Summed volume region selection based three-dimensional automatic target recognition for airborne LIDAR

Airborne LIDAR can flexibly obtain point cloud data with three-dimensional structural information,which can improve its effectiveness of automatic target recognition in the complex environment.Compared with 2D information,3D information performs better in separating objects and background.However,an aircraft platform can have a negative influence on LIDAR obtained data because of various flight attitudes,flight heights and atmospheric disturbances.A structure of global feature based 3D automatic target recognition method for airborne LIDAR is proposed,which is composed of offline phase and online phase.The performance of four global feature descriptors is compared.Considering the summed volume region(SVR) discrepancy in real objects,SVR selection is added into the pre-processing operations to eliminate mismatching clusters compared with the interested target.Highly reliable simulated data are obtained under various sensor’s altitudes,detection distances and atmospheric disturbances.The final experiments results show that the added step increases the recognition rate by above 2.4% and decreases the execution time by about 33%.

TWO NEW RECOGNITION METHODS FOR SPATIAL PLANAR POLYGONS

Two new recognition methods for the spatial planar POlygon using perspective invariants are presented. The corss-ratio (R c) of a vetex and the co-base area rotio (RA) of a edge in a spatial planar polygon are proposed and used as the invariant primitive of the recognition eigenvector. The second distance error decision rule (SD EDR) estimating the relative error of RA is introduced also too. The mthods could recognize a spatial planar polygon with an arbitrary orientation through only a single perspective view. Experimental examples are gievn.

Research of the ATR system based on the 3-D models and L-M BP neural network

Automatic target recognition （ATR） is an important issue for military applications, the topic of the ATR system belongs to the field of pattern recognition and classification. In the paper, we present an approach for building an ATR system with improved artificial neural network to recog- nize and classify the typical targets in the battle field. The invariant features of Hu invariant moments and roundness were selected to be the inputs of the neural network because they have the invari- ances of rotation, translation and scaling. The pictures of the targets are generated by the 3-D mod- els to improve the recognition rate because it is necessary to provide enough pictures for training the artificial neural network. The simulations prove that the approach can be implement ed in the ATR system and it has a high recognition rate and can be applied in real time.

Construction of Ship Target Image Library Based on 3DS MAX and AP Algorithm

To achieve accurate classification and recognition of ship target types,it is necessary to establish a sample library of ship targets to be identified.On the basis of exploring the principles of building a ship target image library,the paper determines the sample set.Using 3DS MAX software as the platform,combined with the accurate 3D model of the ship in an offline state,the software fully utilizes its own rendering and animation functions to achieve the automatic generation of multi-view and multi-scale views of ship targets.To reduce the storage capacity of the image database,a construction method of the ship target image database based on the AP algorithm is presented.The algorithm can obtain the optimal cluster number,reduce the data storage capacity of the image database,and save the calculation amount for the subsequent matching calculation.

水下目标识别的1/3倍频程掩蔽谱方法

在对现有水下目标噪声信号分布研究的基础上,基于声学分析中的1/3倍频程分析和人耳的听觉掩蔽效应,提出了1/3倍频程掩蔽谱特征提取方法,并对水下目标辐射噪声进行了特征提取和特征分析。结果表明,不同类的目标,其主频范围有其固定的区域。I类目标的主频一般在100Hz附近,II类目标的主频一般在100Hz和200Hz附近,III类目标的主频一般在450Hz附近。针对从属于三大类目标的29种目标中提取出的1107个样本进行了分类识别实验,识别正确率大于86%,验证了所提出的方法的有效性。

利用卷积神经网络对GF-3输电塔的检测与分类

高压输电塔廊道的快速、大范围监测能力对于国家能源安全战略至关重要。合成孔径雷达遥感技术以其全天时、全天候、穿透能力强等众多优势能够为区域电力基础设施监测提供稳定数据源。但由于复杂的成像机理和大量相干斑噪声的影响,SAR数据的快速智能解译存在一定的困难。为此,提出一个基于深度卷积神经网络的输电塔快速识别分类算法框架。利用我国首颗C频段多极化合成孔径雷达高分三号数据,结合目标检测网络自动标注构建RAD-GFEP输电塔数据集,然后采用基于卷积神经网络的分类算法对该样本集进行分类测试。结果表明,基于深度卷积神经网络的分类算法能够对复杂背景场下SAR微小目标精准识别。在输电塔数据集RAD-GFEP上分类的总体精度达到了98.21%,混淆矩阵的Kappa系数值为0.9729,该结果远远优于传统的视觉算法。研究也表明了国产星载SAR较好的成像能力和利用其进行广域输电塔发现、识别和分类的可行性,在电力基础设施规划、建设、维护和灾后评估等方面展现出了巨大的应用前景。

A High Speed Detection Scheme for Point Targets in a Multitarget Environment

The purpose of this paper is to develop a high speed detection scheme for moving and / or stationary point targets in a multitarget environment as registered in an IR image sequence. An iterative approximate 3-D line searching algorithm based upon the geometric representation of lines (for non-maneuvering targets in space) in a 3-D space is derived. The convergency of the algorithm is proved. An analysis is performed of the theoretical detection performance of the algorithm. The statistical experiment results show high effectiveness and computational efficiency of the algorithm in the case of low SNR. The idea may be employed to satisfy the real-time processing requirement of an IR system.

Computation of Edge-Edge-Edge Events Based on Conicoid Theory for 3-D Object Recognition

The availability of a good viewpoint space partition is crucial in three dimensional （3-D） object recognition on the approach of aspect graph. There are two important events, depicted by the aspect graph approach, edge-：edge-edge （EEE） events and edge-vertex （EV） events. This paper presents an algorithm to compute EEE events by characteristic analysis based on conicoid theory, in contrast to current algorithms that focus too much on EV events and often overlook the importance of EEE events. Also, the paper provides a standard flowchart for the viewpoint space partitioning based on aspect graph theory that makes it suitable for perspective models. The partitioning result best demonstrates the algorithm＇s efficiency with more valuable viewpoints found with the help of EEE events, which can definitely help to achieve high recognition rate for 3-D object recognition.

Recognition of 3-D objects based on Markov random field models

The recognition of 3-D objects is quite a difficult task for computer vision systems.This paper presents a new object framework,which utilizes densely sampled grids with different resolutions to represent the local information of the input image.A Markov random field model is then created to model the geometric distribution of the object key nodes.Flexible matching,which aims to find the accurate correspondence map between the key points of two images,is performed by combining the local similarities and the geometric relations together using the highest confidence first method.Afterwards,a global similarity is calculated for object recognition.Experimental results on Coil-100 object database,which consists of 7200 images of 100 objects,are presented.When the numbers of templates vary from 4,8,18 to 36 for each object,and the remaining images compose the test sets,the object recognition rates are 95.75%,99.30%,100.0%and 100.0%,respectively.The excellent recognition performance is much better than those of the other cited references,which indicates that our approach is well-suited for appearance-based object recognition.

Solution structure of the RNA recognition domain of METTL3-METTL14 N^6-methyladenosine methyltransferase

N^6-methyladenosine(m6A),a ubiquitous RNA modification,is installed by METTL3-METTL14 complex.The structure of the heterodimeric complex between the methyltransferase domains(MTDs)of METTL3 and METTL14 has been previously determined.However,the MTDs alone possess no enzymatic activity.Here we present the solution structure for the zinc finger domain(ZFD)of METTL3,the inclusion of which fulfills the methyltransferase activity of METTL3-METTL14.We show that the ZFD specifically binds to an RNA containing 5'-GGACU-3'consensus sequence,but does not to one without.The ZFD thus serves as the target recognition domain,a structural feature previously shown for DNA methyltransferases,and cooperates with the MTDs of METTL3-METTL14 for catalysis.However,the interaction between the ZFD and the specific RNA is extremely weak,with the binding affinity at several hundred micromolar under physiological conditions.The ZFD contains two CCCH-type zinc fingers connected by an anti-parallel P-sheet.Mutational analysis and NMR titrations have mapped the functional interface to a contiguous surface.As a division of labor,the RNA-binding interface comprises basic residues from zinc finger 1 and hydrophobic residues fromβ-sheet and zinc finger 2.Further we show that the linker between the ZFD and MTD of METTL3 is flexible but partially folded,which may permit the cooperation between the two domains during catalysis.Together,the structural characterization of METTL3 ZFD paves the way to elucidate the atomic details of the entire process of RNA m6A modification.

结合三维电磁散射模型和深度学习的SAR目标识别框架设计

不断提高合成孔径雷达(SAR)图像目标识别能力对于全天时、全天候战场情报侦察具有重要意义。近年来,深度学习模型在SAR目标识别领域得到了广泛应用和验证,但由于SAR图像样本往往十分有限,模型的适应性受到一定制约。提出结合三维电磁散射模型和深度学习的SAR目标识别框架,充分运用三维电磁散射模型在目标SAR数据生成以及物理属性描述方面的优势,提升深度学习模型的分类可靠性和适应性。

基于自旋图的三维自动目标识别

将三维表面匹配领域的自旋图(spin-images)方法运用于扫描激光雷达自动目标识别中,基于自旋图特征,提出了平均最大相似性度量、候选对应关系数目、几何一致性筛选后对应关系数目、分组筛选后最大组的对应关系数目这4个识别指标,并将其组合构成组合识别准则,从而进行三维目标识别。同时针对实际应用需求,进一步研究了点云空间分辨率、激光雷达测距误差以及遮挡对目标识别率的影响,为激光雷达三维目标识别系统的设计提供了参考。

基于Zernike矩的三维目标多视点特性视图建模

目标的模型化是三维目标识别的一个重要环节。由于从多视点特征法建立的模型能够避免从二维图像中恢复目标的三维结构,在三维目标识别中应用比较广泛。使用镶嵌式多面体分割视觉空间以得到三维目标的多视点投影图像,采用较小的镶嵌单元尺寸以完备地描述目标各种姿态的信息。Zernike矩具有旋转不变性,并能够方便地由各阶矩重建图像。计算多面体各个单元的投影图像的Zernike矩,所需的矩的最高阶次由重建图像与原图像的差别确定,通过聚类方式合并那些图像的矩变化很小的投影对应的几个小单元,每个新单元可以提取一幅特性视图,实现较小数目的多视点特性视图的建模。实验证明了这种方法的可行性。

IgY抗体作为导向载体对消化系统肿瘤的选择性识别作用研究

用生物治疗方法治疗肿瘤已被视为肿瘤治疗的第四大疗法，其主要是免疫治疗，包括抗体与偶合物，肿瘤疫苗等。而要想获得有效的肿瘤治疗药物，其关键是要寻找小型化的、高效的导向载体。我们的实验室以低分化腺胃癌的Ｐ１１０癌蛋白作为抗原，免疫ＳＰＦ鸡，从卵黄中提取抗体ＩｇＹ作为植物毒素的导向性载体；实验结果证明，ＩｇＹ能特异性地选择识别消化系统的肿瘤组织。

基于投影降维的激光雷达快速目标识别

激光雷达可以获得目标的三维形状信息,是复杂地面背景下车辆识别的有效手段。提出了一种基于投影降维的快速激光雷达目标识别方法,对检测后提取的疑似目标三维点云数据进行投影降维,得到数字表面模型(DSM)数据,根据轮廓相似性度量值以及尺寸相似度量值构成的组合识别准则进行目标识别。采用8组地面装甲目标的仿真点云数据进行实验,实验表明算法的目标型号识别率高于90%,实时性远优于传统算法。针对实际应用需求,进一步研究了点云空间分辨率,激光雷达成像系统误差对目标识别的影响。

Kinect在现代农业信息领域中的应用与研究进展

2010年微软公司推出的Kinect体感设备不仅在游戏界引起了巨大的轰动,在其它多个研究领域也得到了越来越多的重视。本研究对Kinect在农业信息领域的应用现状和发展趋势做了深入分析,阐述了Kinect在果实目标检测识别、植物三维形态重建、畜牧养殖监督系统及农业虚拟教学等领域的应用,探讨了Kinect在农业领域应用中存在的问题及其在农业应用上的优缺点,并提出了Kinect在信息农业领域未来的发展方向及前沿问题。

基于混合特征提取的易混淆三维目标识别研究

针对易混淆三维目标识别这一问题,通过提取混合特征完成识别;首先获取各类三维目标的若干二维视图,将这些视图放在一起提取它们的大体轮廓特征并进行分类,使得具有相似外形的目标分为一类;然后采用基于统计学的标志矩提取方法提取每类中能分辨各种目标的局部特征,这样特征库就建立了;识别过程中,针对实际要识别的目标,提取它的混合特征并与库中数据进行匹配,确定其类型;算例研究表明,基于混合特征提取的识别系统结构简单、高效。

基于体积特征的空间目标识别算法

提出了基于体积特征的空间目标识别算法,首先通过高分辨力单脉冲雷达对空间目标进行三维成像,然后提取空间目标的三维像体积特征,由于卫星的体积通常比碎片大,根据空间目标的三维像体积可以实现对卫星和碎片的识别。计算机仿真实验表明,该算法取得了比较好的识别效果。

Three-dimensional cooperative guidance laws against stationary and maneuvering targets

This paper presents the cooperative strategies for salvo attack of multiple missiles based on the classical proportional navigation（PN） algorithm.The three-dimensional（3-D） guidance laws are developed in a quite simple formulation that consists of a PN component for target capture and a coordination component for simultaneous arrival.The centralized algorithms come into effect when the global information of time-to-go estimation is obtained, whereas the decentralized algorithms have better performance when each missile can only collect information from neighbors.Numerical simulations demonstrate that the proposed coordination algorithms are feasible to perform the cooperative engagement of multiple missiles against both stationary and maneuvering targets.The effectiveness of the 3-D guidance laws is also discussed.

基于深度卷积神经网络的点云三维目标识别方法研究

为了提高对三维点云目标的识别精确度,提出一种基于深度卷积神经网络(CNN,convolutional neural network)的点云目标识别模型;针对已有的深度卷积点云目标识别网络无法有效提取点云局部拓扑特征的问题,采用迭代最远点采样(FPS,terative farthest point sampling)结合方向卷积编码方式来捕获局部形状特征;并引入空间变换网络(STN,spatial transform network)使点云数据能够自适应进行空间变换和对齐,以解决点云数据旋转性会造成目标识别结果不稳定的问题;实验结果表明:文中提出的点云目标识别方法有效提高了识别精度度,相较于PointNet在ModelNet40和ShapeNetCore两个数据集上分别提高1.2%和1.4%。