基于视频的运动目标检测算法的比较与分析

帧差法和背景差分法是目前常用的基于视频的运动目标检测方法。首先从帧差法和背景差分法中选取了几种具有代表性的算法;然后针对典型场景条件对这些方法进行了实验测试,并利用实验结果对算法进行了定性和定量的比较和分析。实验结果表明,ViBe算法、码本模型、混合高斯模型、自适应混合高斯模型、中值滤波和自适应背景建模具有较好的检测效果,但任何一种方法都有其局限性。     

面元法的红外制导图像边缘检测

红外图像通常存在着噪声大、目标和背景之间具有较小的灰度差、边缘较模糊的特点,使现有的方法不能有效地提取红外图像的边缘。而图像的表面积特征能较好地针对红外图像的这些特征提取出边缘,因此利用图像的表面积特征提出了一种实用的面元边缘检测法。在对图像灰度值变化情况进行分析的基础上,使用了一种十字面积计算公式以满足边缘检测的需要。通过噪声误差对面元法和梯度法计算结果的影响分别进行分析,发现面元法比梯度法的噪声抑制能力至少高两倍,而且在边缘处的噪声抑制能力更高。将面元法几种常用模板算子法的红外图像边缘检测结果进行实际对比后发现,所提出的面元法对红外图像的目标边缘检测能取得良好的结果。     

基于Hough变换的高分辨SAR图像道路目标检测

给出了一种检测高分辨率SAR图像道路目标的方法。该方法首先对原始图像进行一系列的预处理,然后利用Hough变换识别道路。在提取感兴趣区域时,该算法采用了高斯概率迭代方法代替了一般的CFAR检测或阈值分割;在进行Hough变换时,该算法用平均Hough变换代替一般的Hough变换;在检测变换域峰值点时,采用了结合全局CFAR检测的最大值点搜索的方法;最后对检测出来的准道路,该算法根据道路的独具性质进行鉴别,以确定其是否确实为道路。使用MSTARRedstone实测杂波图进行实验,取得了满意的效果。     

水下声源引起的水表面横向微波的理论研究

利用水下声信号在水表面引起的水表面横向微波振幅很小的条件,将普遍的流体力学方程线性化,推导出在水下点声源的激励下,水表面产生的二维横向微波色散关系以及波的传播形式。结果表明,二维水表面的横向微波具有和一维情况类似的结果,即具有波长短、传播速度小的特点,因而可以对入射到表面的激光束进行调制,为水下声信号检测奠定了理论基础。     

自然场景车标数据集的构建及其应用

车标作为车辆身份的关键特征之一,在车辆的监控与辨识中发挥着重要作用。由于自然场景复杂多变,对其中的车标进行准确识别仍具有很大的挑战性。目前公开数据库很少且存在诸多局限,导致研究缺乏可信度和实用性。本文建立了一个面向自然场景的全新数据集,包含多种采集环境下的10 324幅、67类车辆图像。基于此数据集开展应用研究,提出一个目标检测与深度学习相结合的车标识别方法,包括车标区域定位和车标种类预测两大步骤。实验表明,该方法对复杂背景有较强的适应性,在涉及30种车标的分类任务中达到89.0%的总体识别率。     

Bidirectional parallel multi-branch convolution feature pyramid network for target detection in aerial images of swarm UAVs

In this paper, based on a bidirectional parallel multi-branch feature pyramid network (BPMFPN), a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles (UAVs). First, the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers. Next, the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance. In order to validate the effectiveness of the proposed algorithm, experiments are conducted on four datasets. For the PASCAL VOC dataset, the proposed algorithm achieves the mean average precision (mAP) of 85.4 on the VOC 2007 test set. With regard to the detection in optical remote sensing (DIOR) dataset, the proposed algorithm achieves 73.9 mAP. For vehicle detection in aerial imagery (VEDAI) dataset, the detection accuracy of small land vehicle (slv) targets reaches 97.4 mAP. For unmanned aerial vehicle detection and tracking (UAVDT) dataset, the proposed BPMFPN Det achieves the mAP of 48.75. Compared with the previous state-of-the-art methods, the results obtained by the proposed algorithm are more competitive. The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.     

Influence of a liquid-filled compartment structure on the incoming shaped charge jet stability

Liquid-filled compartment structure consists of a bulk steel plate with matrix blind holes which are filled with liquid and a steel front plate to seal up the liquid with rings and bolts.The liquid-filled compart-ment structure can resist the shaped charge warhead effectively.This paper presents experimental and theoretical investigations of the penetration ability of the residual shaped charge jet emerging from the liquid-filled compartment structure after the penetration process at different impact angles.On the basis of shock wave propagation theory,the influence of the liquid-filled compartment structure on jet sta-bility is analysed.The interferences of the liquid backflow caused by a reflected shock wave and a back plate on jet stability under different impact angles are also examined.In addition,the range of the disturbed velocity segments of the jet at different impact angles and the penetration ability of the re-sidual jet are obtained.A theoretical model is validated against the experimental penetration depths.     

Electronic warfare in the optical band: Main features,examples and selected measurement data

The paper presents the possibilities of, and methods for, acquiring, analysing and processing optical signals in order to recognise, identify and counteract threats on the contemporary battleground. The main ways electronic warfare is waged in the optical band of the electromagnetic wave spectrum have been formulated, including the acquisition of optical emitter signatures, as well as ultraviolet (UV) and thermal (IR) signatures. The physical parameters and values describing the emission of laser radiation are discussed, including their importance in terms of creating optical signatures. Moreover, it has been shown that in the transformation of optical signals into signatures, only their spectral and temporal parameters can be applied. This was confirmed in experimental part of the paper, which includes our own measurements of spectral and temporal emission characteristics for three types of binocular laser rangefinders. It has been further shown that through simple registration and quick analysis involving comparison of emission time parameters in the case of UV signatures in “solar-blind” band, various events can be identified quickly and faultlessly. The same is true for IR signatures, where the amplitudes of the recorded signal for several wavelengths are compared. This was confirmed experimentally for UV signatures by registering and then analyzing signals from several events during military exercises at a training ground, namely Rocket Propelled Grenade (RPG) launches and explosions after hitting targets, trinitrotoluene (TNT) explosions, firing armour-piercing, fin-stabilised, discarding sabots (APFSDS) or high explosive (HE) projectiles. The final section describes a proposed model database of emitters, created as a result of analysing and transforming the recorded signals into optical signatures.     

Fracture mechanism of a cylindrical shell cut by circumferential detonation collision

The failure mechanism of a cylindrical shell cut into fragments by circumferential detonation collision was experimentally and numerically investigated. A self-designed detonation wave regulator was used to control the detonation and cut the shell. It was found that the self-designed regulator controlled the fragment shape. The macrostructure and micro-characteristics of fragments revealed that shear fracture was a prior mechanism, the shell fractured not only at the position of detonation collision, but the crack also penetrated the shell at the first contact position of the Chapmen-Jouguet (C-J) wave. The effects of groove number and outer layer thickness on the fracture behavior were tested by simulations. When the thickness of the outer layer was 5–18 mm, it has little effect on fragmentation of the shell, and shells all fractured at similar positions. The increase of the groove number reduced the fracture possibility of the first contact position of the C-J wave. When the groove number reached 7 with a 10 mm outer layer (1/4 model), the fracture only occurred at the position of detonation collision and the fragment width rebounded.     

Numerical investigation on free air blast loads generated from center-initiated cylindrical charges with varied aspect ratio in arbitrary orientation

In current guidelines, the free air blast loads (overpressure and impulse) are determined by spherical charges, although most of ordnance devices are more nearly cylindrical than spherical in geometry. This may result in a great underestimation of blast loads in the near field and lead to an unsafe design. However, there is still a lack of systematic quantitative analysis of the blast loads generated from cylindrical charges. In this study, a numerical model is developed by using the hydrocode AUTODYN to investigate the influences of aspect ratio and orientation on the free air blast loads generated from center-initiated cylindrical charges. This is done by examining the pressure contours, the peak overpressures and impulses for various aspect ratios ranged from 1 to 8 and arbitrary orientation monitored along every azimuth angle with an interval of 5°. To characterize the distribution patterns of blast loads, three regions, i.e., the axial region, the vertex region and the radial region are identified, and the propagation of blast waves in each region is analyzed in detail. The complexity of blast loads of cylindrical charges is found to result from the bridge wave and its interaction with primary waves. Several empirical formulas are presented based on curve-fitting the numerical data, including the orientation where the maximum peak overpressure emerges, the critical scaled distance beyond which the charge shape effect could be neglected and blast loads with varied aspect ratio in arbitrary orientation, all of which are useful for blast-resistant design.