基于贝叶斯核主成分分析的远距离地形标记方法

由于非结构化室外场景外观特征分布存在动态不确定性以及映射偏移特性,因此在室外移动机器人自主导航的过程中采用预确定外观特征并不能非常有效地进行地形标记.为了解决此问题,提出了基于贝叶斯核主成分分析(BKPCA)的远距离地形标记方法.该方法融合了基于贝叶斯公式的聚类中心后验概率,且采用自定义的核函数,实现了原始特征数据结构在低维空间上的保持,能够提取出适合当前场景地形标记的外观特征.实验结果表明,BKPCA模型有效地提高了远距离地形标记的精度.     

金隆闪速炉精矿喷嘴的优化

介绍金隆公司闪速炉精矿喷嘴的结构特点和运行情况,针对运行中存在的问题,通过优化操作参数、改进结构,喷嘴的性能得到了很大改善。     

Obtaining complete 2 D view representation of polyhedra using concept of seedling single-view area

This article deals with construction of complete 2 D exact view models of polyhedral objects for visual identification systems. In particular, a new method and an algorithm views generation using the view sphere with perspective concept are described. A set of views generated by this method forms a complete view representation of the object. The method of ensuring completeness of the view representation by controlling covering of the view space (by single-view areas) is used in the presented algorithm. The perspective projection used for calculating the views, the total, tight covering of the view sphere by the single-view areas and -dimensionality of the views ensure, in our opinion, unambiguous and proper identification of polyhedral objects. The method consists in calculating single (any) view, determining the corresponding single-view area (so-called seedling single-view area) and then spiral propagation of neighbouring single-view areas until the whole view sphere is covered by them (i.e., until the border register containing the border between the covered and uncovered parts of the view sphere becomes empty). Having a complete set of single-view areas, we get a complete set of views as well. A method of determining single-view areas for convex polyhedra is also presented.     

地形三维可视化的实现与应用

文中讨论了地形三维可视化的原理，详细介绍了高级编程语言与OpenGL结合开发环境下的地形三维可视化的计算机实现过程。在此基础之上，讨论了基于GRID DEM的应用分析功能的实现,包括等高线、坡度图、通视分析以及淹没分析。为三维地形可视化的实施提出了有效的方案。     

Natural resonance-based feature extraction with reduced aspect sensitivity for electromagnetic target classification

This paper presents a model-based electromagnetic feature extraction technique that makes use of time-frequency analysis to extract natural resonance-related target features from scattered signals. In this technique, the discrete auto-Wigner distribution of a given signal is processed to obtain a partitioned energy density vector with a significantly reduced sensitivity to aspect angle. Each partition of this vector contains, in the approximate sense, spectral distribution of the signal energy confined to a particular subinterval of time. Selection of sufficiently late-time partitions provides target features with a markedly increased target discrimination capacity. The potential of the suggested technique and the practical issues in its implementation are demonstrated by applying it to realistic target classification problems with very encouraging results.     

Iris detection using intensity and edge information

In this paper we propose a new algorithm to detect the irises of both eyes from a face image. The algorithm first detects the face region in the image and then extracts intensity valleys from the face region. Next, the algorithm extracts iris candidates from the valleys using the feature template of Lin and Wu (IEEE Trans. Image Process. 8 (6) (1999) 834) and the separability filter of Fukui and Yamaguchi (Trans. IEICE Japan J80-D-II (8) (1997) 2170). Finally, using the costs for pairs of iris candidates proposed in this paper, the algorithm selects a pair of iris candidates corresponding to the irises. The costs are computed by using Hough transform, separability filter and template matching. As the results of the experiments, the iris detection rate of the proposed algorithm was 95.3% for 150 face images of 15 persons without spectacles in the database of University of Bern and 96.8% for 63 images of 21 persons without spectacles in the AR database.     

小波分析在三维地形数据简化中的应用研究

研究了小波分析在三维地形数据简化中的应用。在分析了小波多分辨率分析理论的基础上,重点探讨了小波多分辨率分析理论在三维地形简化中的应用,提出了实现三维地形数据简化的一种新的方法。     

关于最佳鉴别特征维数问题的讨论

该文对最佳鉴别特征的最佳维数问题进行了详细的讨论．文章首先对最佳维数问题进行了界定，然后指出了两种最佳特征维数为c-1维的情况即以某些基于矩的可分性判据(准则函数)为优化目标的最优特征和以某些特殊的分类器错误率为优化目标的最优特征．最后该文运用方差分析法对最佳鉴别特征进行特征选择使之代入最小距离分类器后识别率最大．     

用遗传BP网络进行图像边缘检测

该文提出了一种基于遗传算法与图像特征向量的边缘检测方法。由于噪声的干扰,常规的图像边缘检测方法往往效果不佳,因此在充分考虑边缘和噪声本质区别的基础上,构造具有较强抗噪能力的特征向量;然后用样本图像对多层前馈神经网络采用遗传学习算法和误差反向传播算法(BP)相结合进行训练,即先用遗传学习算法进行全局训练,再用BP算法进行精确训练,使网络收敛速度加快和避免局部极小。最后,将训练后的网络用于图像的边缘检测。实验证明这种方法是有效的。     

Application of multi-layer perceptron neural networks to vision problems

This paper discusses the application of a class of feed-forward Artificial Neural Networks (ANNs) known as Multi-Layer Perceptrons(MLPs) to two vision problems: recognition and pose estimation of 3D objects from a single 2D perspective view; and handwritten digit recognition. In both cases, a multi-MLP classification scheme is developed that combines the decisions of several classifiers. These classifiers operate on the same feature set for the 3D recognition problem whereas different feature types are used for the handwritten digit recognition. The backpropagationlearning rule is used to train the MLPs. Application of the MLP architecture to other vision problems is also briefly discussed.