种机型的飞行程序和性能参数,计算飞机起飞航迹及航迹上各点的推力、速度、姿态等,实现了飞机起飞过程及其航迹的三维可视化仿真。     

立体显示技术及其在航空电子系统中的应用

分析了航空电子系统对立体显示技术的需求；介绍了各种立体显示技术的基本原理，并对比了各种立体显示技术的性能特点，提出了航空电子可应用的立体显示技术设想。     

Virtual Reality-based Teleoperation with Robustness Against Modeling Errors

This article investigates virtual reality (VR)-based teleoperation with robustness against modeling errors. VR technology is an effective way to overcome the large time delay during space robot teleoperation. However, it depends highly on the accuracy of model. Model errors between the virtual and real environment exist inevitably. The existing way to deal with the problem is by means of either model matching or robot compliance control. As distinct from the existing methods, this article tries to combine model matching and robot compliance control. On one hand, the status of the virtual robot is corrected by using the position sensor data from robot joints before and during teleoperation, and the pose of the virtually manipulated object is obtained with visual recognition technology. On the other hand, compliance control algorithms of impedance control based on joint torque sensors and hybrid position/force control based on a wrist sensor have been executed in order to eliminate the small sustaining model errors. A VR-based teleoperation system of satellite on-orbit self-serving is built up. In order to verify the proposed method, an experiment deploying the solar panel troubled by malfunction is carried out through teleoperation. It shows that the large model errors are removed with the model matching method and the adopted compliance control is robust against the remaining small model errors.     

IMPROVEMENT OF PHASE GRADIENT AUTOFOCUS ALGORITHM

ＩＭＰＲＯＶＥＭＥＮＴＯＦＰＨＡＳＥＧＲＡＤＩＥＮＴＡＵＴＯＦＯＣＵＳＡＬＧＯＲＩＴＨＭＬｉＬｉｗｅｉ（李立伟），ＭａｏＳｈｉｙｉ（毛士艺），ＡｓｉｆＲａｚａ，ＬｉｕＹｉｎｇ（刘莹）（ＤｅｐａｒｔｍｅｎｔｏｆＥｌｅｃｔｒｏｎｉｃＥｎｇｉｎｅｅｒｉｎｇ...     

无人机载SAR一体化显控系统的设计研究

阐述了无人机载SAR一体化显控系统的设计,对系统实现中应用到的一些关键技术进行了详细说明,就多位面技术、多线程技术及内存映射技术进行了探讨。     

适应拓扑变化的拥塞最小化网络更新策略

软件定义网络的出现推动了航空集群机载网络的发展，同时也为机载网络的一致性更新带来了挑战。针对拓扑变化导致的网络更新期间可用路径失效问题，提出适应拓扑变化的拥塞最小化网络更新策略。首先，为减少可用路径失效带来的数据包丢失，在更新之前采用重路由机制进行处理；然后，针对重路由机制可能引起的网络拥塞，设计了贪婪流迁移算法缓解拥塞；最后，通过瞬时拥塞最小化更新算法完成整个网络更新。仿真结果表明：与传统的拥塞一致性更新算法相比，所提更新策略用规则开销、瞬时网络拥塞方面的少量提高换取了网络更新期间数据包丢失的显著降低。     

基于多步裁定法评估编队超视距空战效能

提出了评估编队歼击机超视距空战效能的多步裁定法。用损失交换比和剩余飞机数量作为效能指标,将最优火力分配与空空反导弹引入到多步裁定模型中。考虑了电子对抗与飞机生存力,计算了歼击机领先发射概率、空空导弹击毁概率和发射次数。算例表明,领先发射一方超视距空战效能通常较高,滞后发射一方若采用最优火力分配、空空反导弹、电子对抗及提高飞机生存力等措施也可提高超视距空战效能。此模型计算简便,合理有效。