Advanced Adaptive Sonar for Mapping Applications

An advanced adaptive sonar module is described, capable of being configured to different circumstances and distances according to reflectors found in the environment. Thanks to the sensory distribution, it is possible to identify three basic types of reflector (planes, edges and corners). Furthermore, a heuristic map of the environment is built. The proposed methods have been computationally optimized, and implemented in a real-time system based on a Field-Programmable Gate Array (FPGA) and a Digital Signal Processor (DSP). Results have been obtained in the detection, classification and mapping of obstacles; and finally testing has been carried out on a commercial vehicle.     

A modular neural network for super-resolution of human faces

This paper presents the original and versatile architecture of a modular neural network and its application to super-resolution. Each module is a small multilayer perceptron, trained with the Levenberg-Marquardt method, and is used as a generic building block. By connecting the modules together to establish a composition of their individual mappings, we elaborate a lattice of modules that implements full connectivity between the pixels of the low-resolution input image and those of the higher-resolution output image. After the network is trained with patterns made up of low and high-resolution images of objects or scenes of the same kind, it will be able to enhance dramatically the resolution of a similar object’s representation. The modular nature of the architecture allows the training phase to be readily parallelized on a network of PCs. Finally, it is shown that the network performs global-scale reconstruction of human faces from very low resolution input images.     

Oxidation-abrasion of TiC-based cermets in SiC medium

The aim of the current study was to investigate the effect of oxidation on abrasive wear behaviour of TiC based cermets at temperatures ranging from 20 to 900 °C. Three types of material performance maps were constructed: oxidation rate maps, wear rate maps and maps showing the effect of oxidation on abrasion. Discussion on the performance of different cermet grades is supported by the SEM images combined with EDS and XRD analysis. The results should facilitate the selection of TiC-based cermets providing optimum composition of cermets for high temperature applications.     

卫星遥感数字图象地理位置纠正、分类与成图研究

本文就MSS图象的地理位置纠正、分类与成图以及有关问题进行论述。在监督分类过程中,提出并采用了“同类分组法”准则和“相对距离阈值”,以提高分类质量。在地理位置纠正方面,分析了MSS图象的畸变因素,对连续性和非连续性畸变都作了纠正。绘图程序设计中考虑了绘图机的成图特点和效率,以提高图件精度和绘图速度。绘制的杭州西湖地区与大门山地区1∶5万彩色分类图质量好,地理位置正确,自动注记出的高斯—克吕格方里网和地形图上的方里网格完全重合,使遥感分类图象“地图化”。     

Bayesian super-resolution of text in videowith a text-specific bimodal prior

To increase the range of sizes of video scene text recognizable by optical character recognition (OCR), we developed a Bayesian super-resolution algorithm that uses a text-specific bimodal prior. We evaluated the effectiveness of the bimodal prior, compared and in conjunction with a piecewise smoothness prior, visually and by measuring the accuracy of the OCR results on the variously super-resolved images. The bimodal prior improved the readability of 4- to 7-pixel-high scene text significantly better than bicubic interpolation and increased the accuracy of OCR results better than the piecewise smoothness prior.     

基于RGB-D图像的室内机器人同时定位与地图构建

同时定位与地图构建（SLAM）是机器人在未知环境实现自主导航的关键技术，针对目前常用的RGB-D SLAM系统实时性差和精确度低的问题，提出一种新的RGB-D SLAM系统，以进一步提升实时性和精确度。首先，采用ORB算法检测图像特征点，并对提取的特征点采用基于四叉树的均匀化策略进行处理，并结合词袋模型（BoW）进行特征匹配。然后，在系统相机姿态初始值估计阶段，结合PnP和非线性优化方法为后端优化提供一个更接近最优值的初始值；在后端优化中，使用光束法平差（BA）对相机姿态初始值进行迭代优化，从而得到相机姿态的最优值。最后，根据相机姿态和每帧点云地图的对应关系，将所有的点云数据注册到同一个坐标系中，得到场景的稠密点云地图，并对点云地图利用八叉树进行递归式的压缩以得到一种用于机器人导航的三维地图。在TUM RGB-D数据集上，将构建的RGB-D SLAM同RGB-D SLAMv2、ORB-SLAM2系统进行了对比，实验结果表明所构建的RGB-D SLAM系统在实时性和精确度上的综合表现更优。     

Steerable pyramid-based face hallucination

In this paper we propose a robust learning-based face hallucination algorithm, which predicts a high-resolution face image from an input low-resolution image. It can be utilized for many computer vision tasks, such as face recognition and face tracking. With the help of a database of other high-resolution face images, we use a steerable pyramid to extract multi-orientation and multi-scale information of local low-level facial features both from the input low-resolution face image and other high-resolution ones, and use a pyramid-like parent structure and local best match approach to estimate the best prior; then, this prior is incorporated into a Bayesian maximum a posterior (MAP) framework, and finally the high-resolution version is optimized by a steepest decent algorithm. The experimental results show that we can enhance a 24×32 face image into a 96×128 one while the visual effect is relatively good.     

计算机辅助网格拼接技术

映射法生成网格一般先分片生成网格，然后不同片上网格拼到一起。此时涉及兼容性问题。本文研究了获得兼容性拼接网格的拼接技术，分三种情况：两片皆为三角形网格、一片为三角形网格，而另一片为四边形网格、两片皆为四边形网格。编制了程序并用数值例子作了验证。     

基于Web的XML与数据库映射

本文讨论了XML与数据之间的结构对比，并介绍了基于Web方式下的XML与数据库之间映射的实例。     

拟向量变分不等式的存在性

讨论了拟向量变分不等式问题，在适当条件下，针对不连续映射得到了拟向量变分不等式的存在性。