Development of cost effective personnel armour through structural hybridization

The objective of the present study is to develop cost effective thermoplastic hybrid laminate using Dyneema® HB50 and Tensylon®HSBD 30A through structural hybridization method. Laminates having 20 mm thickness were fabricated and subjected to 7.62 × 39 mm mild steel core projectile with an impact velocity of 730 ± 10 ms⁻¹. Parameters such as energy absorption, back face deformation and rate of back face deformation were measured as a function of hybridization ratio. It was observed that hybrid laminate with 50:50 ratio (w/w) of Tensylon® and Dyneema® with Tensylon® as front face showed 200% more energy absorption when compared to 100% Tensylon® laminate and showed equal energy absorption as that of expensive 100% Dyneema® laminate. Moreover, hybrid laminate with TD50:50 ratio showed 40% lower in terms of final back face deformation than Dyneema® laminate. Rate of back face deformation was also found to be slow for hybrid laminate as compared to Dyneema® laminate. Dynamic mechanical analysis showed that, Tensylon® laminate has got higher stiffness and lower damping factor than Dyneema® and hybrid laminates. The interface between Tensylon® and Dyneema® layers was found to be separating during the penetration process due to the poor interfacial bonding. Failure behaviour of laminates for different hybridization ratios were studied by sectioning the impacted laminates. It was observed that, the Tensylon® laminate has undergone shear cutting of fibers as major failure mode whereas the hybrid laminate showed shear cutting followed by tensile stretching, fiber pull out and delamination. These inputs are highly useful for body armour applications to design cost effective armour with enhanced performance.     

一种复合模式的人脸识别系统设计

通过综合考察红外 可见光图像人脸识别的优缺点,利用红外温谱图进行人脸检测与识别的优势,在研究可见光和红外人脸温谱图识别技术以及两者融合技术的基础上,提出和设计了一种新的红外 可见光复合模式的人脸识别系统。初步实验结果表明,这种识别方法不论从理论上还是从实验上都是可行的,系统具有良好的识别能力。     

判决特征选择的快速人脸识别算法

为了在确保识别精度的条件下提高人脸识别的速度,提出了判决特征选择算法(SVM-DFS).针对多类分类问题,判决特征选择算法根据统计学习理论使用支持向量机来实现特征选择,根据全概率定理把特征选择和多类分类集成到一个统一框架.在UMIST和FERET人脸数据库上的实验表明:SVM-DFS算法可以用来挑选对分类最有用的特征,这些挑选出来的特征具有明显的物理意义.使用判决特征选择方法不但可以加快分类器的响应速度,而且不降低分类器的泛化能力.     

多特征空间下的支持向量机及其在图像识别中的应用

分别在主成分分析(PCA)、独立成分分析(ICA)和线性鉴别分析(LDA)所构造的特征空间下用模糊支持向量机(FSVM)进行人脸识别。同时,提出了一种改进的FSVM方法,即利用FSVM和多叉决策树相结合的思想来设计人脸分类器,从而使FSVM分类器的速度得到了大幅度的提高。通过在ORL人脸库上的实验结果表明,该算法是有效的。     

虚拟现实系统的建模方法

采用先进的建模方法 ,开发组织和管理复杂的虚拟环境 ,不仅能够提高开发效率 ,甚至关系到项目开发的成败。研究了面向对象和面向智能体两种虚拟现实 (VR)系统设计的基本方法。