HOG-VGG:VGG Network with HOG Feature Fusion for High-Precision PolSAR Terrain Classification

This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain classification.However,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not promising.In fact,edge and shape features play an important role in PolSAR terrain classification.To solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification.HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly elevated.Moreover,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results.The superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen datasets.Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.

Free gait generation method for omnidirectional locomotion on abrupt terrain with multi-legged biomimetic robot

In order to achieve omnidirectional locomotion on rough terrain with multi-legged biomimetic robot,a free gait generation approach is proposed based on local rules.The phase coordinates of each operation leg was established according to the motion task and a universal depiction of leg-end locomotion was implemented;the mathematical relation of gait pattern and walking velocity of multi-legged robot was put forward;combined polynomial curve was adopted to generate the leg-end trajectory,which was capable of accomplishing walking missions and accommodating to landform conditions;a distributed network of local rules for gait control was constructed based on a set of local rules operating between adjacent legs.In the simulation experiments,adaptive regulation of inter-leg phase sequence,omnidirectional locomotion and ground accommodation were realized.Moreover,statically stable free gait was obtained simultaneously,which provided multi-legged robot with the capability of walking on irregular terrain reliably and expeditiously.

面向复杂地形海洋勘探的Multi-AUV编队协同控制策略

针对Multi-AUV编队执行复杂海底地形勘探任务的实际需求和问题,提出Multi-AUV的编队协同控制策略。首先采用领航-跟随思想和反馈线性化方法推导出编队控制律,使Multi-AUV编队可以维持在恒定的几何队形进行巡航,实现高效的并行作业;其次为使搭载的设备获得更佳的扫描效果,引入基于最小二乘法估计的高度控制方法,以保持AUV处在期望的距底高度;然后针对执行梳状探测路径中存在的路径变换和极端地形避障问题提出路径变换优化策略和避障策略,最后通过计算机仿真试验验证提出的编队方法和策略在执行海底复杂地形探测任务中的有效性。

Multi-features Based Approach for Moving Shadow Detection

In the video-based surveillance application, moving shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for shadow detection and suppression used for moving visual object detection. The major novelty of the shadow suppression is the integration of several features including photometric invariant color feature, motion edge feature, and spatial feature etc. By modifying process for false shadow detected, the averaging detection rate of moving object reaches above 90% in the test of Hall-Monitor sequence.

The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST)

The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST, also called the Guo Shou Jing Telescope) is a special reflecting Schmidt telescope. LAMOST’s special design allows both a large aperture (effective aperture of 3.6 m–4.9 m) and a wide field of view (FOV) (5°). It has an innovative active reflecting Schmidt configuration which continuously changes the mirror’s surface that adjusts during the observation process and combines thin deformable mirror active optics with segmented active optics. Its primary mirror (6.67m×6.05 m) and active Schmidt mirror (5.74m×4.40 m) are both segmented, and composed of 37 and 24 hexagonal sub-mirrors respectively. By using a parallel controllable fiber positioning technique, the focal surface of 1.75 m in diameter can accommodate 4000 optical fibers. Also, LAMOST has 16 spectrographs with 32 CCD cameras. LAMOST will be the telescope with the highest rate of spectral acquisition. As a national large scientific project, the LAMOST project was formally proposed in 1996, and approved by the Chinese government in 1997. The construction started in 2001, was completed in 2008 and passed the official acceptance in June 2009. The LAMOST pilot survey was started in October 2011 and the spectroscopic survey will launch in September 2012. Up to now, LAMOST has released more than 480 000 spectra of objects. LAMOST will make an important contribution to the study of the large-scale structure of the Universe, structure and evolution of the Galaxy, and cross-identification of multiwaveband properties in celestial objects.

Dynamic Analysis of the Seafloor Pilot Miner Based on Single-Body Vehicle Model and Discretized Track-Terrain Interaction Model

In order to achieve the complex dynamic analysis of the self-propelled seafloor pilot miner moving on the seafloor of extremely cohesive soft soil and further to make it possible to integrate the miner system with some subsystems to form the complete integrated deep ocean mining pilot system and perform dynamic analysis, a new method for the dynamic modeling and analysis of the miner is proposed and developed in this paper, resulting in a simplified 3D single-body vehicle model with three translational and three rotational degrees of freedom, while the track-terrain interaction model is built by partitioning the track-terrain interface into discrete elements with parameterized force dements built on the theory of terramechanics acting on each discrete dement. To evaluate and verify the correctness and effectiveness of this new modeling and analysis method, typical comparative studies with regard to computational efficiency and solution accuracy are carried out between the traditional modeling method of building the tracked vehicle as a multi-body model and the new modeling method. In full consideration of the particMar structure design of the pilot miner, the special characteristics of the seafioor soil and the hydrodynamic force of near-seafloor currnt, the dynamic simulation analysis of the miner is performed and discussed, which can provide useful guidance and reference for the practical miner system in design and operation. This new method can not only realize the rapid dynamic simulation analysis of the miner but also make possible the integration and rapid dynamic analysis of the complete integrated deep ocean mining pilot system in further researches.

基于路网信息辅助的多星编队系统SAR-GMTI动目标径向速度估计与重定位方法

针对混合多基线系统构型下由动目标高程导致的目标径向速度估计偏差和定位偏差问题,提出一种基于路网信息辅助的动目标径向速度估计与重定位方法。首先,利用目标邻域杂波样本估计动目标的高程干涉相位导向,并结合路网先验信息补偿目标成像位置与其真实位置之间的高程差;然后,采用自适应匹配滤波算法估计目标的径向速度,并进一步将目标径向速度估计及重定位结果与路网信息进行匹配,以消除虚假估计;最后,将目标径向速度估计与重定位结果用于辅助目标高程补偿,并通过迭代处理获得最终结果。基于多星仿真数据的实验结果表明,所提方法能够有效消除目标高程影响,提升多星编队系统在地形起伏背景下的目标径向速度估计和重定位性能。

Large-Scale Terrain Simplification and Visualization Based on TIN

In the preprocessing phase, the global terrain model is partitioned into blocks with their feature points being picked out to generate TIN model for each terrain block, then the multi-resolution models of terrain organized in the form of quad-tree is created bottom-up. Cracks between terrain blocks are avoided by inserting vertices to form common boundaries. At run-time, a view-dependent LOD algorithm is used to control the loading and unloading of the proper blocks by an additional synchronous thread. To eliminate the artifacts created by LOD transitions, geomorphing is used in real-time. These rendering strategies increase the throughput of GPU and avoid imbalance of load among CPU, GPU and Disk I/O. Experimental results show that the system can perform visually smooth rendering of large-scale terrain scenes with fine quality at an average rate of 80 fps.

A 3D Nonhydrostatic Compressible Atmospheric Dynamic Core by Multi-moment Constrained Finite Volume Method

A 3D compressible nonhydrostatic dynamic core based on a three-point multi-moment constrained finite-volume (MCV) method is developed by extending the previous 2D nonhydrostatic atmospheric dynamics to 3D on a terrainfollowing grid. The MCV algorithm defines two types of moments: the point-wise value (PV) and the volume-integrated average (VIA). The unknowns (PV values) are defined at the solution points within each cell and are updated through the time evolution formulations derived from the governing equations. Rigorous numerical conservation is ensured by a constraint on the VIA moment through the flux form formulation. The 3D atmospheric dynamic core reported in this paper is based on a three-point MCV method and has some advantages in comparison with other existing methods, such as uniform third-order accuracy, a compact stencil, and algorithmic simplicity. To check the performance of the 3D nonhydrostatic dynamic core, various benchmark test cases are performed. All the numerical results show that the present dynamic core is very competitive when compared to other existing advanced models, and thus lays the foundation for further developing global atmospheric models in the near future.

A Comparative Study of Acute Hemodynamic Effects of Multi -site Cardiac Pacing in patients with cardiac function NYHA class ⅠtoⅡ without bundle branch block

Objective To compare the acute hemodynamic effects of five different pacing modes in patients with cardiac function NYHA class Ⅰ to Ⅱ without bundle branch block (BBB). Methods This study included 12 patients (SSS 7, Ⅲ°AVB 5) undergoing pacemaker implantation. Right ventricular apex (RVA), right ventricular outflow tract (RVOT), right ventricular bifocal (RV-Bi), left ventricular base (LVB) and bi -ventricular (Bi-Ⅴ) pacing at 60 -80 ppm were done in VVI mode prior to implantation of DDD pacemaker. The cardiac index (CI), mean pulmonary artery pressure (mPAP) and pulmonary capillary wedge pressure (PCWP) were measured with Swan - Ganz thermodilution catheter after 5 minutes of each pacing mode. Results (1) Comparing to pacing at RVA (CI: 2. 41± 0. 38 L/min per m2, PCWP: 16. 7 ±3.3 mmHg), the CI increased and the PCWP decreased significantly in pacing at RVOT(CI: 2. 63 ± 0.46, PCWP: 13. 8±2. 3), LVB(CI: 2. 78±0.52, PCWP: 14. 4±3.1), RV-Bi(CI: 2. 83±0.57, PCWP: 12. 8± 2. 5) and Bi -Ⅴ pacing (CI: 2. 94± 0.60, PCWP: 12. 7±2. 5), P < 0. 01, respectively. (2) The CI of RV-Bi and Bi-Ⅴ pacing was higher than that of RVOT and LVB pacing, the PCWP was lower, P < 0. 05, respectively. (3) There was no significant difference between RV - Bi pacing and Bi-Ⅴ pacing in CI and PCWP. Conclusion There is no significant difference between RV - Bi pacing and Bi -V pacing in the acute hemodynamic effects; however,dual - site pacing is much better than single site pacing in that aspect for patients with cardiac function NYHA class Ⅰ to Ⅱ without BBB. Among single site pacing, the RVOT and LVB pacing is better than RVA pacing in cardiac function.

Research on A Master - slave Multi - microcomputers Control System for Hollow Spindle Fancy Yarn Spinning Machine

In this paper, a successfully studied and developed master - slave muld - microcomputers control system based on PC - BUS for hollow spindle fancy yarn spinning machine, mainly Its overall scheme, software and hardware construction, is introduced. Spinning experiments show that the system achieves satisfactory result. This system can solve the diftkultles of mechatronical fusion between domestic hollow splndk fancy yarn spuming muchine and its microcomputer control technology.

On the Representation of Multi-layer Woven Structure

A quantitative method is developed to identify the structures of multi-layer woven fabric in this study. Six structural parameters are selected to represent the fabric structure. With some design criteria for the reinforcement of textile composites, the relationships among the structural parameters are derived for different binding patterns of the fabric structure. The conditions, which meet the requirements of structural cell stability,are also discussed.

Computer-aided Pattern Design of Multi-bar Warp Knitted Fabrics

To meet the development trend of multi-bar warp knit-ting machine towards high-speed,advanced technologyand computer control and the requirements of variousproducts with small quantity,there are many researcheson the computer-aided pattern design of multi-barwarp knitted fabrics.In terms of the special propertiesof the computer-aided pattern design of multi-barwarp knitted fabrics,the Object Oriented Program(OOP)programming-Object Windows class Library(OWL)programming is selected.According to thecharacters of the OWL programming,various functionsare defined.Pattern design and technical parameters canbe output,which offers a great convenience for the fac-tory.

MODS： A Novel Metaheuristic of Deterministic Swapping for the Multi-Objective Optimization of Combinatorials Problems

This paper states a new metaheuristic based on Deterministic Finite Automata （DFA） for the multi - objective optimization of combinatorial problems. First, a new DFA named Multi - Objective Deterministic Finite Automata （MDFA） is defined. MDFA allows the representation of the feasible solutions space of combinatorial problems. Second, it is defined and implemented a metaheuritic based on MDFA theory. It is named Metaheuristic of Deterministic Swapping （MODS）. MODS is a local search strategy that works using a MDFA. Due to this, MODS never take into account unfeasible solutions. Hence, it is not necessary to verify the problem constraints for a new solution found. Lastly, MODS is tested using well know instances of the Bi-Objective Traveling Salesman Problem （TSP） from TSPLIB. Its results were compared with eight Ant Colony inspired algorithms and two Genetic algorithms taken from the specialized literature. The comparison was made using metrics such as Spacing, Generational Distance, Inverse Generational Distance and No-Dominated Generation Vectors. In every case, the MODS results on the metrics were always better and in some of those cases, the superiority was 100%.

基于激光SLAM多地形机器人的设计

为解决传统轮式机器人在复杂地形中受限与腿式机器人控制策略复杂的问题,提出一种多地形机器人。结合激光即时定位与地图构建(SLAM)方法和自适应式轮腿机构,将树莓派作为运算单元,搭载(ROS)机器人操作系统,应用激光SLAM技术实现环境地图构建和机器人导航,同时结合深度模型和摄像头完成图像任务。自适应式轮腿机械结构使机器人能够根据环境需求自动切换为轮式或腿式行进模式。底层控制器采用STM32F407,机器人通过PID算法能实现精准的移动和机械臂作业。结果表明:该多地形机器人控制方法简单高效,在坡地、草地、坑地、台阶障碍物等复杂地形中展现了灵活移动的能力,最大翻越障碍高度可达250 mm,爬坡角度可达45°,在稳定性和适应性方面具有显著优势。

基于机载多角度InSAR技术的复杂地形高精度DEM重建方法

干涉合成孔径雷达(Interferomtric Synthetic Aperture Radar,InSAR)是全天时、全天候获取三维地表信息重要的技术手段。机载InSAR系统具有机动灵活、多角度获取数据的优势,可以高效率、高精度获取数字高程模型(Digital Elevation Model,DEM)数据。但是,在地形复杂区域,InSAR侧视成像易在地形陡峭区域形成较大范围的阴影和严重的叠掩现象,阴影和叠掩区域在SAR图像上体现为信息的丢失,从而导致DEM数据大面积无效数据的存在,严重影响DEM数据的质量及应用。针对这一问题,本文提出了基于机载多角度InSAR技术的复杂地形高精度DEM重建方法,基于考虑地形起伏的机载多角度InSAR数据获取任务规划设计,最大程度的避免阴影和叠掩导致的无效数据;基于高精度InSAR数据处理,保证每个角度DEM数据精度的高度一致性;基于快速多角度DSM数据融合与滤波处理,实现多角度InSAR体制复杂地形DEM高精度重建。本文以四川省西部山区大坡度、非连续等复杂地形为例,基于本文提出的方法,利用3个角度InSAR数据融合处理,生成了高精度DEM数据,试验结果表明,本文提出的方法获取复杂地形DEM数据高程均方根误差为0.6 m,同时,数据有效率大于99%。

面向关隘地形的分层调度多机器人路径规划

针对关隘地形下多机器人路径规划存在的高度耦合性,引入调度次序优化思想构造了分层的多机器人路径求解与优化算法。首先,在优化层采用遗传算法生成所有机器人的调度次序,并根据适应度对调度次序进行迭代和进化。其次,根据优化层制定的调度次序,在规划层采用改进的层级协作A*(IHCA*)算法进行路径求解,并将求解结果返回上层以对该次序的适应度进行更新。最后,通过上下层相互配合,逐步提升问题求解成功率并降低路径耗时。此外,提出搜索熔断机制,避免原始HCA*算法在关隘地形中陷于反复无效搜索的状态,可进一步提升求解效率。研究结果表明,所提算法在高耦合关隘环境下具有较高的求解成功率,且路径总耗时更少。

基于多任务强化学习的地形自适应模仿学习方法

地形自适应能力是智能体在复杂地形条件下稳定运动的基础,而由于机器人动力学系统的复杂性,传统逆动力学方法通常难以使其具备这种能力。现有利用强化学习在解决序列决策问题上的优势训练智能体地形适应能力的单任务学习方法无法有效学习各类地形中的相关性。事实上,复杂地形自适应任务可以认为是一种多任务,子任务间的关系可以用不同地形影响因素来衡量,通过子任务模型的相互学习解决数据分布信息获取不全面的问题。基于此,本文提出一种多任务强化学习方法。该方法包含1个由子任务预训练模型组成的执行层和1个基于强化学习方法、采用软约束融合执行层模型的决策层。在LeggedGym地形仿真器上的实验证明,本文方法训练的智能体运动更加稳定,在复杂地形上的摔倒次数更少,并且表现出更好的泛化性能。

基于PPMU-net的多特征高分辨率遥感道路提取

针对复杂地形条件下道路特征选取不具代表性,分割精度低的问题,提出了一种基于卷积神经网络(PPMUnet)的高分辨率遥感道路提取的方法。将3通道的高分二号光谱信息与相应的地形信息(坡度、坡向、数字高程信息)进行多特征融合,合成6通道的遥感图像;对多特征的遥感图像进行切割并利用卷积网络(CNN)筛选出含道路的图像;将只含道路的遥感图像送进PPMU-net中训练,构建出高分辨率遥感图像道路提取模型。在与U-net神经网络、PSPnet神经网络相比时,所提的方法在对高分辨率遥感道路提取时能够达到较好的效果,提高了复杂地形条件下道路分割的精度。

一种多运动模式的软体爬行机器人

为了提高软体机器人对复杂地形的适应能力,提出了一种具有多运动模式的软体爬行机器人。首先,分别利用聚乙烯材质与聚丙烯材质的波纹管设计了软体爬行机器人的转向伸缩执行器与弯曲执行器,并通过浇注成型与3D打印技术制造了软体爬行机器人样机;其次,分析软体爬行机器人的平面直行、平面转向和平面杆过渡等运动模式,研究了软体爬行机器人的运动步态规律;再次,基于常曲率假设,分析压强与执行器弹性变形的关系,建立了执行器的运动学模型;最后,通过运动学试验,验证了执行器运动学模型的正确性,检验了软体爬行机器人在多模式下的运动能力。